{"as_of":"2026-08-05T03:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e616e0505d62a144487fec9b9c17e57b7f66f8b69111cc4a61b24d4d4033cef3","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":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":35,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T16:50:12.797817Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"pith","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":2644,"observed_at":"2026-08-05T02:28:24.338817Z","source":"pith"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2502.06809","last_updated":"2026-04-10T17:29:37Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-04T03:33:55Z","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-23T04:09:40.210836Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2502.06809"},"observation_digest":"sha256:b39c0733189dcd9e34903c1906aadfbbeb72f3f10a38aece99cbfaba7fcbc1b4","observation_id":"3bf0021b-71a8-4a60-9c62-e803254677e2","resolution":{"observed_at":"2026-05-23T04:12:30.688500Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2504.20906","last_updated":"2026-04-08T16:56:51Z","snapshot_observed_at":"2026-07-06T21:16:32.500188Z","submitted_at":"2025-04-29T16:24:11Z","title":"A Giant-Step Baby-Step Classifier For Scalable and Real-Time Anomaly Detection In Industrial Control Systems and Water Treatment Systems","version":4},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-22T18:41:14.111830Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2504.20906"},"observation_digest":"sha256:0b5167fa285796d35f0ffa3914ec6aaa3c2f287cdd1c027f8f2fca7e5c928602","observation_id":"bd779b0f-0397-454b-9883-475edfee49d0","resolution":{"observed_at":"2026-05-22T18:41:56.371932Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2505.21042","last_updated":"2025-05-27T11:24:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-27T11:24:17Z","title":"What exactly did the Transformer learn from our physics data?","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-19T13:30:18.950499Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2505.21042"},"observation_digest":"sha256:d386ec62a4650979f37ae99049ef9bf138d00e6ad3b876509fa7becf37b62455","observation_id":"095e63b9-81ac-47e5-84aa-9190c79a3b0c","resolution":{"observed_at":"2026-05-19T13:32:19.207424Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2511.01411","last_updated":"2025-11-03T10:02:21Z","snapshot_observed_at":"2026-08-02T23:32:23.419249Z","submitted_at":"2025-11-03T10:02:21Z","title":"Extremal Contours: Gradient-driven contours for compact visual attribution","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-18T01:25:27.004958Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2511.01411"},"observation_digest":"sha256:be80f8b6f2e38a08bc01d3c02627fc970f0e2a001e599a9e07567d2b0badcdb8","observation_id":"22720a27-66bf-48bf-b47f-8ed1a908b7a8","resolution":{"observed_at":"2026-05-18T01:25:34.706083Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-03T16:50:12.797817Z","title":"Sundararajan, A","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.11767","last_updated":"2025-12-12T18:26:05Z","snapshot_observed_at":"2026-08-03T16:50:05.555683Z","submitted_at":"2025-12-12T18:26:05Z","title":"Learning Minimal Representations of Fermionic Ground States","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-03T16:50:12.797817Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2512.11767"},"observation_digest":"sha256:2c8b2ce36f17fe55516dfcee368771581efc889639498dcf9b581637f4354028","observation_id":"084d9bf7-cd8b-4f44-a70f-1d68b98ee723","resolution":{"observed_at":"2026-08-03T16:50:12.797817Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-03T03:50:17.277989Z","title":"In: Proceedings of the 34th International Conference on Machine Learning arXiv:1703.01365 (2017)","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2602.06841","last_updated":"2026-05-31T17:09:07Z","snapshot_observed_at":"2026-08-03T03:50:13.129080Z","submitted_at":"2026-02-06T16:34:29Z","title":"From Features to Actions: Explainability in Traditional and Agentic AI Systems","version":4},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:17.277989Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2602.06841"},"observation_digest":"sha256:797222ab31861ad28d4b62d6620cb463a78c60a6ffba01b877443681eea41320","observation_id":"2e8285cf-785f-4480-afb1-350349f29474","resolution":{"observed_at":"2026-08-03T03:50:17.277989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2604.08502","last_updated":"2026-04-09T17:47:31Z","snapshot_observed_at":"2026-08-02T04:50:55.613198Z","submitted_at":"2026-04-09T17:47:31Z","title":"Quantifying Explanation Consistency: The C-Score Metric for