{"as_of":"2026-08-20T21:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:62bf655896739d3884af8096b1ce8301fed5d6a2b0d3dff970936fad9494cbb4","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T04:16:36.170249Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.06258/citation-record","integrity":"/paper/2505.06258/integrity","json":"/paper/2505.06258/citation-record.json","paper":"/paper/2505.06258"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:16:37.321046Z","title":"Evaluating the quality of machine learning explanations: A survey on methods and metrics,","venue":null,"work_id":"c2fcb2ec-3ff6-4b9a-8ba8-58e98135cb5a","year":2021},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.871188Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:5a69870ac0ab310537d5e5ca1b42f7ebec98a036c7c1a89ce5e92f98a8d49e96","observation_id":"7c71cdce-e182-41e1-bc1b-8130d874a3b6","resolution":{"observed_at":"2026-08-16T04:16:37.328249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:16:35.878762Z","title":"Axiomatic attribution for deep networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.878762Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:0c50eb269e45e3301d01b53fc4e09bdab239bc9006bd52ac0f03380aae8440a6","observation_id":"69ca1a7f-a085-4c4f-a4b5-f9e3b2caefb9","resolution":{"observed_at":"2026-08-16T04:16:35.878762Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.11257","last_updated":"2021-10-06T02:21:53Z","snapshot_observed_at":"2026-08-18T03:38:49.566214Z","submitted_at":"2021-03-20T22:36:39Z","title":"Robust Models Are More Interpretable Because Attributions Look Normal","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.11257","snapshot_observed_at":"2026-08-16T04:16:35.887767Z","title":"Robust models are more interpretable because attributions look normal,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.887767Z"},"links":{"cited_paper":"/paper/2103.11257","citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:ba9ae9c765a1fd9fe4c9f56c0ac923e3b96a93c4616f22a81e29ca66cff68db0","observation_id":"633a93cc-1faa-4d6d-a8d6-d96de5bca032","resolution":{"observed_at":"2026-08-16T04:16:35.887767Z","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":"2026-08-16T04:16:37.273407Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization,","venue":null,"work_id":"b1a23338-01a5-4961-b74f-adb05479ce93","year":2017},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.894756Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:6b9d7d6c645a0ecfee31b6e989068a79ad54d3d52698c318fc58cf2d9644aebb","observation_id":"3e698571-dd1a-4230-8de7-7ccbfdf9572d","resolution":{"observed_at":"2026-08-16T04:16:37.281177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:37.254011Z","title":"Explaining deep neural network models with adversarial gradient integration,","venue":null,"work_id":"35845e21-f97d-4b85-ad0a-906511ca0da8","year":2021},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.900213Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:aa9e1702cb2db01d36dafcefecd471eba859d036efb18a89c8134323ecdd2bb8","observation_id":"d7646b40-2ab4-43f8-98d4-026d24be1efc","resolution":{"observed_at":"2026-08-16T04:16:37.258870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:37.224786Z","title":"Mfaba: A more faithful and accelerated boundary-based attribution method for deep neural networks,","venue":null,"work_id":"4cda45b2-a698-4d3a-87e5-ad3672dd1f5f","year":2024},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.907080Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:d263ae0ce2962fb866648d2d97b4526b31f9cbec1fabc3e242650cfb8cf043f4","observation_id":"260ab4f5-1a77-4750-87c7-a3f36db5c3eb","resolution":{"observed_at":"2026-08-16T04:16:37.238530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:37.200749Z","title":"Attexplore: Attribution for explanation with model parameters exploration,","venue":null,"work_id":"a0828f7e-f174-4fd8-bc49-de22198ce1b9","year":2024},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.913442Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:77852b8dc8129d27b7d062abff620f8ce06cce48cf33996ad98d301608b15566","observation_id":"3f48aeb2-86b6-4003-b1d8-4fa0305691b8","resolution":{"observed_at":"2026-08-16T04:16:37.208027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:37.163511Z","title":"A unified approach to interpreting model predictions,","venue":null,"work_id":"28832ed7-d6f2-4409-94b5-06f335e5ba28","year":2017},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.919777Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:0ca8831fd0cc926b5810028b0808e2665f83513330997ce08ce88b416ed99740","observation_id":"a5223835-43ad-4230-950f-04c862e8ecc6","resolution":{"observed_at":"2026-08-16T04:16:37.170377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.01612","last_updated":"2022-12-12T09:26:32Z","snapshot_observed_at":"2026-08-16T16:56:02.447984Z","submitted_at":"2022-06-01T11:35:37Z","title":"OmniXAI: A Library for Explainable AI","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.01612","snapshot_observed_at":"2026-08-16T04:16:35.927416Z","title":"Omnixai: A library for explainable ai,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.927416Z"},"links":{"cited_paper":"/paper/2206.01612","citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:f791db33d6d7ea84c63b12ae3ef9a87940212a5aa3c1996f2c397b8ea02bf73f","observation_id":"fc3e7b1d-80b6-426c-8c39-16cc941ad133","resolution":{"observed_at":"2026-08-16T04:16:35.927416Z","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":"2026-08-16T04:16:37.140871Z","title":"Interpretdl: explaining deep models in paddlepaddle,","venue":null,"work_id":"28ddcf86-6366-4f69-952b-37478794c800","year":2022},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.933235Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:18a2dc1af2fc89c2fd006743691f0d0039247fd17a520e2bc920b32beca04d5d","observation_id":"b408befb-afda-42d8-9e8d-8613b58ba3c5","resolution":{"observed_at":"2026-08-16T04:16:37.147776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6034","last_updated":"2014-04-19T11:54:52Z","snapshot_observed_at":"2026-08-17T14:45:30.096775Z","submitted_at":"2013-12-20T16:45:54Z","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6034","snapshot_observed_at":"2026-08-16T04:16:35.939510Z","title":"Deep inside convolutional networks: Visualising image classification models and saliency maps,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.939510Z"},"links":{"cited_paper":"/paper/1312.6034","citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:8dd9bc6d10db7c148adc6e010545c282cb6e1be1dd87210967e5842eb8ec36ba","observation_id":"abcaf9fb-b468-4630-803f-9032aeec6cba","resolution":{"observed_at":"2026-08-16T04:16:35.939510Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.03825","last_updated":"2017-06-12T19:53:30Z","snapshot_observed_at":"2026-08-14T20:54:30.978618Z","submitted_at":"2017-06-12T19:53:30Z","title":"SmoothGrad: removing noise by adding noise","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.03825","snapshot_observed_at":"2026-08-16T04:16:35.945685Z","title":"Smoothgrad: removing noise by adding noise,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.945685Z"},"links":{"cited_paper":"/paper/1706.03825","citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:0d09bcd19190a6164d190ac23893a6e24f15729c6cae78e5858d05efbe0ad7cb","observation_id":"aa3249b9-82fd-4f09-8cf5-7be713bd78b7","resolution":{"observed_at":"2026-08-16T04:16:35.945685Z","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":"2026-08-16T04:16:37.113629Z","title":"Layer-wise relevance propagation for neural networks with local renor- malization layers,","venue":null,"work_id":"922d1754-6d97-4579-8fab-ce4dfec594a2","year":2016},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.954606Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:2a9726074cfd25c8e6790c9ed90bf9d016e010f5b63103c0cbd66e3317cda310","observation_id":"f31a4e47-50e1-4409-8a73-d0ef9ffecf0f","resolution":{"observed_at":"2026-08-16T04:16:37.121349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:37.089520Z","title":"Learning important features through propagating activation differences,","venue":null,"work_id":"037b6f3e-081e-449f-a459-ce724c02a561","year":2017},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.960999Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:7e5031cb67b3bd106f4a5d3a922eaf5ca1a63a6322d70c4110365b21a6c2287f","observation_id":"06210e8f-eb18-4fde-8817-d2964b698447","resolution":{"observed_at":"2026-08-16T04:16:37.097641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:16:35.967688Z","title":"A unified approach to interpreting model predictions,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.967688Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:877afe9e6e5c33f831ded840018449447e8c9717f3fbed91f92568d746f09123","observation_id":"d59eff8b-ea9b-4f45-904d-0a3334df70fe","resolution":{"observed_at":"2026-08-16T04:16:35.967688Z","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":"2026-08-16T04:16:37.037544Z","title":"” why should i trust you?","venue":null,"work_id":"cd34b8b6-ca3b-48c5-be0e-b64761d6f224","year":2016},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.973868Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:8824b3fbca3396c1a70e7b07809e721ec1f77b7c81a422c7cb4a59dcbf8ccbf3","observation_id":"17686713-1302-4733-9b60-2f1a468968a4","resolution":{"observed_at":"2026-08-16T04:16:37.049941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:16:35.979945Z","title":"Captum: A unified and generic model inter- pretability library for