{"as_of":"2026-08-19T04:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:41cdca6900572b6875be350c045f51c0ac7121c4676b4a90c45ed42e6c057583","coverage":[{"denominator":90,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":90,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T21:43:06.899716Z","state":"measured"},{"denominator":90,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":90,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2505.09660/citation-record","integrity":"/paper/2505.09660/integrity","json":"/paper/2505.09660/citation-record.json","paper":"/paper/2505.09660"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:06.477113Z","title":"Open XAI : Towards a transparent evaluation of model explanations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.477113Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:127a63387da4412fed2bc16d50a5b79946ec77feeb14e94f0606b97ab4c082bf","observation_id":"6f501b2f-3dda-4a46-b3e0-ce3929e28d46","resolution":{"observed_at":"2026-08-15T21:43:06.477113Z","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":"2026-08-15T21:43:06.482424Z","title":"A causal framework for explaining the predictions of black-box sequence-to-sequence models","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.482424Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:5e93d425375f1806d763bc069fbc55eefe1c53348f6f0334f60d2007cc4a40d5","observation_id":"d7a04e56-7738-4c35-a8e9-643223a0b1ed","resolution":{"observed_at":"2026-08-15T21:43:06.482424Z","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":"2026-08-15T21:43:06.487726Z","title":"Athreya and Soumen N","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.487726Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:a76d3590319b53140429390a35b7363c758cda725b2d5436c79bf85158023e21","observation_id":"f6d27446-2a46-40ad-81b8-7bb52df927ce","resolution":{"observed_at":"2026-08-15T21:43:06.487726Z","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":"2026-08-15T21:43:06.492252Z","title":"Fairness seen as global sensitivity analysis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.492252Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:241272c08f8d0c81148c853d5aea70e2dc2ea20771c0709240028cada5092d24","observation_id":"a8f2a026-5e60-4a2c-9299-a23ec4ce0b5e","resolution":{"observed_at":"2026-08-15T21:43:06.492252Z","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":"2026-08-15T21:43:06.496685Z","title":"o baum, Peter G \\","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.496685Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:b92de3c3a34cb405bdc8eb82513dba649c5293bb8fa244b43ed3ff16bcd2b410","observation_id":"3403dce4-3e19-4ad3-86d1-4ef4e7188156","resolution":{"observed_at":"2026-08-15T21:43:06.496685Z","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":"2026-08-15T21:43:06.501086Z","title":"Random forests","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.501086Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:f9dbf5b225fc84c0b3b4a5952149de06d48969aa6e3c2d42800ac8845b3981c2","observation_id":"cc34c40c-1080-4db4-b5f5-a96b7a78d070","resolution":{"observed_at":"2026-08-15T21:43:06.501086Z","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":"2026-08-15T21:43:06.505590Z","title":"Cage: Causality-aware shapley value for global explanations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.505590Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:37df9e93fa0affb46518eb11cc001589a8846aecf04402fff23b15f041b7f940","observation_id":"ae3cc739-b7ba-480c-9d60-34f47e6db898","resolution":{"observed_at":"2026-08-15T21:43:06.505590Z","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":"2026-08-15T21:43:06.510133Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.510133Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:26143e0e3bbffbc3a4a3854129c5f79ec194410d6eecad5f794ec9316fabd9aa","observation_id":"52cdeda4-c00d-4f2d-b1a0-f6f9b3bedd6e","resolution":{"observed_at":"2026-08-15T21:43:06.510133Z","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":"2026-08-15T21:43:06.514944Z","title":"Neural network attributions: A causal perspective","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.514944Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:43d7e56b473ff3f2c54278bce5b5c84cf1d375ca7646c87e877fefe8c6d7f137","observation_id":"afaeabb8-8571-48a8-b1ac-f21a84288c9c","resolution":{"observed_at":"2026-08-15T21:43:06.514944Z","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":"2026-08-15T21:43:06.519862Z","title":"Beyond First-Order Uncertainty Estimation with Evidential Models for Open-World