CAM-Based Explainability in Medical Image Classification","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-10T18:21:16.402501Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2604.08502"},"observation_digest":"sha256:af1a293e970368340900c692e22d79bec96d7b96f5171b7c14e541f2cf75b4cf","observation_id":"57156fc0-c162-4482-9475-6b21f8aee3d9","resolution":{"observed_at":"2026-05-10T20:25:46.715000Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2604.08885","last_updated":"2026-04-10T02:48:50Z","snapshot_observed_at":"2026-08-02T07:50:45.650446Z","submitted_at":"2026-04-10T02:48:50Z","title":"Uncertainty-Aware Transformers: Conformal Prediction for Language Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-10T17:25:56.160227Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2604.08885"},"observation_digest":"sha256:4d2266b5af1d44abb5ad211b9601744033123ef9c67889beffa0bfe72306a165","observation_id":"846f7061-da46-491b-ad5e-654f5597c718","resolution":{"observed_at":"2026-05-11T06:47:09.329361Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2604.18307","last_updated":"2026-06-11T17:17:53Z","snapshot_observed_at":"2026-08-03T02:01:39.638350Z","submitted_at":"2026-04-20T14:15:57Z","title":"Reasoning Models Know What's Important, and Encode It in Their Activations","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-11T11:50:26.030339Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2604.18307"},"observation_digest":"sha256:1f7d1e251ba9ad1dfb13cbc97a3adee4cb2b7d748b0e79f12baf1dcbd72de5b0","observation_id":"bb19d8fe-ad1d-457a-9096-c5c13a8da13f","resolution":{"observed_at":"2026-07-05T12:41:04.225252Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2604.25786","last_updated":"2026-04-28T15:54:51Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-28T15:54:51Z","title":"Homogeneous Stellar Parameters from Heterogeneous Spectra with Deep Learning","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-05-07T15:44:40.727732Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2604.25786"},"observation_digest":"sha256:80f25003bccd80d7e09cda3598e9bdaaa6d34adf7619771f656f5895a53dfe61","observation_id":"f224b7f3-9f8e-4a59-bfde-cd47b0fa0143","resolution":{"observed_at":"2026-05-12T00:11:14.330354Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2604.26491","last_updated":"2026-04-29T09:55:22Z","snapshot_observed_at":"2026-07-31T17:25:21.232495Z","submitted_at":"2026-04-29T09:55:22Z","title":"TwinSpecNet: Extending APOGEE's chemical reach to low-S/N spectra via empirical paired learning","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-05-07T13:27:55.355551Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2604.26491"},"observation_digest":"sha256:4f360eab6274d57073e27c29f066c858f11efef2efeed8c38f85ff465426bec4","observation_id":"067f53dc-d5e2-49b0-8ed9-fc7e3ade0a34","resolution":{"observed_at":"2026-05-12T08:56:26.281032Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2604.27017","last_updated":"2026-04-29T12:21:43Z","snapshot_observed_at":"2026-07-06T23:12:33.898150Z","submitted_at":"2026-04-29T12:21:43Z","title":"Validating the Clinical Utility of CineECG 3D Reconstructions through Cross-Modal Feature Attribution","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-07T11:39:33.906199Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2604.27017"},"observation_digest":"sha256:6915e525a75bd7db32bca411eb29d2a3b218d7ec171cf1eeaafd6f25c8732f78","observation_id":"1127e97d-0ed6-4952-9e4a-9f8afb2713d7","resolution":{"observed_at":"2026-05-12T09:16:27.248915Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2605.01048","last_updated":"2026-05-01T19:23:33Z","snapshot_observed_at":"2026-07-06T23:14:20.123289Z","submitted_at":"2026-05-01T19:23:33Z","title":"Compared to What? Baselines and Metrics for Counterfactual Prompting","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-05-09T19:02:46.991897Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2605.01048"},"observation_digest":"sha256:1644c628258d85ada05a38568206553fb6c2b79b4b6bfd0eea041eca4b7e87ca","observation_id":"c2575b08-b386-40a6-beae-e3e53760b79e","resolution":{"observed_at":"2026-05-09T19:05:10.618453Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2605.01240","last_updated":"2026-05-08T03:44:47Z","snapshot_observed_at":"2026-08-03T03:47:15.698465Z","submitted_at":"2026-05-02T04:44:49Z","title":"Rhamba: Region-Aware Hybrid Attention-Mamba Framework for Self-Supervised Learning in Resting-State