{"as_of":"2026-08-16T20:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2d9f326c938f6a761ff3a4f5c5c0e603c56dd43e082201a49d3eb81739daf12c","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T11:36:29.802225Z","state":"measured"},{"denominator":118,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":118,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":66,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":66,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T12:17:20.973338Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-08T11:24:54.882129Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2004.10934","last_updated":"2020-04-23T02:10:02Z","snapshot_observed_at":"2026-08-16T04:20:57.069798Z","submitted_at":"2020-04-23T02:10:02Z","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-12T14:34:24.456280Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2004.10934"},"observation_digest":"sha256:5288dcb9bcb6a31fa251cc52dc8bdb20bd1bfe18e77e768883dd8d908e45ba54","observation_id":"1c2b5420-62fc-4cd0-86aa-c97b1d5d5ec4","resolution":{"observed_at":"2026-05-12T14:34:24.571684Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2310.16828","last_updated":"2024-03-21T17:56:19Z","snapshot_observed_at":"2026-07-31T05:32:29.431480Z","submitted_at":"2023-10-25T17:57:07Z","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","version":2},"reference_index":176,"source":"arxiv_source","source_observed_at":"2026-05-14T17:27:35.733800Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2310.16828"},"observation_digest":"sha256:09f2f0af0b017aafa1f6dca8aa630d2b500c9350bd419c6590139c82c7fd38a0","observation_id":"1ab868de-60e3-4385-97e3-e95cddc466a7","resolution":{"observed_at":"2026-05-14T17:27:35.976929Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-11T21:42:21.485064Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.04246","last_updated":"2025-01-24T02:48:14Z","snapshot_observed_at":"2026-08-15T13:35:31.253896Z","submitted_at":"2024-12-05T15:27:56Z","title":"Ternary Stochastic Neuron -- Implemented with a Single Strained Magnetostrictive Nanomagnet","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T21:42:21.485064Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2412.04246"},"observation_digest":"sha256:40516b7a5345bbfc54d7cc71fb142e05696ff631a5d4caf4abef828dfbf08239","observation_id":"22966b41-bb6e-440d-a4f2-398901d361b3","resolution":{"observed_at":"2026-08-11T21:42:21.485064Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-11T19:03:05.995881Z","title":null,"venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2412.07224","last_updated":"2024-12-10T06:19:21Z","snapshot_observed_at":"2026-08-15T21:58:58.430697Z","submitted_at":"2024-12-10T06:19:21Z","title":"Parseval Regularization for Continual Reinforcement Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T19:03:05.995881Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2412.07224"},"observation_digest":"sha256:a61d618ff1162dd786b32465ee558dca42af6bbab308a181694300fb97e30a93","observation_id":"6e9645b1-bb8b-430c-a0fa-e896b61f0dbe","resolution":{"observed_at":"2026-08-11T19:03:05.995881Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-10T22:45:00.038936Z","title":null,"venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2501.00811","last_updated":"2025-01-01T11:46:54Z","snapshot_observed_at":"2026-08-16T05:29:24.325183Z","submitted_at":"2025-01-01T11:46:54Z","title":"Regression Guided Strategy to Automated Facial Beauty Optimization through Image Synthesis","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T22:45:00.038936Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2501.00811"},"observation_digest":"sha256:0d97facf9e7a3fc0641bd23103ed334f1a8d09ba3a24bcf311e9bf780d404e7c","observation_id":"8e20f70d-8d4d-4aca-a82d-fb82c1e4ada3","resolution":{"observed_at":"2026-08-10T22:45:00.038936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2501.05465","last_updated":"2026-05-14T16:52:31Z","snapshot_observed_at":"2026-08-14T18:35:28.225116Z","submitted_at":"2025-01-03T19:53:57Z","title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","version":2},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-05-23T05:47:48.488826Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2501.05465"},"observation_digest":"sha256:2329d5ca4505982b123f992e2e73641855a21ef527af0677ec9eba29277b9c80","observation_id":"22401449-ba7b-4b90-b2e5-6756d56417fa","resolution":{"observed_at":"2026-05-23T05:52:37.465652Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-10T20:18:25.575154Z","title":"Misra, Mish: A self regularized nonmonotonic activation function (2020), arXiv:1908.08681 [cs.LG]","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.08966","last_updated":"2025-01-15T17:23:21Z","snapshot_observed_at":"2026-08-16T06:00:19.588102Z","submitted_at":"2025-01-15T17:23:21Z","title":"Reconstructing Time-of-Flight Detector Values of Angular Streaking Using Machine Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T20:18:25.575154Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2501.08966"},"observation_digest":"sha256:fd6e64dc02fcf65925cdb3ccc4224acc92fce4337bd78d2ef85bad4e465b0f3a","observation_id":"499905e2-63d4-4333-9138-fff193ae79d8","resolution":{"observed_at":"2026-08-10T20:18:25.575154Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-10T18:14:00.745289Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.11540","last_updated":"2025-01-20T15:25:17Z","snapshot_observed_at":"2026-08-11T18:15:55.674745Z","submitted_at":"2025-01-20T15:25:17Z","title":"A Hands-free Spatial Selection and Interaction Technique using Gaze and Blink Input with Blink Prediction for Extended Reality","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T18:14:00.745289Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2501.11540"},"observation_digest":"sha256:8029f8224aac3e21509e8ab21d49b254056d918dbc25bf91fee92c9d3550e7f0","observation_id":"17db94a0-97fe-47aa-8792-72e643bab166","resolution":{"observed_at":"2026-08-10T18:14:00.745289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-10T16:15:39.481878Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.13428","last_updated":"2026-06-01T01:21:19Z","snapshot_observed_at":"2026-08-15T21:59:40.323843Z","submitted_at":"2025-01-23T07:21:08Z","title":"Softplus Attention with Re-weighting Boosts Length Extrapolation in Large Language Models","version":6},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-10T16:15:39.481878Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2501.13428"},"observation_digest":"sha256:37c182f1c7c61edac9b52b32d27e5e2c93c5ead7dc0625d5a2055b04a8234f60","observation_id":"53c1ade8-1970-4297-8ee3-ef44a3de66a1","resolution":{"observed_at":"2026-08-10T16:15:39.481878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-10T15:52:17.656980Z","title":"Mish: A self regularized non-monotonic activation function","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2501.14000","last_updated":"2025-04-25T05:19:40Z","snapshot_observed_at":"2026-08-10T15:46:22.709647Z","submitted_at":"2025-01-23T11:34:25Z","title":"Local Control Networks (LCNs): Optimizing Flexibility in Neural Network Data Pattern Capture","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-10T15:52:17.656980Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2501.14000"},"observation_digest":"sha256:c861c8e520d0ab755588194429f5404b2fe7327295db583a63a97bc831ed8d34","observation_id":"1f3f4444-892e-4ca8-91e1-949e6653f562","resolution":{"observed_at":"2026-08-10T15:52:17.656980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-09T13:24:22.955377Z","title":"Mish: A self regularized non-monotonic neural activation function","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2502.02103","last_updated":"2025-02-04T08:35:57Z","snapshot_observed_at":"2026-08-15T13:59:53.424388Z","submitted_at":"2025-02-04T08:35:57Z","title":"Neural Networks Learn Distance Metrics","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-09T13:24:22.955377Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2502.02103"},"observation_digest":"sha256:b87c8f732055b4b255848d237c92649d30ef5474dbe49dba816a02ea71ff28eb","observation_id":"253a7c72-92bf-460e-8071-8503e3ad9007","resolution":{"observed_at":"2026-08-09T13:24:22.955377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-09T04:17:04.778491Z","title":"Mish: A self regularized non-monotonic activation function","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2502.03654","last_updated":"2025-05-21T15:36:14Z","snapshot_observed_at":"2026-08-16T01:26:18.931270Z","submitted_at":"2025-02-05T22:32:22Z","title":"Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-09T04:17:04.778491Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2502.03654"},"observation_digest":"sha256:1a6ddfe840697c18f8cbae5ed7988dd0133fc79e69e1fa9f6b257c4e83de4616","observation_id":"1bfc6acc-d79a-4a41-8a2b-caba8a8910a2","resolution":{"observed_at":"2026-08-09T04:17:04.778491Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-09T00:36:02.823268Z","title":"Mish: A self regularized non-monotonic activation function,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2502.03845","last_updated":"2025-02-06T07:55:24Z","snapshot_observed_at":"2026-08-15T22:58:36.437322Z","submitted_at":"2025-02-06T07:55:24Z","title":"PAGNet: Pluggable Adaptive Generative Networks for Information Completion in Multi-Agent