{"as_of":"2026-08-09T22:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ec7770e551c716861727873090ab51ef8d843e93580f039d5f0e191284c4d91e","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":17,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":17,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":17,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":17,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:26:32.988235Z","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":"2026-07-04T06:19:38.882684Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":"1703.04730","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-07-04T06:19:38.882684Z","title":"arXiv:1703.04730 [cs, stat] , author =","venue":null,"work_id":"c60d6497-3724-4a3c-99e9-b230c013d45b","year":2020},"citing_paper":{"arxiv_id":"1907.08657","last_updated":"2019-07-19T19:27:14Z","snapshot_observed_at":"2026-07-06T08:08:56.355510Z","submitted_at":"2019-07-19T19:27:14Z","title":"Learning More From Less: Towards Strengthening Weak Supervision for Ad-Hoc Retrieval","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-24T18:42:45.418392Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/1907.08657"},"observation_digest":"sha256:32736751602dca1b406c20581482a3e3a5c64836fcc03a5ae656c92042f46e7b","observation_id":"9122ca2a-26d2-4016-94ba-dceadd4403f3","resolution":{"observed_at":"2026-05-24T18:44:49.315388Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":"1703.04730","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-07-04T06:19:38.882684Z","title":"arXiv:1703.04730 [cs, stat] , author =","venue":null,"work_id":"c60d6497-3724-4a3c-99e9-b230c013d45b","year":2020},"citing_paper":{"arxiv_id":"1909.01066","last_updated":"2019-09-04T09:33:20Z","snapshot_observed_at":"2026-07-06T08:18:37.267833Z","submitted_at":"2019-09-03T11:11:08Z","title":"Language Models as Knowledge Bases?","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-05-16T10:51:45.447733Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/1909.01066"},"observation_digest":"sha256:c87c6e688236825dd8da20ddcaa9e95e1a3eabeab53488836243cb0a815451cb","observation_id":"332d541b-eb1f-479c-9c02-957200b33d07","resolution":{"observed_at":"2026-05-16T10:51:45.810779Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-08-06T17:26:32.988235Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10886","last_updated":"2025-07-15T00:59:42Z","snapshot_observed_at":"2026-08-09T20:08:36.691731Z","submitted_at":"2025-07-15T00:59:42Z","title":"How to Protect Models against Adversarial Unlearning?","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T17:26:32.988235Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2507.10886"},"observation_digest":"sha256:92c55ba2d867f88ebdf3fa3fa58efc76d35d5ca35cb3397f88930d23243a4be6","observation_id":"42ddc9e5-d103-47c2-99ed-1fa08c2726d1","resolution":{"observed_at":"2026-08-06T17:26:32.988235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-08-06T10:58:05.967606Z","title":"W.; and Liang, P","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.23291","last_updated":"2025-08-03T23:23:03Z","snapshot_observed_at":"2026-08-09T09:39:32.022353Z","submitted_at":"2025-07-31T07:09:52Z","title":"Evaluating the Dynamics of Membership Privacy in Deep Learning","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-06T10:58:05.967606Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2507.23291"},"observation_digest":"sha256:a5f00e2a14e567759bbb32c3da6835ef21bff797b88820f6ae1f95e1ab742f0c","observation_id":"fa4bdcb8-5bcc-4560-bf57-b462143da1ae","resolution":{"observed_at":"2026-08-06T10:58:05.967606Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-08-04T10:05:14.440621Z","title":"Understanding black-box predictions via influence functions, December 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.12071","last_updated":"2026-06-09T09:56:26Z","snapshot_observed_at":"2026-08-07T13:20:46.043762Z","submitted_at":"2025-10-14T02:21:23Z","title":"Influence Dynamics and Stagewise Data Attribution","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:14.440621Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2510.12071"},"observation_digest":"sha256:090155817125a9a4911cdb98351cd1acc3a7715f90fcd63f750e24428cdd0ea5","observation_id":"683381e6-0376-4a69-ad10-3e586deb8ae9","resolution":{"observed_at":"2026-08-04T10:05:14.440621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-08-03T18:28:32.268921Z","title":"Alex Krizhevsky, Geoffrey Hinton, et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.05254","last_updated":"2026-07-29T23:30:29Z","snapshot_observed_at":"2026-08-09T15:32:48.696471Z","submitted_at":"2025-12-04T21:10:31Z","title":"When unlearning is free: leveraging low influence points to reduce computational