{"as_of":"2026-08-18T15:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:12c9ac526181de312e6b6395c0fd8bcb48f643b3bae97ffdef8a5d4404dafbb4","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T01:05:55.212825Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-13T17:51:29.832500Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-13T17:53:05.007180Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"cited_work":{"arxiv_id":"2505.02537","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.02537","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Advancing constrained monotonic neural networks: Achieving universal approxi- mation beyond bounded activations","venue":null,"work_id":"761f2081-ccf5-4c90-89f9-6fe0fe620e65","year":2025},"citing_paper":{"arxiv_id":"2604.16426","last_updated":"2026-04-04T17:50:07Z","snapshot_observed_at":"2026-08-15T07:37:41.798158Z","submitted_at":"2026-04-04T17:50:07Z","title":"Functional Similarity Metric for Neural Networks: Overcoming Parametric Ambiguity via Activation Region Analysis","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-13T17:51:29.832500Z"},"links":{"cited_paper":"/paper/2505.02537","citing_paper":"/paper/2604.16426"},"observation_digest":"sha256:a19405cf48941d093f6f5a420a2a5c3185af813a44577514d22ff0a94c43f6c9","observation_id":"7b74ae1d-0a08-4eba-b112-3c1690a168d8","resolution":{"observed_at":"2026-05-13T17:53:05.009631Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.02537/citation-record","integrity":"/paper/2505.02537/integrity","json":"/paper/2505.02537/citation-record.json","paper":"/paper/2505.02537"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T01:05:55.018595Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.018595Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:41b8e37e05db4703f830fba37de44a7da85a2075b046929c440864bf42f11bbb","observation_id":"6b330d33-2b53-45a6-9379-a8d456f16f1e","resolution":{"observed_at":"2026-08-16T01:05:55.018595Z","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":"2026-08-16T01:05:55.741245Z","title":"Machine bias","venue":null,"work_id":"c3f340db-064b-4503-87e8-1f556d7405b7","year":2022},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.024869Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:56570fe128e381e7f1be70ff42ac49ba43b26bd07b38c1fffc9822109ab91a9f","observation_id":"9378f69d-bc9f-4c86-a5ad-26106dbe31a9","resolution":{"observed_at":"2026-08-16T01:05:55.745669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.07483","last_updated":"2017-04-24T22:37:08Z","snapshot_observed_at":"2026-08-16T06:04:09.785647Z","submitted_at":"2017-04-24T22:37:08Z","title":"Continuously Differentiable Exponential Linear Units","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.07483","snapshot_observed_at":"2026-08-16T01:05:55.030119Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.030119Z"},"links":{"cited_paper":"/paper/1704.07483","citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:ad05df708e808c4a9c52f8d05a03cc948e7d26245b45ed4220607cf17987a88b","observation_id":"814010ea-4ffe-4287-a432-a6ec9a13c858","resolution":{"observed_at":"2026-08-16T01:05:55.030119Z","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":"2026-08-16T01:05:55.727401Z","title":"Feedback prediction for blogs","venue":null,"work_id":"8d743112-e257-4aa6-b738-e28141f9f0ae","year":2013},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.034992Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:d874b4082fa2438601557799ff6d145b48f523af2ee5ce79e5c23641f6a5cdfc","observation_id":"f01ac0f8-ca5f-4a72-8f08-e180e2f6cbf1","resolution":{"observed_at":"2026-08-16T01:05:55.731863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.038898Z","title":"and Guestrin, C","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.038898Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:dd681d4068772ad0532b3f6e674ec6ebad622b9016c00f5dc111467c9574e2b3","observation_id":"21075a42-a349-4f62-96e2-dfb62390c400","resolution":{"observed_at":"2026-08-16T01:05:55.038898Z","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":"2026-08-16T01:05:55.708189Z","title":"and Silva, R","venue":null,"work_id":"93ccfb51-c2d5-465e-9538-9c44265c4bb6","year":2020},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.042315Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:1efa5e5847dc4e91521a09a28660c5524c327c9a310e65327185b7098c5bd230","observation_id":"5bcbea17-49d4-43d6-98d5-c33771db363b","resolution":{"observed_at":"2026-08-16T01:05:55.711479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.694240Z","title":"Fast and accurate deep network learning by exponential linear units (elus)","venue":null,"work_id":"338ccf37-406e-43a8-8ffd-fc53ddf8acbd","year":2016},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.046069Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:468c5f28a1bd128750bfa3ec60004fa4d733c692cca46f9158f6f05f5252970f","observation_id":"1df3f5a4-ed81-4476-a772-9ca1d6e3eb3f","resolution":{"observed_at":"2026-08-16T01:05:55.701082Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.683236Z","title":"and Velikova, M","venue":null,"work_id":"667bf815-58a3-4afd-a99e-863441591e87","year":2010},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.049959Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:2d93634e00e79cf4aed20a3300cb991b402e6e545bcd963924786fefec62756d","observation_id":"60a1425d-2f8d-40c7-93d3-b2d401face99","resolution":{"observed_at":"2026-08-16T01:05:55.686735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.670742Z","title":"and Farid, H","venue":null,"work_id":"df99e68d-463b-4f44-b522-330827128539","year":2018},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.054489Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:1c3054210fb32f5075f8293e8e3c7e02cbde508187a8a253ecb6532174b5d38a","observation_id":"20129198-b9ce-4840-98fe-67402fd28a66","resolution":{"observed_at":"2026-08-16T01:05:55.674413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.659710Z","title":"R., Singh, S","venue":null,"work_id":"133192a2-97c2-44a8-9d10-9b3b4f88ee69","year":2022},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.060133Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:b629c639c69a04c824534477db4ddfc650ca4d6c1977715a5f46571b7e7a2ab1","observation_id":"0531a5af-2aa4-4e9d-83c3-c89130b3dca2","resolution":{"observed_at":"2026-08-16T01:05:55.663228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.648844Z","title":"Incorporating second-order functional knowledge for better option pricing","venue":null,"work_id":"43fd76dc-f8c5-4167-beb6-7f4f63ab5782","year":2000},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.063125Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:1e43cfc9b3f82f3ccdbd3eb03a933378250a11e69674c6a66bb80bc81e5f1c39","observation_id":"6f69c032-ad49-4a50-aa06-e566f2e58382","resolution":{"observed_at":"2026-08-16T01:05:55.652880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.638795Z","title":"Incorporating functional knowledge in neural networks","venue":null,"work_id":"64594bbc-1a69-4a2a-a47e-96bf283f806f","year":2009},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.067128Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:06c19820d87b939a58d02e7ed426ab9076a7f924b08d7ec8f0e758aca848ac02","observation_id":"87723832-2836-44c0-bd91-80c6237cc4c7","resolution":{"observed_at":"2026-08-16T01:05:55.642007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.629241Z","title":null,"venue":null,"work_id":"9af511f3-8358-4a16-8601-66ad4e5d6393","year":2022},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.071044Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:17b15a948a770d65eeb3bab74872e2974ce4bd7b24035712f041f24a480952ed","observation_id":"260f9f8c-07b6-49d8-a7ff-e40cee9f1722","resolution":{"observed_at":"2026-08-16T01:05:55.632561Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.074523Z","title":"and Bengio, Y","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.074523Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:94f67ad1149a2f09c073d74baa654adc83cb4b7fb6ef310398d021c8a247075a","observation_id":"aa3fa419-2ca1-43c8-8a3a-4d7b930732f2","resolution":{"observed_at":"2026-08-16T01:05:55.074523Z","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":"2026-08-16T01:05:55.608227Z","title":"Maxout networks","venue":null,"work_id":"73d3ce16-a2d7-4553-83f4-c7a81beb8cba","year":2013},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.078607Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:612dedcbd71e4d24dc3dc6c75df2260038231f27a990961d2e08a4000d507080","observation_id":"a97ebd45-9ca0-4ad1-aaaa-9a7f0d884e6f","resolution":{"observed_at":"2026-08-16T01:05:55.613602Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.596837Z","title":"How to incorporate monotonicity in deep networks while preserving flexibility? in NeurIPS, 2019","venue":null,"work_id":"9054b52e-96c0-4581-a6ca-7339f5e225e6","year":2019},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.082091Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:bc7e4e731bbc47eb236b9615f1a332cffddf81c602c8b07d391044a77e2e6266","observation_id":"ea042d7e-8fbf-4859-8679-770541a5f918","resolution":{"observed_at":"2026-08-16T01:05:55.600884Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.585088Z","title":"Monotonic calibrated interpolated look-up