Communication","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-09T00:36:02.823268Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2502.03845"},"observation_digest":"sha256:40d903d0e97df5066224c2678de350ba93dd982f4ce717871fb7431f8a2f308e","observation_id":"485639cf-2548-45c7-bd80-25388ee87c7d","resolution":{"observed_at":"2026-08-09T00:36:02.823268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-08T10:14:31.675916Z","title":"Mish: A self regularized non-monotonic activation func- tion,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2502.08169","last_updated":"2025-02-12T07:23:26Z","snapshot_observed_at":"2026-08-13T18:47:02.811371Z","submitted_at":"2025-02-12T07:23:26Z","title":"CoDynTrust: Robust Asynchronous Collaborative Perception via Dynamic Feature Trust Modulus","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-08T10:14:31.675916Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2502.08169"},"observation_digest":"sha256:3e51d64887bd620e7f1b19520724a346ce1700fa79e723435a5b5d2cfa058d75","observation_id":"2106b4ee-9ce9-4e78-b0b9-515d453b673e","resolution":{"observed_at":"2026-08-08T10:14:31.675916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-07T23:32:55.658655Z","title":"Mish: A self regularized non-monotonic activation function","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2502.08858","last_updated":"2025-02-13T00:18:08Z","snapshot_observed_at":"2026-08-13T18:08:13.613824Z","submitted_at":"2025-02-13T00:18:08Z","title":"Estimating Probabilities of Causation with Machine Learning Models","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T23:32:55.658655Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2502.08858"},"observation_digest":"sha256:1cca3a31c3aac18942e0c60d53c027083f660dd45401a7adf253b22bfccbdf61","observation_id":"cfe4bc50-daeb-4a50-ab88-a0b5466b851c","resolution":{"observed_at":"2026-08-07T23:32:55.658655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-16T12:17:20.973338Z","title":"Mish: A self regularized non-monotonic neural acti- vation function,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2504.13112","last_updated":"2025-04-17T17:26:29Z","snapshot_observed_at":"2026-08-16T12:12:16.712500Z","submitted_at":"2025-04-17T17:26:29Z","title":"Hadamard product in deep learning: Introduction, Advances and Challenges","version":1},"reference_index":279,"source":"pdf_text","source_observed_at":"2026-08-16T12:17:20.973338Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2504.13112"},"observation_digest":"sha256:c73bb2ccedf5d4ea58f7df0be031b705a7a06c0979047e7139914eba56d5bb01","observation_id":"188a5cb1-133c-49b8-aa3a-1dd1cb97dcc6","resolution":{"observed_at":"2026-08-16T12:17:20.973338Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-16T11:24:23.128686Z","title":"Mish: A self regularized non-monotonic neural ac- tivation function,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2504.16146","last_updated":"2026-06-22T02:11:42Z","snapshot_observed_at":"2026-08-16T11:13:35.232881Z","submitted_at":"2025-04-22T13:13:35Z","title":"Active RIS-Empowered Covert Satellite-Terrestrial Communications","version":4},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T11:24:23.128686Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2504.16146"},"observation_digest":"sha256:2396af317b905a17b2ff1df12f947f864d451d00b77c04e968bed14f027185c3","observation_id":"1318bce5-077b-44a3-9270-d4be664f95ac","resolution":{"observed_at":"2026-08-16T11:24:23.128686Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-16T06:06:08.868618Z","title":"Mish: A self regularized non-monotonic activation function,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2504.19074","last_updated":"2025-04-27T02:04:49Z","snapshot_observed_at":"2026-08-16T10:03:22.914576Z","submitted_at":"2025-04-27T02:04:49Z","title":"Dual-Branch Residual Network for Cross-Domain Few-Shot Hyperspectral Image Classification with Refined Prototype","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T06:06:08.868618Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2504.19074"},"observation_digest":"sha256:ce9ea8656ddf4a4aff938c43193fed46bd5b91e3e789a4e218bb6b0407b39e2c","observation_id":"fe12f69c-07e6-4705-83aa-8c4cc74f3d9d","resolution":{"observed_at":"2026-08-16T06:06:08.868618Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-16T05:37:11.772540Z","title":"Mish: A self regularized non-monotonic activation function,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2504.20383","last_updated":"2026-06-29T14:02:23Z","snapshot_observed_at":"2026-08-16T05:28:18.021705Z","submitted_at":"2025-04-29T03:04:09Z","title":"Neural Stereo Video Compression with Hybrid Disparity Compensation","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-16T05:37:11.772540Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2504.20383"},"observation_digest":"sha256:a202cefd2463cf0a14fe87457cfb0e8c17d16a45db3855a33079db757c65559b","observation_id":"58ed05f9-02c9-4536-a56c-1e9991973389","resolution":{"observed_at":"2026-08-16T05:37:11.772540Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-15T21:33:59.049816Z","title":"Mish: A self regularized non-monotonic activation function","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2505.09486","last_updated":"2025-05-14T15:36:51Z","snapshot_observed_at":"2026-08-15T21:27:39.495336Z","submitted_at":"2025-05-14T15:36:51Z","title":"Preserving Plasticity in Continual Learning with Adaptive Linearity Injection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T21:33:59.049816Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2505.09486"},"observation_digest":"sha256:606c11322b8beedb9b25d5bb0b90c0bbfd93a308a231a3db3fdfdc3e9af256af","observation_id":"ffc06570-4494-4429-8e4f-45d03ec796a8","resolution":{"observed_at":"2026-08-15T21:33:59.049816Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-07T15:42:50.478554Z","title":"Seohong Park, Qiyang Li, and Sergey Levine","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2505.14139","last_updated":"2025-05-20T09:43:05Z","snapshot_observed_at":"2026-08-11T22:28:18.522157Z","submitted_at":"2025-05-20T09:43:05Z","title":"FlowQ: Energy-Guided Flow Policies for Offline Reinforcement Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:50.478554Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2505.14139"},"observation_digest":"sha256:2ba3957205395e4e973dd98a1065a849303f0312e8ac7d5be373a0c672711b4f","observation_id":"ccf2fe4e-d7b2-4ccc-9501-c01f458b10c6","resolution":{"observed_at":"2026-08-07T15:42:50.478554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-07T14:44:31.214961Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.17999","last_updated":"2025-05-28T14:16:45Z","snapshot_observed_at":"2026-08-07T15:58:33.131228Z","submitted_at":"2025-05-23T15:04:16Z","title":"Revisiting Feature Interactions from the Perspective of Quadratic Neural Networks for Click-through Rate Prediction","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T14:44:31.214961Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2505.17999"},"observation_digest":"sha256:1f1b5c4cc6398b7877f0f80bab18e5efe115ce1f41e98857bfe67baceb709902","observation_id":"7e9c9ffe-095d-489f-8dd0-3db0f473a863","resolution":{"observed_at":"2026-08-07T14:44:31.214961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-07T12:42:03.531466Z","title":"Mish: A self regularized non-monotonic neural activation function","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2505.23942","last_updated":"2025-05-29T18:48:18Z","snapshot_observed_at":"2026-08-14T14:45:39.133727Z","submitted_at":"2025-05-29T18:48:18Z","title":"SG-Blend: Learning an Interpolation Between Improved Swish and GELU for Robust Neural Representations","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T12:42:03.531466Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2505.23942"},"observation_digest":"sha256:bd4f50052a0ec958efe914eecc9b53b8b0dd724dfdda2071ee7a1058bdfd1ba2","observation_id":"1e33387b-a5cd-4fe0-8ccc-6ff22f0ce5a7","resolution":{"observed_at":"2026-08-07T12:42:03.531466Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-07T12:24:12.307546Z","title":"Mish: A self regularized non-monotonic neural activation function,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2505.24576","last_updated":"2025-05-30T13:26:42Z","snapshot_observed_at":"2026-08-13T03:53:46.630334Z","submitted_at":"2025-05-30T13:26:42Z","title":"A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancement","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T12:24:12.307546Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2505.24576"},"observation_digest":"sha256:19214e56258ae6e71121bdaceb7e924e73ea6cac6970e6cf39f0d2663a41f3df","observation_id":"4bcfc627-8130-47e1-9fa1-c0cc91ef5ad8","resolution":{"observed_at":"2026-08-07T12:24:12.307546Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-07T00:26:31.146060Z","title":"Mish: A self regularized non-monotonic neural activation function","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2506.14095","last_updated":"2025-06-18T12:59:54Z","snapshot_observed_at":"2026-08-12T19:49:45.784799Z","submitted_at":"2025-06-17T01:19:28Z","title":"Transformers Learn Faster with Semantic Focus","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-07T00:26:31.146060Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2506.14095"},"observation_digest":"sha256:b02d07b13752bb50b8431d0b1e21100308e49383a030f952980136a8bd09a14f","observation_id":"bfb46c1d-85a6-4889-b1b2-37873f04faca","resolution":{"observed_at":"2026-08-07T00:26:31.146060Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-06T20:59:05.887630Z","title":"A