costs","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T18:28:32.268921Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2512.05254"},"observation_digest":"sha256:cb3df186b5b7fd910f5804912e143347550e083c101ddb3d7c6c489b40714efd","observation_id":"0a748625-897f-4672-8df3-7e4b3380310d","resolution":{"observed_at":"2026-08-03T18:28:32.268921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-08-03T06:35:42.846711Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.22651","last_updated":"2026-06-01T06:29:25Z","snapshot_observed_at":"2026-08-07T22:51:52.958241Z","submitted_at":"2026-01-30T07:10:59Z","title":"GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning","version":2},"reference_index":2002,"source":"pdf_text","source_observed_at":"2026-08-03T06:35:42.846711Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2601.22651"},"observation_digest":"sha256:ae9c8e51fc1a398ea92c4e36ccbc6bfde9d0cda1d06db299ebf9fee726608e23","observation_id":"207e8ca3-091c-4d4e-b8d7-faf936a6859f","resolution":{"observed_at":"2026-08-03T06:35:42.846711Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":"1703.04730","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-07-04T06:19:38.882684Z","title":"arXiv:1703.04730 [cs, stat] , author =","venue":null,"work_id":"c60d6497-3724-4a3c-99e9-b230c013d45b","year":2020},"citing_paper":{"arxiv_id":"2604.16197","last_updated":"2026-07-19T20:58:40Z","snapshot_observed_at":"2026-08-07T01:48:38.832815Z","submitted_at":"2026-04-17T16:07:11Z","title":"Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-10T08:47:36.122054Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2604.16197"},"observation_digest":"sha256:fbf7c6fbd06230ac05efb64c92c19decda5fd9aa8fc03fdfb49f3dbfcc80d3f5","observation_id":"25756fc6-8e5a-47b0-a809-10440d6bfb2e","resolution":{"observed_at":"2026-05-10T08:48:01.070059Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-08-02T16:12:09.386234Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2604.16197","last_updated":"2026-07-19T20:58:40Z","snapshot_observed_at":"2026-08-07T01:48:38.832815Z","submitted_at":"2026-04-17T16:07:11Z","title":"Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-02T16:12:09.386234Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2604.16197"},"observation_digest":"sha256:34aa770c51957162769a65552a9b25a16ad68bf4f83aade065523f7c9135d14d","observation_id":"86c168f7-4dc6-4375-8c87-c100414036ab","resolution":{"observed_at":"2026-08-02T16:12:09.386234Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":"1703.04730","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-07-04T06:19:38.882684Z","title":"arXiv:1703.04730 [cs, stat] , author =","venue":null,"work_id":"c60d6497-3724-4a3c-99e9-b230c013d45b","year":2020},"citing_paper":{"arxiv_id":"2604.28154","last_updated":"2026-04-30T17:42:12Z","snapshot_observed_at":"2026-07-06T23:13:29.310140Z","submitted_at":"2026-04-30T17:42:12Z","title":"Mapping data sensitivities in global QCD analysis with linear response and influence functions","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-07T07:11:36.939657Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2604.28154"},"observation_digest":"sha256:1e4ac3be0787425f3b701f8b83ee6da3b5c9dac8cc928d2e150fc2cc6831a2d5","observation_id":"edd46b5a-9b4c-4c09-b197-2d54b0edd7da","resolution":{"observed_at":"2026-05-12T10:11:28.387642Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":"1703.04730","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-07-04T06:19:38.882684Z","title":"arXiv:1703.04730 [cs, stat] , author =","venue":null,"work_id":"c60d6497-3724-4a3c-99e9-b230c013d45b","year":2020},"citing_paper":{"arxiv_id":"2605.08007","last_updated":"2026-05-08T16:59:38Z","snapshot_observed_at":"2026-08-04T08:15:28.547850Z","submitted_at":"2026-05-08T16:59:38Z","title":"Interpreting Reinforcement Learning Agents with Susceptibilities","version":1},"reference_index":119,"source":"arxiv_source","source_observed_at":"2026-05-11T02:47:40.996583Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2605.08007"},"observation_digest":"sha256:138c92a37592ff04b4fd16eb352299e7b6024c798cc09c479251b278756a65c3","observation_id":"9a260e86-97d3-4a97-ad1a-55a68850e789","resolution":{"observed_at":"2026-05-11T03:05:55.348566Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":"1703.04730","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-07-04T06:19:38.882684Z","title":"arXiv:1703.04730 [cs, stat] , author =","venue":null,"work_id":"c60d6497-3724-4a3c-99e9-b230c013d45b","year":2020},"citing_paper":{"arxiv_id":"2605.21422","last_updated":"2026-06-01T04:58:51Z","snapshot_observed_at":"2026-07-06T23:31:51.443407Z","submitted_at":"2026-05-20T17:15:43Z","title":"PRISM: Preference-Aware Influence Function Based Data Selection Method for Efficient