{"as_of":"2026-08-21T15:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:99e49c912e795def0790d0b7b9f0729a0871adad640a5352d41031c9d49207cc","coverage":[{"denominator":17,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":17,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T10:49:01.974430Z","state":"measured"},{"denominator":18,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":18,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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":"2026-08-16T05:04:06.366517Z","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":"2026-08-16T05:04:06.787431Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"cited_work":{"arxiv_id":"1908.10382","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.10382","snapshot_observed_at":"2026-08-16T05:04:06.787431Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","venue":"stat.ML","work_id":"d5cd7637-7a6b-4b94-ae6d-fe1e2e69afc3","year":2019},"citing_paper":{"arxiv_id":"2504.21581","last_updated":"2025-08-02T12:55:19Z","snapshot_observed_at":"2026-08-19T02:34:02.860142Z","submitted_at":"2025-04-30T12:38:42Z","title":"Make Both Ends Meet: A Synergistic Optimization Infrared Small Target Detection with Streamlined Computational Overhead","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T05:04:06.366517Z"},"links":{"cited_paper":"/paper/1908.10382","citing_paper":"/paper/2504.21581"},"observation_digest":"sha256:b47158f591475aca2096dc8d485203bbe0986f8067f7be3d4f02145edbdf7647","observation_id":"41a51c02-7713-45da-a87c-c0384f0650ae","resolution":{"observed_at":"2026-08-16T05:04:06.792703Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1908.10382/citation-record","integrity":"/paper/1908.10382/integrity","json":"/paper/1908.10382/citation-record.json","paper":"/paper/1908.10382"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1901.09346","last_updated":"2019-01-31T04:35:55Z","snapshot_observed_at":"2026-08-15T17:15:59.064953Z","submitted_at":"2019-01-27T09:48:49Z","title":"Concrete Autoencoders for Differentiable Feature Selection and Reconstruction","version":2},"cited_work":{"arxiv_id":"1901.09346","doi":null,"metadata_source":"pith","pith_arxiv_id":"1901.09346","snapshot_observed_at":"2026-08-14T10:49:02.081998Z","title":"Concrete Autoencoders for Differentiable Feature Selection and Reconstruction","venue":"cs.LG","work_id":"efa98611-9b18-44d0-a3af-8de403c7446f","year":2019},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.870610Z"},"links":{"cited_paper":"/paper/1901.09346","citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:420b76300006b40b8bcb333f0ce3ba4b24e84b5f89aa1c4e37e3eac917abc0f1","observation_id":"5b3abd41-a45c-439a-a1d5-e678e36631af","resolution":{"observed_at":"2026-08-14T10:49:02.086338Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.04310","last_updated":"2018-06-12T03:03:13Z","snapshot_observed_at":"2026-08-15T11:12:05.411348Z","submitted_at":"2018-06-12T03:03:13Z","title":"MISSION: Ultra Large-Scale Feature Selection using Count-Sketches","version":1},"cited_work":{"arxiv_id":"1806.04310","doi":null,"metadata_source":"pith","pith_arxiv_id":"1806.04310","snapshot_observed_at":"2026-08-14T10:49:02.064215Z","title":"MISSION: Ultra Large-Scale Feature Selection using Count-Sketches","venue":"cs.DS","work_id":"da49c738-5314-4511-95fa-633fc855ac9b","year":2018},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.881349Z"},"links":{"cited_paper":"/paper/1806.04310","citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:e6d5999a97cf173089e1ae5c1fd74ba3daf301c984566e8ab67c7b07525cfe46","observation_id":"a60ffe2a-24d3-4566-9561-416ce1929475","resolution":{"observed_at":"2026-08-14T10:49:02.070268Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T10:49:02.196881Z","title":null,"venue":null,"work_id":"f2098269-963e-4359-8d4d-8b0959e9bf56","year":2003},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.889132Z"},"links":{"citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:054a0fc525575bc55653f287a95a40ff7f1ad5824f5b5870d6bc390649d90d77","observation_id":"942949b6-4858-46d5-a3e9-e012b42087ad","resolution":{"observed_at":"2026-08-14T10:49:02.201190Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T10:49:02.184878Z","title":"Guyon