fMRI","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-09T15:16:49.719785Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2605.01240"},"observation_digest":"sha256:11a36181ca750ef0361b42bbd583be4c2cbbaa712411ef55ebec31e8a923c77b","observation_id":"8825d33b-9520-41ff-aab5-d274313d333a","resolution":{"observed_at":"2026-05-11T16:41:24.608287Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2605.01240","last_updated":"2026-05-08T03:44:47Z","snapshot_observed_at":"2026-08-03T03:47:15.698465Z","submitted_at":"2026-05-02T04:44:49Z","title":"Rhamba: Region-Aware Hybrid Attention-Mamba Framework for Self-Supervised Learning in Resting-State fMRI","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-11T00:48:28.219831Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2605.01240"},"observation_digest":"sha256:ce6c07864cb9c5ffe1f7f8c15b493629efac64401b68d8aab3ecd0dbd932049a","observation_id":"c0373115-da4a-4aa1-8d49-af6676819a9e","resolution":{"observed_at":"2026-05-11T00:50:49.915775Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2605.06143","last_updated":"2026-05-07T12:40:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-05-07T12:40:13Z","title":"AI-Generated Images: What Humans and Machines See When They Look at the Same Image","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-08T13:59:06.220904Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2605.06143"},"observation_digest":"sha256:5886d20d54f156a387834f47de7b512937f65b5ebd9b77e647a440ef3053ce07","observation_id":"f802104e-d309-4c1c-8ae1-6c02587d81b5","resolution":{"observed_at":"2026-05-11T18:46:09.861994Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2605.14255","last_updated":"2026-05-23T10:21:00Z","snapshot_observed_at":"2026-07-06T23:25:44.508166Z","submitted_at":"2026-05-14T01:48:00Z","title":"Architecture-Aware Explanation Auditing for Industrial Visual Inspection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-15T02:40:36.771439Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2605.14255"},"observation_digest":"sha256:6b5f2788613a594e4c17bcc5271e1a20fbd1e5a6928a7989d618c4d05720e3ed","observation_id":"43d9a0a7-dfbd-4240-b11d-03037e3e344f","resolution":{"observed_at":"2026-05-15T02:49:41.697402Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2605.14255","last_updated":"2026-05-23T10:21:00Z","snapshot_observed_at":"2026-07-06T23:25:44.508166Z","submitted_at":"2026-05-14T01:48:00Z","title":"Architecture-Aware Explanation Auditing for Industrial Visual Inspection","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-20T21:02:52.559284Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2605.14255"},"observation_digest":"sha256:a911be465a30cc88d1c68bce625f7bf1c71867c4111eb85c116ad4f60c78571b","observation_id":"c3c5f150-f4e7-4d09-b190-1f11f7650213","resolution":{"observed_at":"2026-05-20T21:03:46.338025Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2605.14255","last_updated":"2026-05-23T10:21:00Z","snapshot_observed_at":"2026-07-06T23:25:44.508166Z","submitted_at":"2026-05-14T01:48:00Z","title":"Architecture-Aware Explanation Auditing for Industrial Visual Inspection","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-30T21:37:34.236270Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2605.14255"},"observation_digest":"sha256:98e8077741e6c2b57093cc6b3273f5dc5525607918db8fc872c40339d0cde8c2","observation_id":"001cc30f-b8bd-499a-8371-231af17b8dd7","resolution":{"observed_at":"2026-07-01T14:25:46.312293Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2605.18768","last_updated":"2026-04-13T10:07:03Z","snapshot_observed_at":"2026-08-01T02:49:14.468592Z","submitted_at":"2026-04-13T10:07:03Z","title":"ClinQueryAgent: A Conversational Agent for Population Health Management","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-05-21T01:31:07.031424Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2605.18768"},"observation_digest":"sha256:e71481870920492f93380f407d4e8a0d68be21d6789d41e6cf75b704add30512","observation_id":"67c32e9c-65e7-47de-8633-2c6c3eb3b57b","resolution":{"observed_at":"2026-05-21T01:33:56.456701Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2605.27618","last_updated":"2026-05-26T19:38:10Z","snapshot_observed_at":"2026-07-06T23:37:16.981482Z","submitted_at":"2026-05-26T19:38:10Z","title":"Evaluating Local Explainability Metrics for Machine Learning Models on Tabular Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-29T18:22:11.550521Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2605.27618"},"observation_digest":"sha256:aeccb84172efc882183d47b59926b0859f8951774cfc558b1cc85de70ed70009","observation_id":"059802d8-a09b-4582-97bf-86e40bc8be68","resolution":{"observed_at":"2026-06-29T18:23:50.565815Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2606.03549","last_updated":"2026-06-25T16:34:14Z","snapshot_observed_at":"2026-07-06T23:43:46.458792Z","submitted_at":"2026-06-02T12:10:43Z","title":"How Many Trees in