Recognition","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.519862Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:6845fdc278d759d83d825fef45b096dbd9e156adf6ce2d102c5ae33eaddb5c23","observation_id":"8e1ee037-4062-4b17-ba51-adfc06e92cf9","resolution":{"observed_at":"2026-08-15T21:43:06.519862Z","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":"2026-08-15T21:43:06.525297Z","title":"Bach, and Himabindu Lakkaraju","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.525297Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:e26e5ba15335496c98630722a04b7487fe148eb76a1bd7ecfbe7c0ccb5e10a73","observation_id":"f6e00530-b6d0-41f1-8227-df12bf20a574","resolution":{"observed_at":"2026-08-15T21:43:06.525297Z","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":"2026-08-15T21:43:06.530468Z","title":"Multi-objective counterfactual explanations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.530468Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:37893f071a09b0b5b1eaba9de7db3e3f160e75e4104a4aa7e34216b54ba59e66","observation_id":"a23ad300-920e-40a1-aba1-cea4bbd87076","resolution":{"observed_at":"2026-08-15T21:43:06.530468Z","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":"2026-08-15T21:43:09.422287Z","title":"Evaluating and mitigating bias in image classifiers: A causal perspective using counterfactuals","venue":null,"work_id":"eeb493be-14c8-400a-9104-12aee7780dd0","year":2022},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.535760Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:be7b70bb7a6866196df9f66585cbe53dd6022c0ecec57df2d022f894e496d893","observation_id":"df072806-38b5-4d94-bdfe-961d89381192","resolution":{"observed_at":"2026-08-15T21:43:09.427737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.402753Z","title":"Look at the variance! efficient black-box explanations with sobol-based sensitivity analysis","venue":null,"work_id":"b10e66ab-077f-4223-a82f-999535c06f28","year":2021},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.540922Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:01cf909e1a853b0589521830e5a2fa11d268e6441d4e03e3ee07738ec2f89698","observation_id":"49502236-1668-4ea8-8e62-2c7c03cc36c7","resolution":{"observed_at":"2026-08-15T21:43:09.408383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.09784","last_updated":"2017-11-27T15:50:50Z","snapshot_observed_at":"2026-08-15T17:22:57.726836Z","submitted_at":"2017-11-27T15:50:50Z","title":"Distilling a Neural Network Into a Soft Decision Tree","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.09784","snapshot_observed_at":"2026-08-15T21:43:06.545565Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.545565Z"},"links":{"cited_paper":"/paper/1711.09784","citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:da7d96191f36c5c11d4d44817ae31a8d0afeb59726ceec4a713eaa7e6c8eb421","observation_id":"c54823c2-7bc1-48d1-9fc6-fd284b1b2d32","resolution":{"observed_at":"2026-08-15T21:43:06.545565Z","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":"2026-08-15T21:43:06.550581Z","title":"Shapley explainability on the data manifold","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.550581Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:873a8ee3fa169857b00f01836557bcd57d171d46f332a43cf3aa995964f5126d","observation_id":"92e8400e-7150-4600-9999-627fa92aaf89","resolution":{"observed_at":"2026-08-15T21:43:06.550581Z","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":"10.1016/s0004-3702(97)00047-7","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:07.106453Z","title":"Axioms of causal relevance","venue":null,"work_id":"d78f3d41-dde6-4d78-b04c-6d4e2cf0dc2b","year":1997},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.554865Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:0491726b8f44c399c10232ff3b36a22a3097f9b662bcc833ddcf83725ab7ec52","observation_id":"2430b5bf-785d-4c3a-98fb-88daffbe9a74","resolution":{"observed_at":"2026-08-15T21:43:07.111645Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/j.jco.2015.06.001","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:07.090379Z","title":"On integration methods based on scrambled nets of arbitrary size","venue":null,"work_id":"86f049dd-a664-49f9-bd16-6ec6a260d1a0","year":2015},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.559285Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:95d9be88cbf744e9d39017212811dc3de9c037cb08811fbd148fa84f084bdf63","observation_id":"80db8582-711a-4ccb-bf15-a259ffc7e9f6","resolution":{"observed_at":"2026-08-15T21:43:07.095472Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.07165","last_updated":"2020-02-28T18:56:14Z","snapshot_observed_at":"2026-08-16T04:32:45.166869Z","submitted_at":"2019-07-16T17:47:43Z","title":"Explaining Classifiers with Causal Concept Effect (CaCE)","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.07165","snapshot_observed_at":"2026-08-15T21:43:06.564104Z","title":"Explaining