pytorch,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.979945Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:5ed5a62340a4527a8f17afd0c5251e96d5e9f27cb58614528ae31b4068a1e12b","observation_id":"1c336c06-f42b-4bc5-8ae2-4339eb51a206","resolution":{"observed_at":"2026-08-16T04:16:35.979945Z","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":"2026-08-16T04:16:36.992640Z","title":"dattri: A library for efficient data attribution,","venue":null,"work_id":"f10dd313-82ac-4418-93ee-b48b91006476","year":2024},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.985774Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:b7afea4553586cbea1186ea8ae529d47579a8aaf2ea5711629a1a7ae655f9ebd","observation_id":"bfdcda57-ee4e-412c-b35b-6c13e3e81a3e","resolution":{"observed_at":"2026-08-16T04:16:36.998666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.09223","last_updated":"2019-09-19T20:22:32Z","snapshot_observed_at":"2026-08-17T05:13:56.376271Z","submitted_at":"2019-09-19T20:22:32Z","title":"InterpretML: A Unified Framework for Machine Learning Interpretability","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.09223","snapshot_observed_at":"2026-08-16T04:16:35.994736Z","title":"Interpretml: A uni- fied framework for machine learning interpretability,","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:35.994736Z"},"links":{"cited_paper":"/paper/1909.09223","citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:2714e52664dad85057bf824f03db5f5b72bba225a6fbe840cb9a78da75914564","observation_id":"e14df881-9a58-4967-aefa-99a96e871fad","resolution":{"observed_at":"2026-08-16T04:16:35.994736Z","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":"2026-08-16T04:16:36.966831Z","title":"Interpretdl: Explaining deep models in paddlepaddle,","venue":null,"work_id":"8971fe6c-114d-46ae-a74b-54e09d1dd937","year":2022},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.002171Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:d8465cd9bf51cbb016598444f3f328a2d7267f8bcc61ef514d304e39f47a1634","observation_id":"0631a8a9-5a6f-453b-ac55-bc651e3e1306","resolution":{"observed_at":"2026-08-16T04:16:36.975768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:36.938450Z","title":"Omnixai: A library for explainable ai,","venue":null,"work_id":"347ebd00-c7b8-47ac-9e0f-1af800e17282","year":2022},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.009050Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:b9d3edddf3fb348913a3ee125a653f56ba0a7e4edcbc28c0951bac3e0bb18e30","observation_id":"923003a9-1ebe-4990-8373-729575398438","resolution":{"observed_at":"2026-08-16T04:16:36.947489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:16:36.016621Z","title":"Improving performance of deep learning models with axiomatic attribution priors and expected gradients,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.016621Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:1f1b126abee69eeb77c3dcb62d6759efc826363bd001954c3a8308525cd52fb4","observation_id":"047b0145-8fe3-4a15-b96b-258e5215f7bf","resolution":{"observed_at":"2026-08-16T04:16:36.016621Z","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":"2026-08-16T04:16:36.876397Z","title":"Fast axiomatic attribution for neural networks,","venue":null,"work_id":"8a98006d-61c0-4286-be10-4633d153e21b","year":2021},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.023365Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:454dc124d8373477db0a3e7f79e78c9b885414e85cc7c8368a2a71b65c4f15fb","observation_id":"93f682ee-3c16-46b8-b849-1ef833dc2edd","resolution":{"observed_at":"2026-08-16T04:16:36.885924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:36.849027Z","title":"Guided integrated gradients: An adaptive path method for removing noise,","venue":null,"work_id":"35aac843-f346-49fb-a287-ba1a682fec46","year":2021},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.029650Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:d67d2be23b2c287e414194c6209a1ba4e16189c826310881ea581485b9226118","observation_id":"2d9cdf21-c65f-49f6-9086-a9c9c3302df4","resolution":{"observed_at":"2026-08-16T04:16:36.858002Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:36.820190Z","title":"Adversarial examples in the physical world,","venue":null,"work_id":"7fda5c9f-d0a4-42e1-9c56-a547fd131892","year":2018},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.036617Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:8b1e1fc42f7f572a0efc0a06c49f56afaa2d7dc05dd4b7e1eb15d0c6fd60ed77","observation_id":"726333a4-85c5-4eac-8e72-fc131f46779d","resolution":{"observed_at":"2026-08-16T04:16:36.827252Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:36.794739Z","title":"Impossibility theo- rems for feature attribution,","venue":null,"work_id":"7cc36a08-149e-4596-962a-47d8aea2eadd","year":2024},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.044634Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:07e04c563496e4edf14b458828e3af04bb6769f68aede0905b75148d410b1347","observation_id":"008e3f68-636a-45e5-b784-3749d3d4bb4d","resolution":{"observed_at":"2026-08-16T04:16:36.801543Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:36.773231Z","title":"Rise: Randomized input sampling for explanation of black-box models,","venue":null,"work_id":"9179cf7d-9b42-4a95-91fb-dfc45a6fe878","year":2018},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.050975Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:1075e0d2977af614a68623e6ed230f1cb7e7be61a97e03a83e2e7d46dab0b6cb","observation_id":"f7998bb6-11c7-40ea-96e3-6c48d27f8c2d","resolution":{"observed_at":"2026-08-16T04:16:36.780403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:36.747537Z","title":"Enhancing model interpretability with local attribution over global exploration,","venue":null,"work_id":"917cf697-f294-4aa3-96ba-9487cf39106b","year":2024},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.058713Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:e92804737e0bd34ab24b9edd8774fb0318f5ba13969ca4c98dc17a57e0a74f39","observation_id":"b6d4782b-0179-4395-be7c-182209115fa1","resolution":{"observed_at":"2026-08-16T04:16:36.754478Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:36.715826Z","title":"Iterative search attribution for deep neural networks,","venue":null,"work_id":"b0120e04-c7c9-4221-ae4c-8d97e54b4aad","year":null},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.067520Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:8aef9678bea3e6c7ba9b8f40bd66a84b883ae393a7e0a925afc76f4c1bfdd67a","observation_id":"dd4d70a2-411a-47ca-ac3f-4e4c08434fb5","resolution":{"observed_at":"2026-08-16T04:16:36.722884Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:36.696425Z","title":"Generic attention-model explain- ability for interpreting bi-modal and encoder-decoder transformers,","venue":null,"work_id":"7b9e176a-8b08-49d5-9876-51e0a150cbc2","year":2021},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.075602Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:a6818e916962608c89c21fef60866c041c202221de7fa1fd73a711c08341e87d","observation_id":"f0e35bb6-e295-429c-bf8e-6d47147e2b84","resolution":{"observed_at":"2026-08-16T04:16:36.703339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:36.669841Z","title":"Visual explanations of image-text representations via multi-modal information bottleneck attri- bution,","venue":null,"work_id":"e69dcc36-d911-43ec-b716-95dca0d9f7d7","year":2023},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.081188Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:09c9ad9e1c713499bcd60b14c7d1d85e8b068484a4090b6ac4ec685e32739d33","observation_id":"c74991c3-3eaf-4448-b01d-78270ed0075f","resolution":{"observed_at":"2026-08-16T04:16:36.676794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:36.638326Z","title":"Iterative search attribution for deep neural networks,","venue":null,"work_id":"0fc60857-4d40-46f0-b72b-ea80c94caf5c","year":2024},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.086689Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:5d7db100b636561e10946f76a1fd5bd4d0f5a84bc197ed9fb04213bf20d1d8fb","observation_id":"1319b515-6919-478d-860f-f32812bbc534","resolution":{"observed_at":"2026-08-16T04:16:36.644223Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-16T04:16:36.612934Z","title":"Rethinking the inception architecture for computer vision,","venue":null,"work_id":"71189d57-0664-424d-88ee-07f175046f1f","year":2016},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.091929Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:7e77125413d82b985d3980762241bf78ae0fe48f21cfb66299de8de46d01246f","observation_id":"68725189-a5db-4eaa-84c7-9081d9505b66","resolution":{"observed_at":"2026-08-16T04:16:36.620006Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:16:36.097729Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.097729Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:68c69a4c589531e5f3f3f5d133a5211020073c674925f665687de594203d10d0","observation_id":"34bf87c3-9772-410a-9674-66ed25fdb8fe","resolution":{"observed_at":"2026-08-16T04:16:36.097729Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-17T19:17:06.411141Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-16T04:16:36.104075Z","title":"Very deep convolutional networks for large-scale image recognition,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.104075Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:daae0691c413ea5f6d1a7f1bbda2d9ef5f0b60760e781f48e16db1d18ee73062","observation_id":"f408329e-9d5d-43a5-b754-14ab9010eed8","resolution":{"observed_at":"2026-08-16T04:16:36.104075Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-16T04:16:36.110106Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.110106Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:c0ea4f33f98a4edf287121a8ab056e4b2e7f66533db9954f9ad97d83363acb27","observation_id":"d96fe449-8d3c-4064-8b57-fb84cb6f19b6","resolution":{"observed_at":"2026-08-16T04:16:36.110106Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:16:36.115394Z","title":"ImageNet