a Random Forest? A Revisited Approach with Plateau Search and Optuna Integration","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:40.761340Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2606.03549"},"observation_digest":"sha256:d2ecd9b3845e671dff0097a5fe7a79d780096364aa5b51d57a4040818e0ac654","observation_id":"688da919-bf33-469b-b94c-cec515013751","resolution":{"observed_at":"2026-07-02T02:06:27.799426Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2606.03879","last_updated":"2026-06-02T16:46:42Z","snapshot_observed_at":"2026-07-06T23:44:05.167767Z","submitted_at":"2026-06-02T16:46:42Z","title":"Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-28T11:08:36.451147Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2606.03879"},"observation_digest":"sha256:2323816a1ed703c5c5fb2cdd5ea18266e0f16c2887c2857108f0e9a6fa71426b","observation_id":"e656bbc8-24ff-4cdf-96c8-5fe73dfd223b","resolution":{"observed_at":"2026-07-02T02:16:26.511695Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2606.05328","last_updated":"2026-06-03T18:11:51Z","snapshot_observed_at":"2026-07-06T23:45:19.055840Z","submitted_at":"2026-06-03T18:11:51Z","title":"The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-06-28T02:39:24.086073Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2606.05328"},"observation_digest":"sha256:f582543d3f2d0f82a209fcf713c37b0be0559f481172e1c7af3127cf941019a8","observation_id":"02ab88c3-231f-4f1c-a87e-f330cdf27d92","resolution":{"observed_at":"2026-07-02T11:56:55.683857Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2606.10170","last_updated":"2026-06-08T21:05:03Z","snapshot_observed_at":"2026-08-02T19:39:58.776743Z","submitted_at":"2026-06-08T21:05:03Z","title":"Learning Entropy and Spatial Adaptation Dynamics of Multilayer Perceptrons for Structural Point Extraction","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-27T17:20:39.468331Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2606.10170"},"observation_digest":"sha256:1bd5e049198f527086386238be46c70a4795aab6c71fe1a29b88f5885c911d68","observation_id":"34d60f3b-fcf8-4d8e-a272-79284d8b659f","resolution":{"observed_at":"2026-06-27T17:21:06.377085Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2606.10877","last_updated":"2026-06-09T13:52:05Z","snapshot_observed_at":"2026-08-03T13:58:29.748815Z","submitted_at":"2026-06-09T13:52:05Z","title":"XtrAIn: Training-Guided Occlusion for Feature Attribution","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-06-27T13:37:35.691503Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2606.10877"},"observation_digest":"sha256:c4ab4bce7e780b3aa4fc9b0d2eb6106033e5b668e1a20a4109ae0216576594f4","observation_id":"0682601a-5cbc-4210-9cd2-8d9d2fa0ac7d","resolution":{"observed_at":"2026-07-03T04:47:38.388277Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2606.12490","last_updated":"2026-06-10T11:30:37Z","snapshot_observed_at":"2026-08-02T18:32:03.971235Z","submitted_at":"2026-06-10T11:30:37Z","title":"Robustness Verification of Recurrent Neural Networks with Abstraction Refinement","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-27T10:16:46.361017Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2606.12490"},"observation_digest":"sha256:dec854dc39647bf330c6cd454a64ec17ea747807d7fbcb42f6d3e127584dd06f","observation_id":"17505f0f-72c8-4b20-a425-7adb614a1a58","resolution":{"observed_at":"2026-07-03T10:07:55.788433Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2606.12661","last_updated":"2026-06-10T20:45:04Z","snapshot_observed_at":"2026-07-06T23:51:31.502574Z","submitted_at":"2026-06-10T20:45:04Z","title":"Finding Novel Precursors for Solar Wind Stream Interaction Regions with Interpretable Deep Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-11T11:50:26.030339Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2606.12661"},"observation_digest":"sha256:1e5e8d9fc8b9109f8261cb7c888603905a6b5f7ac7c13405160ad682d91ed76d","observation_id":"e3e229e1-f4a5-4a90-9789-2a8ec37c4d0b","resolution":{"observed_at":"2026-06-28T07:31:45.572547Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2606.22858","last_updated":"2026-06-22T05:05:36Z","snapshot_observed_at":"2026-07-06T23:57:42.632111Z","submitted_at":"2026-06-22T05:05:36Z","title":"The Unseen Hand: Manipulating Model Fairness and SHAP with Targeted Identity Re-Association