tables","venue":null,"work_id":"4fc8388b-08d1-4851-90e2-5c870074f143","year":2016},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.085874Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:a85db455d225c3416349a3a41eb4a6416ce5c022e49b7e69f207ae0d02ff57b0","observation_id":"dfeca548-3405-4ba7-8c2b-1bb740f05258","resolution":{"observed_at":"2026-08-16T01:05:55.589120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.089663Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.089663Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:427d1fd9fe0d732e43084e80f87d95916d6fc4fe3854c97d2a82b335dd180c81","observation_id":"62fe5640-397a-4c20-813f-afa30258ec27","resolution":{"observed_at":"2026-08-16T01:05:55.089663Z","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":"2026-08-16T01:05:55.093255Z","title":"Why relu networks yield high-confidence predictions far away from the training data and how to mitigate the problem","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.093255Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:9a3b4fd0909b9f442334147673237973560650fd0aa6483cd61d4d340e4e3c1a","observation_id":"7f7f306f-e94f-42bc-be36-9ac83151ef02","resolution":{"observed_at":"2026-08-16T01:05:55.093255Z","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":"2026-08-16T01:05:55.556882Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","venue":null,"work_id":"c7f1a8c2-c4b2-4c8a-9ec9-60d5428ecc76","year":2015},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.097329Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:0b0faa266ebbcbe6f7befb62cbbfde02e92b6db229697f97b069241ee4d2ce9b","observation_id":"14ec4b5c-09b0-4a02-9d4f-933982669ff6","resolution":{"observed_at":"2026-08-16T01:05:55.563766Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.542805Z","title":"H., Tom, B., and Barrett, J","venue":null,"work_id":"777f24d7-3f0a-4b48-8d3d-3dd0e111926b","year":2023},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.102257Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:c892b9daac4c11d1f57c02fe53c4c449abc6e8140729976ebb08af4ab5681d42","observation_id":"69c28d6a-9aac-49ae-b65e-794ce70a36ad","resolution":{"observed_at":"2026-08-16T01:05:55.547537Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.528512Z","title":"Deep learning with s-shaped rectified linear activation units","venue":null,"work_id":"0ee8c393-f71d-48f5-978b-d9e429106d91","year":2016},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.108670Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:97dc63c3201936b8bf412c01d1ae190655fef01804fe187abb984d9badb2c68d","observation_id":"5c3dad7a-06e4-4f5f-898f-781e12221c52","resolution":{"observed_at":"2026-08-16T01:05:55.534554Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.515624Z","title":"and Lee, J.-S","venue":null,"work_id":"f6c89126-8258-4cf2-823d-83dc69d86aae","year":2024},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.113187Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:96ae84b9b57db6148730093756de6efb5c3109c6eb91a6a6fbb7b3f412018db5","observation_id":"2e32d98e-1219-4459-b4b0-07d8d4b96cdc","resolution":{"observed_at":"2026-08-16T01:05:55.520512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.500771Z","title":"Self-normalizing neural networks","venue":null,"work_id":"c53d267a-eb9a-4cb9-8ef2-c7214010429d","year":2017},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.117037Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:ffe16c576fc324a411a03bf85b25a5960c028dbaee40f7900161fb364f926dcd","observation_id":"f052d654-791b-4ef3-833f-c75c7d07b33c","resolution":{"observed_at":"2026-08-16T01:05:55.505867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.487774Z","title":"Certified monotonic neural networks","venue":null,"work_id":"885063e9-7ec6-4762-bb9b-b90f2bf77751","year":2020},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.121097Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:06442a53465a3b01be034f4f3d31401b730387b7e166037bbb03e2616b6e3e21","observation_id":"4b88608f-e9af-4ad5-9971-084f0a0ebecf","resolution":{"observed_at":"2026-08-16T01:05:55.491783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.476945Z","title":"and Reichman, D","venue":null,"work_id":"fb1a2c77-997a-4938-a8d3-f05fedb0f007","year":2022},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.125149Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:82bf30b9900bf3f2328137e3e7b4ac7d59cc64304cc914f537d014681b71c7d9","observation_id":"f7e9337b-5146-49cc-8795-1c1025c1d64d","resolution":{"observed_at":"2026-08-16T01:05:55.480405Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.466046Z","title":"Fast and flexible monotonic functions with ensembles of