Self Regularized Non-Monotonic Activation Function","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2507.01381","last_updated":"2025-07-11T03:34:59Z","snapshot_observed_at":"2026-08-08T15:34:59.587782Z","submitted_at":"2025-07-02T05:50:10Z","title":"Distributional Soft Actor-Critic with Diffusion Policy","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T20:59:05.887630Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2507.01381"},"observation_digest":"sha256:d2e61ae464db972be6c57cdec6b24d8ed0141322c47087c7d73e48c95d936359","observation_id":"0aedb8d0-db2f-4d98-a80f-e8afb80d309d","resolution":{"observed_at":"2026-08-06T20:59:05.887630Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-06T20:17:52.339417Z","title":"Mish: A self regularized non-monotonic activation function","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2507.03393","last_updated":"2025-07-04T08:54:59Z","snapshot_observed_at":"2026-08-16T08:24:04.392762Z","submitted_at":"2025-07-04T08:54:59Z","title":"Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-06T20:17:52.339417Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2507.03393"},"observation_digest":"sha256:d2d68c37d0eedf3d2066c3d32f33eb1881ea294eea4583dae6041dfc5fb376c1","observation_id":"14dc7594-b590-424b-9a4a-e7106257ff0c","resolution":{"observed_at":"2026-08-06T20:17:52.339417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-06T19:14:18.599866Z","title":"In Advances in neural information processing systems, pages 1097–1105","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2507.06148","last_updated":"2025-07-08T16:29:14Z","snapshot_observed_at":"2026-08-14T02:00:31.652295Z","submitted_at":"2025-07-08T16:29:14Z","title":"SoftReMish: A Novel Activation Function for Enhanced Convolutional Neural Networks for Visual Recognition Performance","version":1},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:18.599866Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2507.06148"},"observation_digest":"sha256:feb0fa043f6b81f43687eb796827ad5caa9aec00773bea03622008f24d6bb650","observation_id":"68d0dc3c-55b4-4864-950f-1327c3810744","resolution":{"observed_at":"2026-08-06T19:14:18.599866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-06T17:47:42.043659Z","title":"Mish: A self regularized non-monotonic acti- vation function,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2507.10026","last_updated":"2025-07-14T08:06:58Z","snapshot_observed_at":"2026-08-06T17:39:12.191621Z","submitted_at":"2025-07-14T08:06:58Z","title":"EAT: QoS-Aware Edge-Collaborative AIGC Task Scheduling via Attention-Guided Diffusion Reinforcement Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:42.043659Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2507.10026"},"observation_digest":"sha256:4d2ff40cff2660d54b76a270ad993eb5f4972b7e2fabb461290da91893753427","observation_id":"acb26513-50c1-491a-ae3d-b0f233393eb6","resolution":{"observed_at":"2026-08-06T17:47:42.043659Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-06T20:42:01.089597Z","title":"Mish: A Self Regularized Non-Monotonic Neural Activation Function","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2507.10560","last_updated":"2025-07-02T21:01:27Z","snapshot_observed_at":"2026-08-13T20:39:58.575088Z","submitted_at":"2025-07-02T21:01:27Z","title":"Tangma: A Tanh-Guided Activation Function with Learnable Parameters","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T20:42:01.089597Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2507.10560"},"observation_digest":"sha256:a1c4d12e97877db11ce73dad620e6b9f0cca5efa683227f8369d9c2ccd52fb37","observation_id":"8f11c8db-8397-4935-80fa-c20a6690caac","resolution":{"observed_at":"2026-08-06T20:42:01.089597Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-06T15:48:43.299681Z","title":"Mish: A self regularized non-monotonic activation function,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2507.14951","last_updated":"2025-07-20T13:19:43Z","snapshot_observed_at":"2026-08-14T17:31:30.778735Z","submitted_at":"2025-07-20T13:19:43Z","title":"Latent-attention Based Transformer for Near ML Polar Decoding in Short-code Regime","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T15:48:43.299681Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2507.14951"},"observation_digest":"sha256:5d0cbf6152f53d9fd22add5762db6c01245b14252e36dce87e843c46ac7d4ac0","observation_id":"35a28022-ebac-45cd-9897-fcba2d1f11f3","resolution":{"observed_at":"2026-08-06T15:48:43.299681Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-06T15:33:58.353123Z","title":"Mish: A self regularized non-monotonic activation function,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2507.15578","last_updated":"2025-07-21T12:58:32Z","snapshot_observed_at":"2026-08-14T13:40:50.702280Z","submitted_at":"2025-07-21T12:58:32Z","title":"Compress-Align-Detect: onboard change detection from unregistered images","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T15:33:58.353123Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2507.15578"},"observation_digest":"sha256:c748d4212ddcf5233cf89d188e53449da7e59eb41bf90824b21dd4d17b5f6317","observation_id":"7089f6de-0c18-4d17-ac42-1806484665e1","resolution":{"observed_at":"2026-08-06T15:33:58.353123Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-15T18:01:27.327171Z","title":"Mish: A self regularized non-monotonic activation function","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2507.19344","last_updated":"2025-07-25T14:53:50Z","snapshot_observed_at":"2026-08-15T17:52:25.267426Z","submitted_at":"2025-07-25T14:53:50Z","title":"Joint Inference of Trajectory and Obstacle in Mean-Field Games via Bilevel Optimization","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:27.327171Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2507.19344"},"observation_digest":"sha256:6aa48a75f361b5e917521d117d34b6e1852eb85496978c1e794ef76074e04f22","observation_id":"038f740b-befb-4042-9b68-ac2b6bb27fe6","resolution":{"observed_at":"2026-08-15T18:01:27.327171Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-06T12:39:10.624184Z","title":"Mish: A self-regularized non-monotonic activation function","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-15T09:17:32.697246Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:10.624184Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:ba6f8729ae86301507192041cf1cecfd3dbdc50137e2f81f10d0168532a87fbf","observation_id":"1af972da-eb98-4630-9b01-52330caba868","resolution":{"observed_at":"2026-08-06T12:39:10.624184Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-06T11:44:50.366251Z","title":"Misra, Mish: A self regularized non-monotonic activation function, arXiv preprint arXiv:1908.08681 (2019)","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.22493","last_updated":"2025-07-30T09:00:39Z","snapshot_observed_at":"2026-08-14T00:42:03.380813Z","submitted_at":"2025-07-30T09:00:39Z","title":"LVM-GP: Uncertainty-Aware PDE Solver via coupling latent variable model and Gaussian process","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T11:44:50.366251Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2507.22493"},"observation_digest":"sha256:9fbd91e8505ddd9521209a08ac5b15f1c8252336fb7c01dc7f9e2e6b03c2a6bf","observation_id":"1a0940ec-32ec-4a72-96d8-6c8e82422356","resolution":{"observed_at":"2026-08-06T11:44:50.366251Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-06T11:02:23.551319Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.23215","last_updated":"2025-07-31T03:10:59Z","snapshot_observed_at":"2026-08-13T13:51:08.436399Z","submitted_at":"2025-07-31T03:10:59Z","title":"Silent Impact: Tracking Tennis Shots from the Passive Arm","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T11:02:23.551319Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2507.23215"},"observation_digest":"sha256:109c64f4003b1daed0843ae7d4227fd9ec0edf0a077560ba30ebdf4221fadc19","observation_id":"ab171fc6-9365-4f75-95ab-8ab66b1d14c5","resolution":{"observed_at":"2026-08-06T11:02:23.551319Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-06T05:15:42.396390Z","title":"Mish: A self regularized non-monotonic activation function,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2508.02067","last_updated":"2025-08-04T05:13:51Z","snapshot_observed_at":"2026-08-16T11:29:46.842984Z","submitted_at":"2025-08-04T05:13:51Z","title":"YOLOv1 to YOLOv11: A Comprehensive Survey of Real-Time Object Detection Innovations and Challenges","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T05:15:42.396390Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2508.02067"},"observation_digest":"sha256:7b430f49cdf2bb49ce90386e734bcd397de5986a2e2027f7bbc2df259ec72ee6","observation_id":"ac335f87-ce03-490d-91c3-3691910635d5","resolution":{"observed_at":"2026-08-06T05:15:42.396390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-05T23:35:29.658524Z","title":"arXiv preprint arXiv:1908.08681 (2019) 2, 10","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2508.05069","last_updated":"2025-08-07T06:42:40Z","snapshot_observed_at":"2026-08-16T04:31:30.222863Z","submitted_at":"2025-08-07T06:42:40Z","title":"FLUX-Makeup: High-Fidelity, Identity-Consistent, and Robust Makeup Transfer via Diffusion