Attacks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-26T09:07:42.347940Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2606.22858"},"observation_digest":"sha256:7a1374617105ae80a68b6b3d6f545108fadfa2f881e9716e18df29f7637d5369","observation_id":"285beac1-9545-40ed-a83b-2ab7ddef75a1","resolution":{"observed_at":"2026-07-04T10:09:44.809272Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2606.23591","last_updated":"2026-06-22T17:00:04Z","snapshot_observed_at":"2026-08-02T00:14:44.848420Z","submitted_at":"2026-06-22T17:00:04Z","title":"Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-06-26T08:45:34.884703Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2606.23591"},"observation_digest":"sha256:5a28e10b989c9a0bd99b3d8dc469f55a05dcc3ff00ae6b591128e12d64c9fb2f","observation_id":"5068adef-fbee-4ca6-80f6-843e6b674273","resolution":{"observed_at":"2026-06-26T08:49:14.905017Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2606.29139","last_updated":"2026-06-28T01:00:22Z","snapshot_observed_at":"2026-08-02T06:47:47.746404Z","submitted_at":"2026-06-28T01:00:22Z","title":"How Token Influence Decays with Distance: A Green-Function View of Trained Language Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-30T08:20:19.514808Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2606.29139"},"observation_digest":"sha256:c5a0aced74f15388f6c7b5efa6b0001ba12c40751a5ea9dddc49e42a69b62ace","observation_id":"8bc784f1-a7c5-4ab9-bc60-b5efbf20153e","resolution":{"observed_at":"2026-06-30T08:24:26.461094Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2606.31291","last_updated":"2026-06-30T08:06:07Z","snapshot_observed_at":"2026-07-07T00:05:02.977105Z","submitted_at":"2026-06-30T08:06:07Z","title":"Deep Reinforcement Learning for Spacecraft Attitude Control During Atmospheric Re-Entry","version":1},"reference_index":114,"source":"arxiv_source","source_observed_at":"2026-07-01T06:15:03.638533Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2606.31291"},"observation_digest":"sha256:3c998aa901fdb7cf7dd3f9782a619798c7724e47583c84d3ccec7fb8d2292f65","observation_id":"f74463b9-41a7-48ee-a79f-ae58a8345cd7","resolution":{"observed_at":"2026-07-01T09:45:40.130880Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":"1703.01365","doi":"10.48550/arxiv.1703.01365","metadata_source":"pith","pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Axiomatic Attribution for Deep Networks","venue":"cs.LG","work_id":"477b01a5-d0db-4fd3-82bb-fd705dc04457","year":2017},"citing_paper":{"arxiv_id":"2607.05175","last_updated":"2026-07-06T14:57:26Z","snapshot_observed_at":"2026-08-04T23:24:37.103099Z","submitted_at":"2026-07-06T14:57:26Z","title":"Platonic Projection Structures: Operator-Induced Observability in Representation Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-08T01:11:35.146386Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2607.05175"},"observation_digest":"sha256:2c4786caba8f95dfcdea2b3b33a6ee8b81a19338ebd7d967f3897bbd45c33dad","observation_id":"041576cf-09c8-4ed3-b60e-068859b9b3af","resolution":{"observed_at":"2026-07-08T01:14:27.335083Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.207207+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-07-31T10:48:17.195128Z","title":"In: 34th International Conference on Machine Learning, ICML 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.24608","last_updated":"2026-07-27T16:10:02Z","snapshot_observed_at":"2026-07-31T10:48:15.839300Z","submitted_at":"2026-07-27T16:10:02Z","title":"Attribution and Uncertainty Behavior of Learned Residual Gyro Correction for Gyro-Stellar Estimation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-31T10:48:17.195128Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2607.24608"},"observation_digest":"sha256:2adaa485f7f6ec7f7e4eb572a1b9ab4f8a0585b10c626e2d7e0ae7b35756e13e","observation_id":"9a7c105f-7126-4ed4-ae76-abacdd478591","resolution":{"observed_at":"2026-07-31T10:48:17.195128Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-01T03:04:00.085519Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.25244","last_updated":"2026-07-28T03:38:03Z","snapshot_observed_at":"2026-08-02T06:57:50.841605Z","submitted_at":"2026-07-28T03:38:03Z","title":"CADENCE: A Cardiac Atom Dictionary for Interpretable Neural Concept Extraction from ECG Foundation Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T03:04:00.085519Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2607.25244"},"observation_digest":"sha256:5de962ca1df6cc67186e741eda46338687988cb3916159cfd4b2ef8b53e84976","observation_id":"80cf757b-d70e-4e6e-a85d-118fdf971107","resolution":{"observed_at":"2026-08-01T03:04:00.085519Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1703.01365/citation-record","integrity":"/paper/1703.01365/integrity","json":"/paper/1703.01365/citation-record.json","paper":"/paper/1703.01365"},"outbound":[],"paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T05:32:18.507883Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 35 inbound Pith citation observations for arXiv:1703.01365."}