lattices","venue":null,"work_id":"7f0fbf95-975f-4bec-b31c-88c7623b5cd0","year":2016},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.128842Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:4f9a6eea0af8225eef490a5c05cdc3a7ee87af913510437652340b9291b8dbd9","observation_id":"42938ee5-8555-4ca2-82d8-a2818aa17bff","resolution":{"observed_at":"2026-08-16T01:05:55.469852Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.456846Z","title":null,"venue":null,"work_id":"55b0cfab-d8f1-4d0b-9377-1fa275d1cd20","year":1980},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.132678Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:d644e3062ed7e7623938d7d02e1fc8e31c739d020db58398c6df22cf1cfa7a7b","observation_id":"e09ab555-b740-42bd-a3a7-685d93d3e6e1","resolution":{"observed_at":"2026-08-16T01:05:55.459816Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.136442Z","title":"and Hinton, G","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.136442Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:8569c2da38005555fc0ecb41ed6a62f1c6a0dbf178cba3ab4be21e123b355daf","observation_id":"ee61b53f-ee2b-42bc-8e7d-facf92806ff4","resolution":{"observed_at":"2026-08-16T01:05:55.136442Z","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":"2026-08-16T01:05:55.438907Z","title":"and Mart \\' nez, M","venue":null,"work_id":"413d762a-a9ba-472c-a445-924abab780a0","year":2019},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.139673Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:54a7760d716be4f7927a6b27a6bed7b5559f4398e19623ac14f82be553b482aa","observation_id":"f9f388a0-1dfd-4fde-af1b-0e2b2fba4ade","resolution":{"observed_at":"2026-08-16T01:05:55.442964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.427464Z","title":"Expressive monotonic neural networks","venue":null,"work_id":"3e5c0fbc-2cc5-4ecb-bc19-7ee0794b28d0","year":2023},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.143048Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:2ac29ac643779c1ac2dd0ed51afba58e4d88a02bd26ddd8cdb2b4c558d6710d4","observation_id":"384aac21-6831-4293-ad5d-a20936032b3c","resolution":{"observed_at":"2026-08-16T01:05:55.431359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.146444Z","title":"Fully neural network based model for general temporal point processes","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.146444Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:fcf543d9227aa5042f1e409c2a474407cf3f76f33c9b954fbd313f0a530c108d","observation_id":"77c7444b-54ba-424e-996e-aed3f473fb48","resolution":{"observed_at":"2026-08-16T01:05:55.146444Z","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":"2026-08-16T01:05:55.149909Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.149909Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:2fdf18b607ea5f665048def93f0fa2e294d290a4ba5841d9e59b979f769e9c56","observation_id":"33631b1b-3de3-4954-b34b-409e8ce0adbf","resolution":{"observed_at":"2026-08-16T01:05:55.149909Z","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":"2026-08-16T01:05:55.402490Z","title":"On the expressive power of deep neural networks","venue":null,"work_id":"0656b320-fbfa-41c3-ad38-fcb8c1cf546a","year":2017},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.153457Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:db83afb4fa9ebb908e42df8fb6d1b714da1cf983123fb89c20e74932aa69882a","observation_id":"06342426-fc12-4fea-8929-1c01d05f81c0","resolution":{"observed_at":"2026-08-16T01:05:55.406447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.391689Z","title":"and Sriraman, H","venue":null,"work_id":"48f180af-31c9-4d84-b00c-e50294cad0c7","year":2023},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.157475Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:014f68b3f5505627c16bffc8e20ebba25d7061b0d6e26441424ea0856adbd41b","observation_id":"dbf4492d-4c98-4f2d-b45a-0e2542d0b067","resolution":{"observed_at":"2026-08-16T01:05:55.395168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.379278Z","title":"and Shankaranarayana, S","venue":null,"work_id":"827745fb-d37e-40a4-a5ba-def40a847acb","year":2023},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.161037Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:31eedeb5ec24350607819ff0ca004f91108b21ee59fe19ed65cca61129d9e5af","observation_id":"ebb8843e-42bc-4c58-8b55-beb901a24e22","resolution":{"observed_at":"2026-08-16T01:05:55.383939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.364318Z","title":"Simplified models of remaining useful life based on stochastic orderings","venue":null,"work_id":"f64d5c50-c920-44d8-9204-4e274aa4563d","year":2023},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.164788Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:859aef0141a69e5c8c04df961c2e16d73a663ca3fc2b15c80ffe6b474d7632af","observation_id":"fca6ff91-761a-4130-a564-b9105eea3ee6","resolution":{"observed_at":"2026-08-16T01:05:55.368516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.346899Z","title":"and