Transformer","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T23:35:29.658524Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2508.05069"},"observation_digest":"sha256:5862b8a68eace2f499331cbc9862d4e33a3b85445f7fad5988fb8cb1b3a7bb06","observation_id":"a697ca39-cd0f-43c1-a309-f3df1768b290","resolution":{"observed_at":"2026-08-05T23:35:29.658524Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2508.20614","last_updated":"2026-05-12T12:38:41Z","snapshot_observed_at":"2026-07-06T22:19:58.210578Z","submitted_at":"2025-08-28T10:01:01Z","title":"Improving the Accuracy of Amortized Model Comparison with Self-Consistency","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-18T21:16:08.765171Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2508.20614"},"observation_digest":"sha256:54eed3ab4e7b1d1f41f7c6e4bbe6b3ab5d64338fac323a925d5d286efb765521","observation_id":"00451267-5599-441a-ac36-a5a36edd6172","resolution":{"observed_at":"2026-05-18T21:16:51.076712Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-05T14:24:15.822040Z","title":"Mish: A self regularized non-monotonic activation function, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.21380","last_updated":"2026-06-10T10:31:06Z","snapshot_observed_at":"2026-08-13T20:39:40.369758Z","submitted_at":"2025-08-29T07:51:45Z","title":"The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-05T14:24:15.822040Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2508.21380"},"observation_digest":"sha256:e6446dfd8799c1775a8ee4387477e9131305fb3f3d13c775a9fb5d664e371ae4","observation_id":"2c3804c1-d3de-4228-876b-4e2d9f0d22d5","resolution":{"observed_at":"2026-08-05T14:24:15.822040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2509.13095","last_updated":"2026-04-04T14:43:35Z","snapshot_observed_at":"2026-08-12T19:11:58.603828Z","submitted_at":"2025-09-16T13:52:30Z","title":"Empowering Multi-Robot Cooperation via Sequential World Models","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-05-18T16:27:05.799805Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2509.13095"},"observation_digest":"sha256:19d9ab281888841b667e59d1f48499beaee7fb86018e273614f615c1064003da","observation_id":"be8d892e-fc03-476e-913d-6662aa919404","resolution":{"observed_at":"2026-05-18T16:31:37.405447Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2603.14267","last_updated":"2026-04-03T07:45:32Z","snapshot_observed_at":"2026-08-16T03:13:25.541845Z","submitted_at":"2026-03-15T07:53:23Z","title":"DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization","version":4},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-15T11:56:13.914121Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2603.14267"},"observation_digest":"sha256:9fb1a36fcda9f3eaa4d8f8538fdc87bb521a3580d71a71b1cb8217a1eedcbb13","observation_id":"3c2b4ae7-6690-47b1-a932-130221a83ab8","resolution":{"observed_at":"2026-05-15T11:59:59.601393Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2604.12159","last_updated":"2026-04-14T00:35:07Z","snapshot_observed_at":"2026-08-14T06:43:23.063089Z","submitted_at":"2026-04-14T00:35:07Z","title":"VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scale","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-10T15:37:16.031502Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2604.12159"},"observation_digest":"sha256:e5504998cf2343dc3177bfa49d40dec9554bf20d0e2e18731d7b9cf0c33942bf","observation_id":"37c45461-28c3-4851-a987-984b78ff0629","resolution":{"observed_at":"2026-05-11T10:11:02.509102Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2604.21677","last_updated":"2026-04-23T13:42:49Z","snapshot_observed_at":"2026-08-12T19:48:14.347463Z","submitted_at":"2026-04-23T13:42:49Z","title":"Geometric Monomial (GEM): a family of rational 2N-differentiable activation functions","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-09T22:38:00.317844Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2604.21677"},"observation_digest":"sha256:4d0c8925dda5371d8c16354470d5c3630d15bde4ffb137ff6f322e881d1b5f65","observation_id":"061ff3c9-73b2-457d-84cd-5e61601a0502","resolution":{"observed_at":"2026-05-09T22:39:14.453194Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2605.01702","last_updated":"2026-05-03T04:06:41Z","snapshot_observed_at":"2026-08-14T12:28:19.842631Z","submitted_at":"2026-05-03T04:06:41Z","title":"Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-05-08T19:36:37.805279Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2605.01702"},"observation_digest":"sha256:c3b26bf5bedd3216d3bfbaf010db60a49375116b274bbc6ec6f3bb4f52ef3aa2","observation_id":"acaf4d63-40bb-4636-b839-4fbf4f5d8743","resolution":{"observed_at":"2026-05-09T05:45:21.262768Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2605.02591","last_updated":"2026-05-04T13:38:16Z","snapshot_observed_at":"2026-08-11T05:08:42.777606Z","submitted_at":"2026-05-04T13:38:16Z","title":"Universal Smoothness via Bernstein Polynomials: A Constructive Approximation Approach for Activation Functions","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-08T18:07:54.617417Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2605.02591"},"observation_digest":"sha256:210e71dde6122e4c038a1331da1e5fc7f1c97c2983da3969d1558a67ee63215e","observation_id":"108a5e27-0d11-40b0-b0e0-4b118d0b14c6","resolution":{"observed_at":"2026-05-09T06:45:44.257871Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2605.07060","last_updated":"2026-08-13T05:34:20Z","snapshot_observed_at":"2026-08-16T20:09:25.572177Z","submitted_at":"2026-05-08T00:13:13Z","title":"Functional-prior-based approaches to Bayesian PDE-constrained inversion using physics-informed neural networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-11T02:19:16.737920Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2605.07060"},"observation_digest":"sha256:dd870ce940428d37b322faf9b063b1962bda67e8f13f37ae52040292458514af","observation_id":"7f14eea4-159a-46ad-8f93-9d3d432043fa","resolution":{"observed_at":"2026-05-11T03:45:56.882993Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2605.07060","last_updated":"2026-08-13T05:34:20Z","snapshot_observed_at":"2026-08-16T20:09:25.572177Z","submitted_at":"2026-05-08T00:13:13Z","title":"Functional-prior-based approaches to Bayesian PDE-constrained inversion using physics-informed neural networks","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-15T06:26:43.277631Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2605.07060"},"observation_digest":"sha256:de0c4ab860cfaca513f5177cbf240f8923d3ec4af4d0ae129620efec8b3a2bdf","observation_id":"07b2662e-dd87-4a40-8274-e0786247e634","resolution":{"observed_at":"2026-05-15T06:29:49.747303Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2605.09908","last_updated":"2026-05-11T02:51:35Z","snapshot_observed_at":"2026-08-11T08:56:08.146877Z","submitted_at":"2026-05-11T02:51:35Z","title":"Voice Biomarkers for Depression and Anxiety","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-12T04:33:48.062678Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2605.09908"},"observation_digest":"sha256:4f04a86242c7be548cf70f3f36b28832d680cce4a06dfc458c717757726f1d2b","observation_id":"e9284b4f-bc0d-47e4-bc8c-7689d0fffb28","resolution":{"observed_at":"2026-05-12T06:06:27.810670Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2605.14200","last_updated":"2026-05-13T23:32:00Z","snapshot_observed_at":"2026-07-06T23:25:39.415637Z","submitted_at":"2026-05-13T23:32:00Z","title":"How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization","version":1},"reference_index":267,"source":"arxiv_source","source_observed_at":"2026-05-15T04:45:20.091598Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2605.14200"},"observation_digest":"sha256:e3d671ca0be73c6029f20448843f0c0ff23c3e5da4c1dd44c3fc8a4e885dd40d","observation_id":"0ad67021-018e-4fd7-805f-fed21592dd47","resolution":{"observed_at":"2026-05-15T04:49:44.687054Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2605.14493","last_updated":"2026-05-14T07:33:36Z","snapshot_observed_at":"2026-08-11T15:36:23.431435Z","submitted_at":"2026-05-14T07:33:36Z","title":"Deep Learning for Solving and Estimating Dynamic Models in Economics and Finance","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-15T01:29:18.160292Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2605.14493"},"observation_digest":"sha256:fc627354307ed15dc017b957b824243add5c4d8c1108f142e2a3e564c596127b","observation_id":"6fbf1165-24bd-4839-8bcf-bf1e5660107d","resolution":{"observed_at":"2026-05-15T01:29:37.421261Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2605.26647","last_updated":"2026-05-26T07:30:53Z","snapshot_observed_at":"2026-08-15T23:08:46.171727Z","submitted_at":"2026-05-26T07:30:53Z","title":"More Expressive Feedforward Layers: Part I. Token-Adaptive Mixing of Activations","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-29T19:37:51.563121Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2605.26647"},"observation_digest":"sha256:54c19986123b4ab7db9b3fccf60841267bfcbcc37fa159507d09465cec7e8687","observation_id":"1be5e133-319d-4316-a55e-c8029e9424fc","resolution":{"observed_at":"2026-06-29T19:43:54.851852Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2605.28704","last_updated":"2026-05-27T16:30:41Z","snapshot_observed_at":"2026-08-04T23:08:37.080210Z","submitted_at":"2026-05-27T16:30:41Z","title":"Expressive Power of Floating-Point Neural Networks with Arbitrary Reduction Orders and Inexact Activation