classifiers with causal concept effect (cace)","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.564104Z"},"links":{"cited_paper":"/paper/1907.07165","citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:377b2d21185e9954c9f6de936bf10a9249ab57d7ca32267f584250a2e79435b5","observation_id":"21aeb28f-cd0a-4dd1-b076-2ff004433542","resolution":{"observed_at":"2026-08-15T21:43:06.564104Z","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":"2026-08-15T21:43:09.373938Z","title":"Counterfactual visual explanations","venue":null,"work_id":"0838aced-69e1-4fd6-bd10-8175865ba7be","year":2019},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.568677Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:b4251bd259a75f31d7590f3e10bff3e45374c7854b37adfde7e12a83c6078d60","observation_id":"c66bba74-c0f2-41ab-9ab5-a8b24a726caf","resolution":{"observed_at":"2026-08-15T21:43:09.379449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.355754Z","title":"Causal shapley values: Exploiting causal knowledge to explain individual predictions of complex models","venue":null,"work_id":"164c96b7-278e-4e78-b1d6-70e60cd8fa45","year":2020},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.573008Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:eb474ccea7eb8ba7328ee8eb4e5be9851dd1cf381e80afbf12a40fc5e917b284","observation_id":"acc11976-3553-46b8-a7b8-767629bd9a04","resolution":{"observed_at":"2026-08-15T21:43:09.362009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:06.577885Z","title":"Generalized functional anova diagnostics for high-dimensional functions of dependent variables","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.577885Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:4e0001893cc72413df5c2e44778e4a26e29db9e0a3d72d8532534171f2e998c2","observation_id":"7c6c3d29-1861-4e78-a9bb-398c251708f1","resolution":{"observed_at":"2026-08-15T21:43:06.577885Z","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":"2026-08-15T21:43:06.583093Z","title":"Global explanations of neural networks: Mapping the landscape of predictions","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.583093Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:52340dcb419b50a760fa1d64bc0428e8a81fa90a410866b0ec5a11fac73af683","observation_id":"57b24921-8a9b-4544-9099-ae9fad79f88f","resolution":{"observed_at":"2026-08-15T21:43:06.583093Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.15595","last_updated":"2021-12-31T18:57:37Z","snapshot_observed_at":"2026-08-18T15:49:31.339142Z","submitted_at":"2021-12-31T18:57:37Z","title":"Triangular Flows for Generative Modeling: Statistical Consistency, Smoothness Classes, and Fast Rates","version":1},"cited_work":{"arxiv_id":"2112.15595","doi":null,"metadata_source":"pith","pith_arxiv_id":"2112.15595","snapshot_observed_at":"2026-08-15T21:43:08.389532Z","title":"Triangular Flows for Generative Modeling: Statistical Consistency, Smoothness Classes, and Fast Rates","venue":"stat.ML","work_id":"a34e3bec-dd7d-441e-9387-8020dcdc12f6","year":2021},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.587769Z"},"links":{"cited_paper":"/paper/2112.15595","citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:4d3df9d0d1b743562224350e80d59adde692775ddf6911a4c6c4033e43da49e4","observation_id":"b47a728a-bc72-46c0-8608-f40fcfd807c2","resolution":{"observed_at":"2026-08-15T21:43:08.395996Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/s0010-4655(98)00154-4","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:07.074577Z","title":null,"venue":null,"work_id":"3a52438f-e321-4231-bbbd-62b3641d69f0","year":1999},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.592646Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:88c3b15b76180165bb0a6a65e02de93f3ed37180b27ac527d0cd6e764d693899","observation_id":"9f4cbc0c-4bea-4a0d-b71b-139f1af0b7f5","resolution":{"observed_at":"2026-08-15T21:43:07.079246Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.337775Z","title":"Feature relevance quantification in explainable ai: A causal problem","venue":null,"work_id":"0dbd913f-322e-45fe-b80d-c54db98703fc","year":2020},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.597213Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:5a977500450e31132c25073745b515e9fe72fb3f9f8bf0aa317db9c71aef7b93","observation_id":"47e68de7-3cda-4a5d-8af8-9b896d816c68","resolution":{"observed_at":"2026-08-15T21:43:09.343784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.00714","last_updated":"2024-03-08T13:33:03Z","snapshot_observed_at":"2026-07-06T09:34:36.626306Z","submitted_at":"2020-07-01T19:34:08Z","title":"Quantifying intrinsic causal contributions via structure preserving