Abu-Mostafa, Y","venue":null,"work_id":"e3d9bc71-71c9-4968-bec9-8a9faca999ba","year":1996},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.168590Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:de7a911bdeebe11fd7828db06311354cd209e1491bed1b1bbe2802b21bbbb171","observation_id":"51182f28-3f76-4d7e-b7da-032207755979","resolution":{"observed_at":"2026-08-16T01:05:55.353114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.333718Z","title":"Counterexample-guided learning of monotonic neural networks","venue":null,"work_id":"276e4452-6a33-4b93-b24b-751925399195","year":2020},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.172567Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:6ee8384e63536f2b4b80d19b5606c254883de3e2fe8e5225b4b15430d0f24a73","observation_id":"40b12efd-08bb-4932-841a-c15962703033","resolution":{"observed_at":"2026-08-16T01:05:55.337520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.320431Z","title":"Review and comparison of commonly used activation functions for deep neural networks","venue":null,"work_id":"2c466be0-f3f3-4220-8cf2-c9bc9b8f01ca","year":2021},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.176231Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:8af3f2bdadd3a2ff885dbac7071e93949b2bcb51c2e74e4733d21cef1be4985a","observation_id":"ebf5d864-a7fc-4c7e-906e-379782626760","resolution":{"observed_at":"2026-08-16T01:05:55.324969Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.310303Z","title":"and Lopez-Paz, D","venue":null,"work_id":"73cb8213-7217-486c-a701-a786c75e0766","year":2019},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.179760Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:04cfb8165dcc68c895c4c6317326365db9e2c6cf9ce1ada4de246ac4e42724ea","observation_id":"b9995896-874b-40e2-9c56-6037a40d1a95","resolution":{"observed_at":"2026-08-16T01:05:55.313695Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.192417Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.192417Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:0f7ce9daef9c081576d88655bce30b6b598bed5ecd0bc84898e78f2cbc402ac9","observation_id":"39d17776-e1b5-409b-879f-a729a8ff0031","resolution":{"observed_at":"2026-08-16T01:05:55.192417Z","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":"2026-08-16T01:05:55.290441Z","title":"The resurgence of structure in deep neural networks","venue":null,"work_id":"2eb61f54-e1e7-4fa7-a46b-859b964dde4c","year":2019},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.198352Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:2973eb7d50168150849cfd71e298b7a9006d3d2dc257fbd219c371cbfded9449","observation_id":"7259c431-44d1-4d9c-ac30-b2a2f80399a2","resolution":{"observed_at":"2026-08-16T01:05:55.293855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.203781Z","title":"and Louppe, G","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.203781Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:a3d3b4b410ab6df55a3eec3b603fa5720f5ba773bf9b493bc7ae6e4ef6c30b78","observation_id":"2dade659-2205-4bb3-b65a-1f8aacbbe5e6","resolution":{"observed_at":"2026-08-16T01:05:55.203781Z","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":"2026-08-16T01:05:55.271823Z","title":"Hierarchical lattice layer for partially monotone neural networks","venue":null,"work_id":"fc3e46b9-90a1-4150-9f21-56cf89380b61","year":2022},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.208303Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:974e8188e69fb48cb7524b2d3f69f16205ef4c4dae0a00530c57f5a4edc70d70","observation_id":"ea25cc5a-4de2-45d2-b1d1-d057ccb2d709","resolution":{"observed_at":"2026-08-16T01:05:55.275522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T01:05:55.258798Z","title":"Deep lattice networks and partial monotonic functions","venue":null,"work_id":"d04d7a94-d22e-40fe-87ec-da0191836c26","year":2017},"citing_paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-16T01:05:55.212825Z"},"links":{"citing_paper":"/paper/2505.02537"},"observation_digest":"sha256:f6a654a96c772d83020d9b0ebb558a75ff53eb2a1caf1a906c783ac99f12cbd5","observation_id":"ef2155fc-8f7f-4aad-85dd-2cdbd217bc18","resolution":{"observed_at":"2026-08-16T01:05:55.264253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.02537","last_updated":"2025-05-06T11:45:55Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T10:07:13.424920Z","submitted_at":"2025-05-05T10:18:48Z","title":"Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":0,"verified_fuzzy":33},"total_outbound_references":46},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 1 inbound Pith citation observation for arXiv:2505.02537."}