Implementations","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-29T13:37:29.682764Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2605.28704"},"observation_digest":"sha256:3626ea2780fa98a3d63758659a5cc7583748e4f8d181465d6157f45800f618b3","observation_id":"963a3e83-292b-45ff-ab37-30f78eea67bf","resolution":{"observed_at":"2026-06-29T13:43:29.151721Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2606.08438","last_updated":"2026-06-07T03:29:45Z","snapshot_observed_at":"2026-07-06T23:47:57.376596Z","submitted_at":"2026-06-07T03:29:45Z","title":"Improving Bayesian Optimization via Training-Aware Conditional Diffusion Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-27T18:19:41.476212Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2606.08438"},"observation_digest":"sha256:9e59f2c1aa99685aa8699d3c3db63967b04ce690309e9a73c0c3c838a98da4aa","observation_id":"218bf73c-1ba1-403b-b01b-db7d158ae348","resolution":{"observed_at":"2026-07-02T23:17:29.658521Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2606.10234","last_updated":"2026-06-08T22:47:20Z","snapshot_observed_at":"2026-08-14T02:17:15.947087Z","submitted_at":"2026-06-08T22:47:20Z","title":"Performance of the Eos detector with water","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-27T14:15:54.944686Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2606.10234"},"observation_digest":"sha256:511a2a7390fe420c928742533f872003b39854f2c141a167d9ddd6daf4dd8127","observation_id":"77d7a6ef-afb0-4e23-b558-913808f2080d","resolution":{"observed_at":"2026-07-03T03:57:38.964692Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2606.19397","last_updated":"2026-06-17T08:06:05Z","snapshot_observed_at":"2026-08-03T20:34:23.983001Z","submitted_at":"2026-06-17T08:06:05Z","title":"DiffusionVS: A Generative Framework for Robust Visual Servoing Based on Diffusion Policy","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-26T21:16:44.090808Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2606.19397"},"observation_digest":"sha256:60733f352997739ce81149e3c81b5d6cc8b355553490cc13e6e3e328cd858457","observation_id":"4595382c-c9a9-4d7e-8c13-710b1b1cc71d","resolution":{"observed_at":"2026-07-04T00:19:13.757876Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2606.21789","last_updated":"2026-06-19T22:40:56Z","snapshot_observed_at":"2026-08-16T11:52:11.973829Z","submitted_at":"2026-06-19T22:40:56Z","title":"Bayesian three-dimensional seismic travel-time tomography for active- and passive-source seismic data using physics-informed neural network","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-06-26T12:13:53.218021Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2606.21789"},"observation_digest":"sha256:de8c5a995604a4bf58a0ebdf9e02f2b5c9727cf002d21c54cf46fcaba68bbc00","observation_id":"31b8f230-4f2d-4900-8ff6-733b12f531da","resolution":{"observed_at":"2026-07-04T08:09:40.843940Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-12T04:33:35.163697Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-14T16:18:17.243378Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:e5ad5f10fa69b17c8902ba790121d491a1cebbe6f42a8cda712ea8ac3dc15541","observation_id":"c52b5bbe-8036-4dd4-b1b0-3117424f4b0e","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":"1908.08681","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-08T11:24:54.882129Z","title":"Mish: A self regularized non-monotonic activation function","venue":"cs.LG","work_id":"f314c3b6-cec7-4246-8006-cbed6b9840d3","year":2019},"citing_paper":{"arxiv_id":"2607.06274","last_updated":"2026-07-07T13:41:03Z","snapshot_observed_at":"2026-08-10T03:13:37.901597Z","submitted_at":"2026-07-07T13:41:03Z","title":"Learning-based Physics-Constrained Neural Kernel for Sound Field Estimation With Source-Position-Dependent Directional Weighting","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-08T11:21:43.911143Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2607.06274"},"observation_digest":"sha256:fcbae67aa7517c389fd67010f89eebbd8ae8d4b2b2b60ebf2642dacc06cfcc9a","observation_id":"c5e2538f-ab4d-412c-aa52-a881edf270a6","resolution":{"observed_at":"2026-07-08T11:24:54.884730Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-01T22:29:29.740549Z","title":"Misra, arXiv:1908.08681 [cs.LG]","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2607.15742","last_updated":"2026-07-17T08:23:54Z","snapshot_observed_at":"2026-08-12T19:55:05.861530Z","submitted_at":"2026-07-17T08:23:54Z","title":"Path optimization method for the sign problem: Insights from random matrix models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:29.740549Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2607.15742"},"observation_digest":"sha256:fe5da81c78650dc40d76177b1c8109b9481458e839f8d48a02d0a5ee5d80edcc","observation_id":"ec98a2f6-0353-4e26-ac15-6e1eb717126f","resolution":{"observed_at":"2026-08-01T22:29:29.740549Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-01T21:05:37.659769Z","title":"Misra,Mish: A self regularized non-monotonic activation function,BMVC(2020) [1908.08681]","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.16413","last_updated":"2026-07-17T18:04:43Z","snapshot_observed_at":"2026-08-15T15:53:41.432305Z","submitted_at":"2026-07-17T18:04:43Z","title":"Measurement of the branching ratio of the $K^{+}\\rightarrow\\pi^{+}\\nu\\bar{\\nu}$ decay","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T21:05:37.659769Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2607.16413"},"observation_digest":"sha256:d96c687408c5951a65aeec6742a6a2dab755b69af64f1b0a1050e5709937b884","observation_id":"c0292d3f-72a3-4336-92c3-8739f9bf83a6","resolution":{"observed_at":"2026-08-01T21:05:37.659769Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-01T17:45:22.256131Z","title":"arXiv preprint arXiv:1908.08681 , year=","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2607.17560","last_updated":"2026-07-20T05:09:36Z","snapshot_observed_at":"2026-08-05T13:38:45.921055Z","submitted_at":"2026-07-20T05:09:36Z","title":"Reinforcement Learning: From Algorithms To Foundation Models","version":1},"reference_index":264,"source":"arxiv_source","source_observed_at":"2026-08-01T17:45:22.256131Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2607.17560"},"observation_digest":"sha256:6c7c99c488a8829c5b75e49ed710071829817a9ec90c5dac5cf1de2820f2a5e5","observation_id":"0f6ecba2-37ca-4b7a-ac23-4dd9191fb78d","resolution":{"observed_at":"2026-08-01T17:45:22.256131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-01T11:07:58.437825Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.19987","last_updated":"2026-07-23T07:54:02Z","snapshot_observed_at":"2026-08-12T19:49:44.360068Z","submitted_at":"2026-07-22T10:20:40Z","title":"UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T11:07:58.437825Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2607.19987"},"observation_digest":"sha256:557ede97845b054d4add4b952fd85fbc3f9c3252f6acca05ec960f1c88b0c162","observation_id":"313093d6-dbc1-4fd6-a195-b394b0a43ccc","resolution":{"observed_at":"2026-08-01T11:07:58.437825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-01T08:32:00.094258Z","title":"arXiv preprint arXiv:1908.08681 , year=","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2607.21120","last_updated":"2026-07-23T09:55:45Z","snapshot_observed_at":"2026-08-13T04:22:32.472683Z","submitted_at":"2026-07-23T09:55:45Z","title":"Relative Value Learning","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-01T08:32:00.094258Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2607.21120"},"observation_digest":"sha256:a7122cb6eacd8f87bade713257f8cecaed281aae250c98e5f10c86eb230c8f1f","observation_id":"69e7ea55-825c-44ec-94bc-4b07c8d6d11b","resolution":{"observed_at":"2026-08-01T08:32:00.094258Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-07-31T18:02:34.664093Z","title":"Mish: A self regularized non-monotonic neural activation function.CoRR, abs/1908.08681, 2019","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2607.28093","last_updated":"2026-07-30T12:05:34Z","snapshot_observed_at":"2026-08-10T13:04:16.642619Z","submitted_at":"2026-07-30T12:05:34Z","title":"Meteosat Third Generation imagery improves CNN-based SSI retrieval","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-31T18:02:34.664093Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2607.28093"},"observation_digest":"sha256:aa9beee8ad5495907515f69ea18018c06942a87a5c0b6d0ae19fb802abad0e4b","observation_id":"a1362a05-cff5-40bd-a2b7-dd34ca43d2c4","resolution":{"observed_at":"2026-07-31T18:02:34.664093Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-04T05:05:10.518816Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.02547","last_updated":"2026-08-03T17:32:45Z","snapshot_observed_at":"2026-08-15T01:01:37.630832Z","submitted_at":"2026-08-03T17:32:45Z","title":"Why Does Action Chunking Improve Behavioral Cloning Performance in Robotic Control?","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-04T05:05:10.518816Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2608.02547"},"observation_digest":"sha256:eab5d93e448ff64232c0f345b38f77c1b4b2277d375fb9c3881598b61080b0ff","observation_id":"30e82690-5ac2-428b-adb0-34e66b4b4fe8","resolution":{"observed_at":"2026-08-04T05:05:10.518816Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1908.08681/citation-record","integrity":"/paper/1908.08681/integrity","json":"/paper/1908.08681/citation-record.json","paper":"/paper/1908.08681"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.332988Z","title":"On the rate of convergence of the