Large Scale Visual Recognition Challenge,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.115394Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:a54615cc4ec0f21896ff9c4e03473a5867b247a14712f8633d869bfa31366c9b","observation_id":"0bac1932-c36b-4268-9d2f-5584e635281b","resolution":{"observed_at":"2026-08-16T04:16:36.115394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1510.03820","last_updated":"2016-04-06T23:20:27Z","snapshot_observed_at":"2026-08-19T21:01:29.340842Z","submitted_at":"2015-10-13T19:00:57Z","title":"A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1510.03820","snapshot_observed_at":"2026-08-16T04:16:36.121836Z","title":"A sensitivity analysis of (and practitioners’ guide to) convolutional neural networks for sentence classification,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.121836Z"},"links":{"cited_paper":"/paper/1510.03820","citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:860dc1e74e1948ceb1c2d1b3c3b1aa6a0fe0f0e7f4ef5115d9e0d349644684a7","observation_id":"52c3a133-c5fc-43c1-bd95-1bacc8c53108","resolution":{"observed_at":"2026-08-16T04:16:36.121836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.3555","last_updated":"2014-12-11T06:46:53Z","snapshot_observed_at":"2026-08-20T00:41:09.240026Z","submitted_at":"2014-12-11T06:46:53Z","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.3555","snapshot_observed_at":"2026-08-16T04:16:36.129414Z","title":"Empirical evaluation of gated recurrent neural networks on sequence modeling,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.129414Z"},"links":{"cited_paper":"/paper/1412.3555","citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:a3ca5798ad4c23fcf906862264fcaaf1b1943983218de974abe8a16ecde03d96","observation_id":"07cb390e-1d34-4326-a0db-78195fbfe899","resolution":{"observed_at":"2026-08-16T04:16:36.129414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:16:36.136696Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.136696Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:0a49d3587738ebe8920661139e806afbc96c173072fc52cacbd65baf4bfd14ad","observation_id":"2863703e-65c4-47a6-b987-632b22bd2bdc","resolution":{"observed_at":"2026-08-16T04:16:36.136696Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:16:36.147620Z","title":"Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.147620Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:69936f9a230d9067e059916996b3269bd2932f7b4d39771c97502ffd44d40fb4","observation_id":"064da8a9-65f2-4fd4-8aa1-ab8dd941a149","resolution":{"observed_at":"2026-08-16T04:16:36.147620Z","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":"2026-08-16T04:16:36.499637Z","title":"Framing image description as a ranking task: Data, models and evaluation metrics,","venue":null,"work_id":"a50c4fe1-ed15-4719-b06a-901d1dfb5425","year":2013},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.155808Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:6b555f2b4251699de0e58821dc79583407522ada5e10a2233ee7b588d9982800","observation_id":"8778a2dd-5798-4ba9-b0b0-b74920f4f1fc","resolution":{"observed_at":"2026-08-16T04:16:36.505325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.02002","last_updated":"2018-02-07T18:44:44Z","snapshot_observed_at":"2026-08-17T00:09:26.216715Z","submitted_at":"2017-08-07T06:32:42Z","title":"Focal Loss for Dense Object Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.02002","snapshot_observed_at":"2026-08-16T04:16:36.163562Z","title":"Focal loss for dense object detection,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.163562Z"},"links":{"cited_paper":"/paper/1708.02002","citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:a3040ad387c539025b8b0c698ab89ae6fb05e6d13626e72c02bb6231a62b6710","observation_id":"c73c7a4a-13f7-434c-93c6-690aacebafc5","resolution":{"observed_at":"2026-08-16T04:16:36.163562Z","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":"2026-08-16T04:16:36.477570Z","title":"Microsoft coco: Common objects in context,","venue":null,"work_id":"ef87db88-158b-4fd2-a4c1-2be4866225ba","year":2014},"citing_paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-16T04:16:36.170249Z"},"links":{"citing_paper":"/paper/2505.06258"},"observation_digest":"sha256:e5c05fb8b9e4836f89d5299ee0bfb141c18671371c57b435f8b56fb8dc21c80b","observation_id":"8a0079ea-329b-43fd-ad10-7ec8e974cd1b","resolution":{"observed_at":"2026-08-16T04:16:36.485758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.06258","last_updated":"2025-05-03T12:00:59Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T09:34:08.960471Z","submitted_at":"2025-05-03T12:00:59Z","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":0,"verified_fuzzy":26},"total_outbound_references":44},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2505.06258."}