and A","venue":null,"work_id":"0361eacc-961e-483a-8bf8-c277f3561058","year":2003},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.897939Z"},"links":{"citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:93868540059f17911e4d52c1ee6ff4474f6eced7704c39d5fabd206f061c8250","observation_id":"b6437bf3-27f7-40a4-9b8b-2b4ee9832082","resolution":{"observed_at":"2026-08-14T10:49:02.188982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01144","last_updated":"2017-08-05T22:45:19Z","snapshot_observed_at":"2026-08-15T03:05:41.956181Z","submitted_at":"2016-11-03T19:48:08Z","title":"Categorical Reparameterization with Gumbel-Softmax","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01144","snapshot_observed_at":"2026-08-14T10:49:01.931453Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.931453Z"},"links":{"cited_paper":"/paper/1611.01144","citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:d571adecdadab956d5f707e4ab93398282858fb69942b341fbec4513f4539310","observation_id":"befeffad-6f6c-4632-a3d7-25e9e33415e6","resolution":{"observed_at":"2026-08-14T10:49:01.931453Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","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":"2026-08-14T10:49:01.935671Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.935671Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:9d6c06fc22f43c1e7d2e8c294757767a9bc308cbc0900615a4b4f88037204ec3","observation_id":"eb9cd5b7-6199-4484-ae83-c1bb4b03e941","resolution":{"observed_at":"2026-08-14T10:49:01.935671Z","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":"2026-08-14T10:49:02.174360Z","title":"Kohavi and G","venue":null,"work_id":"841202b9-4b32-4bbf-b2da-94d80fc63d60","year":1997},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.939867Z"},"links":{"citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:7fd1f390cf548af35b9011e418c6956396403bf906f97950b162d205e6135a28","observation_id":"36952c3a-9256-4d90-be26-b6795c86f772","resolution":{"observed_at":"2026-08-14T10:49:02.177951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.01626","last_updated":"2019-03-25T04:47:51Z","snapshot_observed_at":"2026-08-21T14:47:04.187896Z","submitted_at":"2018-05-04T06:57:19Z","title":"Estimating Learnability in the Sublinear Data Regime","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.01626","snapshot_observed_at":"2026-08-14T10:49:01.943175Z","title":"Kong and G","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.943175Z"},"links":{"cited_paper":"/paper/1805.01626","citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:c2c08e341e217c19310db1899ee9c65026a83fb6b9cf478fd338300f353bfa4a","observation_id":"e9f718bc-a829-4977-b81a-c0c226a123d3","resolution":{"observed_at":"2026-08-14T10:49:01.943175Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.09055","last_updated":"2019-04-23T06:29:32Z","snapshot_observed_at":"2026-08-15T06:40:14.261008Z","submitted_at":"2018-06-24T00:06:13Z","title":"DARTS: Differentiable Architecture Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.09055","snapshot_observed_at":"2026-08-14T10:49:01.947345Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.947345Z"},"links":{"cited_paper":"/paper/1806.09055","citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:13bbece6656291cd70c23d7843b80e0baa5e0f043204dc43b7e01afb3902d477","observation_id":"a12603b2-1d81-4e39-b37b-faff0e61f022","resolution":{"observed_at":"2026-08-14T10:49:01.947345Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.00712","last_updated":"2017-03-05T16:59:44Z","snapshot_observed_at":"2026-08-15T03:06:21.621383Z","submitted_at":"2016-11-02T18:25:40Z","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.00712","snapshot_observed_at":"2026-08-14T10:49:01.950810Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.950810Z"},"links":{"cited_paper":"/paper/1611.00712","citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:d50320093ba0c