preconditioned conjugate gradient method","venue":null,"work_id":"03af6793-23dc-48c3-a580-6429ddeb8c26","year":1986},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.613100Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:155b7c1f89c22c656bcfc90615de3116ea49cfc0e084b7f3bdcbd2c4c5872c4a","observation_id":"af01463f-2504-40e9-b731-0922f3bacfa2","resolution":{"observed_at":"2026-08-14T11:36:30.336890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10934","last_updated":"2020-04-23T02:10:02Z","snapshot_observed_at":"2026-08-16T04:20:57.069798Z","submitted_at":"2020-04-23T02:10:02Z","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.10934","snapshot_observed_at":"2026-08-14T11:36:29.617637Z","title":"Yolov4: Optimal speed and accuracy of object detection","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.617637Z"},"links":{"cited_paper":"/paper/2004.10934","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:4ae940798fb5088c8a1e35b1c4b8520db666006a98314a3bfc589ab415e2d339","observation_id":"35e873f5-c9d3-4dd5-89d4-5b2fc74055c4","resolution":{"observed_at":"2026-08-14T11:36:29.617637Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.319574Z","title":"Large-scale machine learning with stochastic gradient descent","venue":null,"work_id":"c9fa6321-e6a5-4665-9ae4-379211ca43fc","year":2010},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.622683Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:9d840033eb2cc1636e4fb54a05b8c455421183777e2593a35dcfbb4d72b8e2bb","observation_id":"e8178b7f-7f68-4d75-9838-5cec886337af","resolution":{"observed_at":"2026-08-14T11:36:30.324441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.09967","last_updated":"2017-11-09T21:59:39Z","snapshot_observed_at":"2026-08-14T20:19:47.854813Z","submitted_at":"2017-10-27T02:01:28Z","title":"Improving Deep Learning by Inverse Square Root Linear Units (ISRLUs)","version":2},"cited_work":{"arxiv_id":"1710.09967","doi":null,"metadata_source":"pith","pith_arxiv_id":"1710.09967","snapshot_observed_at":"2026-08-14T11:36:29.989534Z","title":"Improving Deep Learning by Inverse Square Root Linear Units (ISRLUs)","venue":"cs.LG","work_id":"fee85184-14e7-4f95-a943-6ae9b6c3aca1","year":2017},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.626701Z"},"links":{"cited_paper":"/paper/1710.09967","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:f059d54f635872e3d65fb9fb0be11274f55b41e8d78acf6320eb0ef7444c169c","observation_id":"db9b90c0-c373-4749-b950-9a2c3a3a4969","resolution":{"observed_at":"2026-08-14T11:36:29.995539Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.631031Z","title":"Xception: Deep learning with depthwise separable convolutions","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.631031Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:68a4ae7af437807027682b797dfb5fa1f16a6b52480d384085ba603b83f2d4bc","observation_id":"dbed67c1-db55-4531-9f3c-a5fada3398fd","resolution":{"observed_at":"2026-08-14T11:36:29.631031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1511.07289","last_updated":"2016-02-22T07:02:58Z","snapshot_observed_at":"2026-08-14T22:21:43.095256Z","submitted_at":"2015-11-23T15:58:05Z","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.07289","snapshot_observed_at":"2026-08-14T11:36:29.634702Z","title":"Fast and accurate deep network learning by exponential linear units (elus)","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.634702Z"},"links":{"cited_paper":"/paper/1511.07289","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:b3b859a3d12f61d77b721e151f747104e20595741685d00ad0ee7a6d77c8de2c","observation_id":"e043e858-d9ed-4af0-9d2b-1219bcfea453","resolution":{"observed_at":"2026-08-14T11:36:29.634702Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.638906Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.638906Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:7d7562743430ec4d60909b173a2efbf4a43add7ee8aa236ed323ba1c853cf2ae","observation_id":"af85f19b-64c8-49ff-a52a-beaab788331c","resolution":{"observed_at":"2026-08-14T11:36:29.638906Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.05027","last_updated":"2020-06-17T16:37:15Z","snapshot_observed_at":"2026-07-06T08:43:34.515141Z","submitted_at":"2019-12-10T22:13:42Z","title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.05027","snapshot_observed_at":"2026-08-14T11:36:29.642392Z","title":"Spinenet: Learning scale-permuted backbone for recognition and localization","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.642392Z"},"links":{"cited_paper":"/paper/1912.05027","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:55d3f168b89a7bdd49dde7cb3fa5d7b20f2fbac56e9e5e01af5087f69150af37","observation_id":"71bac3c7-865b-4299-bf94-e851f9a285e4","resolution":{"observed_at":"2026-08-14T11:36:29.642392Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.294195Z","title":"Dropblock: A regularization method for convolutional networks","venue":null,"work_id":"a277c802-e2ec-4861-8b51-d864be932d96","year":2018},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.646461Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:b99c270978ded95409a9c275f2af83841846117ff39ca9c75dd9ce08e7d56d86","observation_id":"0564dea9-6bd8-4898-b556-f2f6e1ce026b","resolution":{"observed_at":"2026-08-14T11:36:30.298043Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.281865Z","title":"Rich feature hierar- chies for accurate object detection and semantic segmentation","venue":null,"work_id":"6e9046f1-eed6-4ff8-a792-e977baf5765d","year":2014},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.651250Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:1ad9fc3f60d15b613ab730a31cb548f1b41122a02ff1ff7fb41de18923af7be3","observation_id":"1d6683f8-3109-4979-9337-646b707afdc3","resolution":{"observed_at":"2026-08-14T11:36:30.286294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.655114Z","title":"Understanding the difficulty of training deep feed- forward neural networks","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.655114Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:789fb5adf04c664898f00efaf28738e5de7647b83bd824b7a5988865403d0cea","observation_id":"4b53931b-bdd5-4466-92be-c0caf59b34aa","resolution":{"observed_at":"2026-08-14T11:36:29.655114Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.06037","last_updated":"2023-04-27T16:20:03Z","snapshot_observed_at":"2026-08-15T18:38:43.738451Z","submitted_at":"2016-08-22T02:50:57Z","title":"Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.06037","snapshot_observed_at":"2026-08-14T11:36:29.658545Z","title":"Lets keep it simple, using simple architectures to outperform deeper and more complex architectures","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.658545Z"},"links":{"cited_paper":"/paper/1608.06037","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:5df4cca77e2c39ba0e41ad015e6d6d9d16dd1798587f356a79635d503b09e087","observation_id":"860a4f32-414a-4fef-93d6-5f9b3bc3c7ce","resolution":{"observed_at":"2026-08-14T11:36:29.658545Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.662622Z","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.662622Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:b9aab652604fd1d9ced6d5293f37f93838d4cb1c399fd8d91f8cfdedf5985027","observation_id":"bb68356b-3ad1-4ecb-8a0f-8b9781bb61e6","resolution":{"observed_at":"2026-08-14T11:36:29.662622Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.666305Z","title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.666305Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:2c6b3f8fd508c17c21660d7dfe0f86ec1af8e6aa5258456f25bcab4b7f8e328f","observation_id":"abfb1859-136d-4ad6-8393-a3dbbb60d398","resolution":{"observed_at":"2026-08-14T11:36:29.666305Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.669878Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.669878Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:f901d87d1c0358cb8cbce8ceced447b77acd35ddd571dd37f3179229b3dee850","observation_id":"76bc8521-0081-48c1-8676-6bc9fcd66f1c","resolution":{"observed_at":"2026-08-14T11:36:29.669878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.08415","last_updated":"2023-06-06T01:53:32Z","snapshot_observed_at":"2026-08-13T19:48:28.322536Z","submitted_at":"2016-06-27T19:20:40Z","title":"Gaussian Error Linear Units (GELUs)","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.08415","snapshot_observed_at":"2026-08-14T11:36:29.673101Z","title":"Gaussian error linear units (gelus)","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.673101Z"},"links":{"cited_paper":"/paper/1606.08415","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:3b7ceae976ebfaa57c23fd520e553e8e67c710e4240c5b0126f185c53bf1c8fd","observation_id":"9c1371db-1344-4274-9291-127c18ad0fdf","resolution":{"observed_at":"2026-08-14T11:36:29.673101Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-04-17T03:57:34Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.04861","snapshot_observed_at":"2026-08-14T11:36:29.676874Z","title":"Mobilenets: Effi- cient convolutional neural networks for mobile vision applications","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.676874Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:b4c3e56050a56ee35a0ca0f76eaf668f12d4fdcb71e0146486535c6595896724","observation_id":"f019212d-ea60-468b-8c47-fe0ee19e91f6","resolution":{"observed_at":"2026-08-14T11:36:29.676874Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.680382Z","title":"Squeeze-and-excitation networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.680382Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:84c801af97d8c4b2c0e292d0b55ec93edc6ccc66ae8ec8e6bf67712aecf237f7","observation_id":"9954a7ad-53dd-41ae-bd9f-fc98017fd7b3","resolution":{"observed_at":"2026-08-14T11:36:29.680382Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.684092Z","title":"Densely connected convolutional networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.684092Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:c8c4a735af5ed4e373631db5bdcbccb8ffd0e45c97ca5929f319ec8c4f319674","observation_id":"7eebbf6d-947b-421a-9e50-46ac993aff69","resolution":{"observed_at":"2026-08-14T11:36:29.684092Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1502.03167","last_updated":"2015-03-02T20:44:12Z","snapshot_observed_at":"2026-08-12T21:01:12.961874Z","submitted_at":"2015-02-11T01:44:18Z","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1502.03167","snapshot_observed_at":"2026-08-14T11:36:29.687260Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.687260Z"},"links":{"cited_paper":"/paper/1502.03167","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:16ee49bfc646a0f356ffa440847c94b29b659620525c7e2039778ac1c5627715","observation_id":"1037566e-4a47-4111-bb53-1135714af536","resolution":{"observed_at":"2026-08-14T11:36:29.687260Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.226254Z","title":"Deep learning with s-shaped rectified linear activation units","venue":null,"work_id":"fa0bdbc9-a42d-48e7-984c-facd517ad8ac","year":2016},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.690873Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:007fd848f78f847ac9799d4e622ae231757a216b5eca317708f60a0a39002bad","observation_id":"93d2fc00-9917-45fc-ba30-49d0ac730ae1","resolution":{"observed_at":"2026-08-14T11:36:30.230704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-14T18:51:16.666127Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-14T11:36:29.694235Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.694235Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:cfd70a99fecd363e7e8c01d8f2d821155782d5c76d7d5ccbd58e68df105dfdc9","observation_id":"2e7c0d0e-53ed-4a98-878f-4374d018248a","resolution":{"observed_at":"2026-08-14T11:36:29.694235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.213843Z","title":"Self- normalizing neural networks","venue":null,"work_id":"c7ea194c-b8e6-4a45-b5d8-8a160d6b072c","year":2017},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.698044Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:566114265d950ac86af4dac87c155f90cbc14969259f21f30387a3913455f17f","observation_id":"9e9825f4-d35e-401e-ad27-55241a844ee7","resolution":{"observed_at":"2026-08-14T11:36:30.217947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.202518Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"cecb4cb3-7a95-4cb9-be15-2021c3ce780f","year":2009},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.701424Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:7ec3f22f1796cc7d867188a36a87ee9e0af2114d65a88ddc26d6bb98f0f35748","observation_id":"0ceb62f2-3634-41c2-b188-5532466e42f3","resolution":{"observed_at":"2026-08-14T11:36:30.206472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.704859Z","title":"Imagenet classification with deep convolutional neural networks","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.704859Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:e62db11f85ac1a64d89a5446290a4c03dc9101e794d39bb3d6d80ac7e8ea11f6","observation_id":"67d43d1b-8160-4220-aed7-8af2f27d186f","resolution":{"observed_at":"2026-08-14T11:36:29.704859Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.183802Z","title":"Mnist handwritten digit database","venue":null,"work_id":"454e3610-7d76-4bb7-9bf3-4eb79d3b303f","year":2010},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.708487Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:32a90aaebda80aea3c8e96710017748b68ba63a92b710262c64fb77c69927b71","observation_id":"ff669ad0-e3e7-48a7-a6b0-17777941c211","resolution":{"observed_at":"2026-08-14T11:36:30.187759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.173692Z","title":"Efficient backprop","venue":null,"work_id":"2402ca3e-8d5e-43e2-b126-956c374634e4","year":2012},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.712074Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:99baa311e80c29aee1861605499709242e8c45e48a3a897a10689db24cf28835","observation_id":"1e0d9cbf-0b6a-4983-a311-a13ac630d35c","resolution":{"observed_at":"2026-08-14T11:36:30.177036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.715618Z","title":"Visualizing the loss landscape of neural nets","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.715618Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:a681206d267b2b8eb0a1571deca96a2fb7c5e431c83822aeea01abea667ea83a","observation_id":"0b5517f8-54cc-4dbd-ac87-b56bb83fe29b","resolution":{"observed_at":"2026-08-14T11:36:29.715618Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.156891Z","title":"Preconditioned stochastic gradient descent","venue":null,"work_id":"f12ba8d4-58ee-4820-a7a2-a47fc1b8e197","year":2017},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.719168Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:8acb9c2ced17b3ae79f42bb0d9c89464a7cf1865b577b5a4f50a877490ddc491","observation_id":"02fc863c-cd1e-4f9c-bb0c-9baab478e880","resolution":{"observed_at":"2026-08-14T11:36:30.160633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.146662Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":"ec228128-f8d4-4eac-9f71-caa1b3026f21","year":2014},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.722604Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:31dc8b424d5b5abc6cad26b7cc330fdd84c2b22cbca6be6d4b0ebe452c02204d","observation_id":"77c5c087-fbe4-413e-bccb-660c1a5949a6","resolution":{"observed_at":"2026-08-14T11:36:30.150300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.03983","last_updated":"2017-05-03T16:28:09Z","snapshot_observed_at":"2026-07-06T05:06:55.589962Z","submitted_at":"2016-08-13T13:46:05Z","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.03983","snapshot_observed_at":"2026-08-14T11:36:29.726026Z","title":"Sgdr: Stochastic gradient descent with warm restarts","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.726026Z"},"links":{"cited_paper":"/paper/1608.03983","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:493bd2d6cbc718a8df038f5ffccbae9c33dafafb7874f51cdc03ce0a82695abc","observation_id":"0368a446-a818-4714-bbf3-24bb7f05b3ab","resolution":{"observed_at":"2026-08-14T11:36:29.726026Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.135083Z","title":"Rectifier nonlinearities improve neural network acoustic models","venue":null,"work_id":"3cf52fb7-2393-446f-a3c0-82d6e90fb3a8","year":2013},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.729812Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:1acbeec7c01b077279b3c0a6159e6ed30dc0ea1b31bb7628affad3660c10463f","observation_id":"193b01cf-12dd-4f6d-b74a-4e2bf4ac6554","resolution":{"observed_at":"2026-08-14T11:36:30.139255Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.122935Z","title":"When does label smoothing help? In Advances in Neural Information Processing Systems, pages 4696–4705, 2019","venue":null,"work_id":"caeceda8-fa92-420a-8489-da1e1fe3500d","year":2019},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.733172Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:664a9dd917955d05a8e61f1dd876d3b86e67ee8ebd3aadfb13fc36b57606ae5f","observation_id":"a48fb977-f099-46bd-978d-6665500b004c","resolution":{"observed_at":"2026-08-14T11:36:30.127218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.736593Z","title":"Rectified linear units improve restricted boltzmann machines","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.736593Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:768e172b083d70cf567585888a406c75529f51ea0d249571ad39f75b4ccedfb1","observation_id":"20523d45-cac7-42c1-9ce5-4f40676061fa","resolution":{"observed_at":"2026-08-14T11:36:29.736593Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.740140Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.740140Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:0d506d38d5739a91018feb86d84b515dd55b4f547d4ee34c3c4d8f6bb4d4489d","observation_id":"56356c7c-1243-42a6-99ae-1e53fccacf5c","resolution":{"observed_at":"2026-08-14T11:36:29.740140Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.098334Z","title":"Language models are unsupervised multitask learners","venue":null,"work_id":"281d233c-c31b-4a8f-b369-33078dfc4ca5","year":2019},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.743737Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:ccf14c5cc1c2d90c780f4cc5d36d3acd8a27e7cb3c0e515ce4013a6eb98b37a9","observation_id":"01fe1e62-ec58-4ec1-87bf-eed79aeeae3f","resolution":{"observed_at":"2026-08-14T11:36:30.103232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.05941","last_updated":"2017-10-27T17:45:21Z","snapshot_observed_at":"2026-08-08T18:23:31.977872Z","submitted_at":"2017-10-16T18:05:45Z","title":"Searching for Activation Functions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.05941","snapshot_observed_at":"2026-08-14T11:36:29.747190Z","title":"Searching for activation