Fine-Tuning","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-30T17:01:21.521025Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2605.21422"},"observation_digest":"sha256:b5c4ba115971952588793e4bd5a12e3bb79ab3fef0313bb6bd3c1e283aeead9d","observation_id":"cff1b5a3-8135-44f6-9b0e-caf64f14f20a","resolution":{"observed_at":"2026-06-30T17:04:56.643545Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":"1703.04730","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-07-04T06:19:38.882684Z","title":"arXiv:1703.04730 [cs, stat] , author =","venue":null,"work_id":"c60d6497-3724-4a3c-99e9-b230c013d45b","year":2020},"citing_paper":{"arxiv_id":"2605.26971","last_updated":"2026-05-26T12:57:12Z","snapshot_observed_at":"2026-08-07T18:23:52.993798Z","submitted_at":"2026-05-26T12:57:12Z","title":"RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-06-29T19:34:12.081362Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2605.26971"},"observation_digest":"sha256:5df1bbefd7dd001e6e51797e34535580a8545908525801d30c7fc8e0148bd737","observation_id":"f33a1bdb-f920-446f-9488-d82e1e082285","resolution":{"observed_at":"2026-06-29T19:43:55.126095Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":"1703.04730","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-07-04T06:19:38.882684Z","title":"arXiv:1703.04730 [cs, stat] , author =","venue":null,"work_id":"c60d6497-3724-4a3c-99e9-b230c013d45b","year":2020},"citing_paper":{"arxiv_id":"2605.30462","last_updated":"2026-05-28T18:38:15Z","snapshot_observed_at":"2026-07-06T23:39:43.967889Z","submitted_at":"2026-05-28T18:38:15Z","title":"idSCD: Identifying Training Datasets through Semantic Correlation Descriptors","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-06-29T08:35:36.928378Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2605.30462"},"observation_digest":"sha256:52ceec50d1703591b13d5b355d70b608b1649136c08ab60324ca5c608c099798","observation_id":"8989d349-9be5-4595-ab05-4e701a3c7df0","resolution":{"observed_at":"2026-06-29T08:43:15.862994Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":"1703.04730","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-07-04T06:19:38.882684Z","title":"arXiv:1703.04730 [cs, stat] , author =","venue":null,"work_id":"c60d6497-3724-4a3c-99e9-b230c013d45b","year":2020},"citing_paper":{"arxiv_id":"2606.21306","last_updated":"2026-06-19T10:38:00Z","snapshot_observed_at":"2026-08-06T11:08:07.178903Z","submitted_at":"2026-06-19T10:38:00Z","title":"Towards Dys-XAI: Influence-Based Explanations for Dysarthria Severity Assessment","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-26T14:31:46.594002Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2606.21306"},"observation_digest":"sha256:73cc6b775515306ca33e172ff319a46fb7d909e5b3498aa4235b6b8ad47bd1fa","observation_id":"29c493bd-8324-49f8-8aaa-13f151e3e33a","resolution":{"observed_at":"2026-07-04T06:19:38.884427Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":"1703.04730","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-07-04T06:19:38.882684Z","title":"arXiv:1703.04730 [cs, stat] , author =","venue":null,"work_id":"c60d6497-3724-4a3c-99e9-b230c013d45b","year":2020},"citing_paper":{"arxiv_id":"2607.00325","last_updated":"2026-07-01T01:55:14Z","snapshot_observed_at":"2026-08-03T04:46:54.117886Z","submitted_at":"2026-07-01T01:55:14Z","title":"Watermarking for Proprietary Dataset Protection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-02T16:09:50.072430Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2607.00325"},"observation_digest":"sha256:7239a9dfaa63c513531ab1b4ff7cadf98510ea888f2d06c6decb800d4a3c9eab","observation_id":"cf2d568d-a380-49b0-b067-c3e2b242877b","resolution":{"observed_at":"2026-07-02T16:17:08.439151Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-08-02T02:44:33.262620Z","title":"Understanding black-box predictions via influence functions, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14242","last_updated":"2026-07-15T18:03:08Z","snapshot_observed_at":"2026-08-06T07:44:58.399871Z","submitted_at":"2026-07-15T18:03:08Z","title":"Implicit Reasoning Steering via Concept Chaining","version":1},"reference_index":132,"source":"arxiv_source","source_observed_at":"2026-08-02T02:44:33.262620Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2607.14242"},"observation_digest":"sha256:344e89f50f9bc4003c3f3f06e7930f9fd875d23ccc86b74245cb9e3a53303d12","observation_id":"3dcbbd04-ac65-491e-a04e-19941dbec998","resolution":{"observed_at":"2026-08-02T02:44:33.262620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1703.04730/citation-record","integrity":"/paper/1703.04730/integrity","json":"/paper/1703.04730/citation-record.json","paper":"/paper/1703.04730"},"outbound":[],"paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","latest_version":3,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-03T04:46:56.967070Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 17 inbound Pith citation observations for arXiv:1703.04730."}