7ceb9496feec22da30981799e837c9799e0ad55c09405e03554","observation_id":"99f68136-a7ad-42e9-a575-5f6139dd391e","resolution":{"observed_at":"2026-08-14T10:49:01.950810Z","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":"2026-08-14T10:49:02.163575Z","title":null,"venue":null,"work_id":"14ff086b-5f53-4907-aafd-8de9ff6b9299","year":1995},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.954146Z"},"links":{"citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:3b5add5eedfcc4f60049a0775c7a0309bef6ea7f6f43b7866eb38c55147c9e5a","observation_id":"7aa197c8-1d05-4936-976c-e7c1c0468ff8","resolution":{"observed_at":"2026-08-14T10:49:02.167077Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T10:49:02.152568Z","title":"Saeys, I","venue":null,"work_id":"4fa0d3da-1657-4213-935e-b8f1c091a8c9","year":2007},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.957665Z"},"links":{"citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:48c8c7668bbe56ef9d04797da641ca76d93cf8b957dfc7b29f0da49191586f2e","observation_id":"d8c423e4-3516-48a4-98aa-dac56f2b2c90","resolution":{"observed_at":"2026-08-14T10:49:02.156086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T10:49:02.141092Z","title":null,"venue":null,"work_id":"43d5d5bc-d2e6-41fe-8468-a574f0a17c58","year":2009},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.961451Z"},"links":{"citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:9b50e3b4d6a896393090c7d761985ab9238ed1d840c5ad3fcb27187bd53c7a0c","observation_id":"de25dd09-ae27-4339-a9d1-9941301b6b7b","resolution":{"observed_at":"2026-08-14T10:49:02.144615Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T10:49:02.128622Z","title":"Tibshirani","venue":null,"work_id":"7591d48f-8ed1-4fde-b80b-1726fca9f349","year":1996},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.964664Z"},"links":{"citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:e7c05208412a2df2ff0aef831ab6faf59696a9810510cf096849600016b0ceaa","observation_id":"cfd2682b-2f5f-41d3-aac3-eef846a57d2c","resolution":{"observed_at":"2026-08-14T10:49:02.133031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T10:49:02.117111Z","title":null,"venue":null,"work_id":"47d55c72-19cf-40cd-ac02-65bdb388b2e6","year":2014},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.967933Z"},"links":{"citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:e95414a8cbab623cef107b9754dbc3b951aa2afcef9dfe2db97d13edeeddb78a","observation_id":"addb49fe-662d-4134-8821-a50cc51195fb","resolution":{"observed_at":"2026-08-14T10:49:02.120767Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T10:49:02.106083Z","title":"Yu and H","venue":null,"work_id":"9b6f2fd2-ee82-43fd-8414-9bb89b2b5795","year":2003},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.971207Z"},"links":{"citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:9c6fc5b49f4fe6b6ca8100a50247760f34569816f5eb01a80afb1d6760079948","observation_id":"86c7a07f-26bf-4dc4-ae92-ccb38f0ec4d6","resolution":{"observed_at":"2026-08-14T10:49:02.109637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-14T10:49:02.094932Z","title":"Yu and H","venue":null,"work_id":"1b3d5fc4-3b1c-4706-9793-476886f1c92e","year":2004},"citing_paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-14T10:49:01.974430Z"},"links":{"citing_paper":"/paper/1908.10382"},"observation_digest":"sha256:b2b3691905e3d25e555b1de60789aa18bf770691e025433687f9b7c820f27018","observation_id":"b742191f-2785-4175-8309-7cb9b37bcebf","resolution":{"observed_at":"2026-08-14T10:49:02.098424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.10382","last_updated":"2019-08-27T18:02:11Z","latest_version":1,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-21T13:13:15.477195Z","submitted_at":"2019-08-27T18:02:11Z","title":"Feature Gradients: Scalable Feature Selection via Discrete Relaxation"},"reference_resolution":{"displayed":17,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":2,"verified_fuzzy":6},"total_outbound_references":17},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 1 inbound Pith citation observation for arXiv:1908.10382."}