functions","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.747190Z"},"links":{"cited_paper":"/paper/1710.05941","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:9e7d2f92c95b56008b8d8fd3221e4d473d2cdef4c4db03d5103d14cc3b0c3639","observation_id":"76c12c13-e757-4973-93f7-07615c4c5232","resolution":{"observed_at":"2026-08-14T11:36:29.747190Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.086496Z","title":"Darknet: Open source neural networks in c","venue":null,"work_id":"c27e13b1-43ac-45f3-a1fa-da30aad6ce0d","year":2013},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.750850Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:5df84334c48b7ea8ed5cc9fcb5d774569c18db85d1daea5c8d5c2efad3e97402","observation_id":"cb3606bf-c54e-4dc4-8dae-4c8626c60b85","resolution":{"observed_at":"2026-08-14T11:36:30.090758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.02767","last_updated":"2018-04-08T22:27:57Z","snapshot_observed_at":"2026-08-15T16:54:48.034047Z","submitted_at":"2018-04-08T22:27:57Z","title":"YOLOv3: An Incremental Improvement","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.02767","snapshot_observed_at":"2026-08-14T11:36:29.754468Z","title":"Yolov3: An incremental improvement","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.754468Z"},"links":{"cited_paper":"/paper/1804.02767","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:1e15af8ba10bd11893a54446420bd5ab5a016056a5e01a852b732c5dd5c57d79","observation_id":"1edd17c8-acfc-422b-af7a-e311f3ea346d","resolution":{"observed_at":"2026-08-14T11:36:29.754468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.075300Z","title":"Dynamic routing between cap- sules","venue":null,"work_id":"0e5b451e-f3df-4d19-a222-cd1dc26e0530","year":2017},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.758644Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:4038709e87a3db76509d832d069be99976d4b1aefb1aef239bf8d5ff2f2835e4","observation_id":"3ab40688-a04c-4c12-a7c3-19bb2c6d884f","resolution":{"observed_at":"2026-08-14T11:36:30.079351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.762254Z","title":"Dropout: a simple way to prevent neural networks from overfitting","venue":null,"work_id":null,"year":1929},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.762254Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:38955c50572fe7353350b78125d8e39468df2c9ba35fc19df3499fbdc6ce4fe3","observation_id":"8994b42a-9847-42d2-8eaa-035e09fae65e","resolution":{"observed_at":"2026-08-14T11:36:29.762254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.765901Z","title":"Going deeper with convolutions","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.765901Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:1451745754d807b9c0a47ad4acc8cd86b73e7c5ce723479e2848ebe1579a76b6","observation_id":"6ed22ae1-7378-4888-b555-264615725493","resolution":{"observed_at":"2026-08-14T11:36:29.765901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.11946","last_updated":"2020-09-11T05:08:01Z","snapshot_observed_at":"2026-08-10T19:44:30.311627Z","submitted_at":"2019-05-28T17:05:32Z","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.11946","snapshot_observed_at":"2026-08-14T11:36:29.770188Z","title":"Efficientnet: Rethinking model scaling for convolu- tional neural networks","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.770188Z"},"links":{"cited_paper":"/paper/1905.11946","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:f7d9f4e8401344645dad23b57ac2d7648a472da1b29db2201fa82f118f46ea25","observation_id":"ac2c568e-1140-4e4b-9224-60653d967a00","resolution":{"observed_at":"2026-08-14T11:36:29.770188Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.09070","last_updated":"2020-07-27T15:55:16Z","snapshot_observed_at":"2026-08-08T20:07:32.536859Z","submitted_at":"2019-11-20T18:16:09Z","title":"EfficientDet: Scalable and Efficient Object Detection","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.09070","snapshot_observed_at":"2026-08-14T11:36:29.773816Z","title":"Efficientdet: Scalable and efficient object detection","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.773816Z"},"links":{"cited_paper":"/paper/1911.09070","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:d02991d89819da830c5863b9b5060b95c77aeb565f288291cb456eb4a178d5e8","observation_id":"5bc78505-99f7-4212-b373-710b02e354c8","resolution":{"observed_at":"2026-08-14T11:36:29.773816Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.11929","last_updated":"2019-11-27T03:15:27Z","snapshot_observed_at":"2026-08-13T15:56:12.814781Z","submitted_at":"2019-11-27T03:15:27Z","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.11929","snapshot_observed_at":"2026-08-14T11:36:29.777558Z","title":"Cspnet: A new backbone that can enhance learning capability of cnn","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.777558Z"},"links":{"cited_paper":"/paper/1911.11929","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:e9f7eba784315b0c94264773b38502578ce9d531099f9bd9f150b808ccc08150","observation_id":"9cd43a9e-0824-4486-95a7-0fc17975b13f","resolution":{"observed_at":"2026-08-14T11:36:29.777558Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.046779Z","title":"Pelee: A real-time object detection system on mobile devices","venue":null,"work_id":"a32424d5-431e-4651-88d2-3c9f0b252b3d","year":1963},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.781068Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:32035a27c12c90064e04b045ec4d9cf77611869daaefa115346c6c7e36d96620","observation_id":"ae828d57-79e0-4ef8-8679-23fd5d035b7e","resolution":{"observed_at":"2026-08-14T11:36:30.050890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:29.784641Z","title":"Aggregated residual transformations for deep neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.784641Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:0979b243c925a173109db3177972df352da842a356cd4de8e62229faaf0b3a84","observation_id":"4eed6dd0-1b82-43ae-a551-1dcd5e28655b","resolution":{"observed_at":"2026-08-14T11:36:29.784641Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1505.00853","last_updated":"2015-11-27T06:58:14Z","snapshot_observed_at":"2026-08-14T22:49:52.991256Z","submitted_at":"2015-05-05T01:16:39Z","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1505.00853","snapshot_observed_at":"2026-08-14T11:36:29.787989Z","title":"Empirical evaluation of rectified activations in convolutional network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.787989Z"},"links":{"cited_paper":"/paper/1505.00853","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:d5f44fe453af32cc33a0af9342632b3c3f1ed6f830cab0810c77aa58013e73f6","observation_id":"2d6cd1a1-c530-4701-bde3-b2a4cd20d430","resolution":{"observed_at":"2026-08-14T11:36:29.787989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.028703Z","title":"Cutmix: Regularization strategy to train strong classifiers with lo- calizable features","venue":null,"work_id":"7fb478cc-221c-4553-9d1a-191b30997443","year":2019},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.791703Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:0257006c197c3e0d0e469215a05bbd6f30f29fe78f96fb2fde225d6d54d93fe7","observation_id":"a87cd76b-29ab-4775-bbe4-6e506417dd7e","resolution":{"observed_at":"2026-08-14T11:36:30.032749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07146","last_updated":"2017-06-14T06:06:48Z","snapshot_observed_at":"2026-08-16T07:54:28.918946Z","submitted_at":"2016-05-23T19:27:13Z","title":"Wide Residual Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.07146","snapshot_observed_at":"2026-08-14T11:36:29.794944Z","title":"Wide residual networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.794944Z"},"links":{"cited_paper":"/paper/1605.07146","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:9e9a6e11bb375a474f58c9e4fe699e5ffa1ee05551ea362e61ba5034a9ed05e2","observation_id":"2c34b8ce-0399-41cc-8dd2-00bf9ab030d0","resolution":{"observed_at":"2026-08-14T11:36:29.794944Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:36:30.017028Z","title":"Shufflenet: An extremely efficient convolutional neural network for mobile devices","venue":null,"work_id":"05710da7-a304-423e-84e3-5381321668ed","year":2018},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.798632Z"},"links":{"citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:3a9145215a53e00a2e9285fc22352b4e3ae9a13c5e49496261a1367c4bbb80ab","observation_id":"efe84c70-cb7f-457b-b50e-51ad4dc0c27b","resolution":{"observed_at":"2026-08-14T11:36:30.021402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01578","last_updated":"2017-02-15T05:28:05Z","snapshot_observed_at":"2026-08-14T21:31:52.294004Z","submitted_at":"2016-11-05T00:41:37Z","title":"Neural Architecture Search with Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01578","snapshot_observed_at":"2026-08-14T11:36:29.802225Z","title":"Neural architecture search with reinforcement learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:29.802225Z"},"links":{"cited_paper":"/paper/1611.01578","citing_paper":"/paper/1908.08681"},"observation_digest":"sha256:88931c5390ee409a09309032d18dda4301c41e64f94070b10189d540c0daa7aa","observation_id":"fcc4f2e9-3fdf-4425-963b-b7f305359188","resolution":{"observed_at":"2026-08-14T11:36:29.802225Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T11:10:42.406459Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":32,"verified_exact":1,"verified_fuzzy":19},"total_outbound_references":52},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 66 inbound Pith citation observations for arXiv:1908.08681."}