interventions","version":4},"cited_work":{"arxiv_id":"2007.00714","doi":null,"metadata_source":"pith","pith_arxiv_id":"2007.00714","snapshot_observed_at":"2026-08-15T21:43:08.362690Z","title":"Quantifying intrinsic causal contributions via structure preserving interventions","venue":"cs.AI","work_id":"414b4197-889c-4a6d-8f04-0f07b87a6631","year":2020},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.602101Z"},"links":{"cited_paper":"/paper/2007.00714","citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:04b21360e7d1ae300d1c17c57a4e1ace172f01b556803383052c98d40e8b5068","observation_id":"01f64e49-18f3-49a4-ab5a-da4c00fd72ff","resolution":{"observed_at":"2026-08-15T21:43:08.369891Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.316213Z","title":"Causal normalizing flows: from theory to practice","venue":null,"work_id":"64e7093a-6385-4ec5-a5a8-1559027b334f","year":2023},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.606849Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:bc631f7d407d9718cfb777cc96c8925bd13a1f84e00c115b538d06eb6f8d1752","observation_id":"504c778e-ef7e-4ff5-bac0-ab2de4cac1ef","resolution":{"observed_at":"2026-08-15T21:43:09.322540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.298409Z","title":"On measuring causal contributions via do-interventions","venue":null,"work_id":"76c45af5-8790-46fc-8ee7-0902541e7a5d","year":2022},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.611277Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:c720a88218b9786af4ad82cfab6bf71652ec4c65707fec6bd45d2c4d4f4162c0","observation_id":"c5086a2c-7788-42dc-b9eb-8d3626e2dd84","resolution":{"observed_at":"2026-08-15T21:43:09.303504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.281361Z","title":"Balasubramanian, and Amit Sharma","venue":null,"work_id":"a2805f97-c936-4e77-b9cd-659152ba5461","year":2021},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.615817Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:c5e2fa2942fc88465db7af82b5b9325e7c32db4f45b411b04d8d4319f7e2f732","observation_id":"c4d9d664-c6d3-4c13-b925-7e090b874a97","resolution":{"observed_at":"2026-08-15T21:43:09.286607Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.255693Z","title":"Kingma, and Aapo Hyv \\\"a rinen","venue":null,"work_id":"eb69eb56-838d-49e6-b1ad-3247f3d69f98","year":2019},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.620460Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:7a8c8850398dc8dc60efbada0fc1aff32fd2483005cd06546efe61f3d5a6cb1b","observation_id":"6e40a73b-348f-4d73-9c62-82c178bc9df6","resolution":{"observed_at":"2026-08-15T21:43:09.261696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:06.624820Z","title":"Knuth and Jayme L","venue":null,"work_id":null,"year":1974},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.624820Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:6e326c628d2ad77b33e10e85ae590201941f76c730524fc07fe301ef87bc932e","observation_id":"903fc903-ff93-4b50-9ca1-8e948e849097","resolution":{"observed_at":"2026-08-15T21:43:06.624820Z","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":"2026-08-15T21:43:06.629267Z","title":"Towards unifying feature attribution and counterfactual explanations: Different means to the same end","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.629267Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:82e9383edb1036167a1547f45e171bb9355403a34434c557cc58467d73c3d4cf","observation_id":"1f3b09cb-a55c-4bf2-a250-8af2d025d690","resolution":{"observed_at":"2026-08-15T21:43:06.629267Z","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":"2026-08-15T21:43:06.633747Z","title":"Kucherenko, S","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.633747Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:99a6764e952fc08028f4f696a90beeaf4caeee07b7f0872ab6f0032a00fb6d09","observation_id":"7ac3a967-6255-46e5-9c28-5ee9b1accac1","resolution":{"observed_at":"2026-08-15T21:43:06.633747Z","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":"2026-08-15T21:43:09.238178Z","title":"Backtracking counterfactuals","venue":null,"work_id":"6da844a8-3fb1-4c39-a083-0c05418cfeb2","year":2023},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.639044Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:d30fb16809f4252a6a1bcadad26b1194c8f5057e0dd21093ff721a28ee9ab614","observation_id":"395b543b-a0a9-4267-b39c-81316bdd844e","resolution":{"observed_at":"2026-08-15T21:43:09.243471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/978-3-031-07155-3_6","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-17T11:03:46.409680Z","title":"Global Sensitivity Analysis for the Interpretation of Machine Learning Algorithms, pages 155--169","venue":null,"work_id":"cea2a722-fb7e-4203-8189-cb9123398a3a","year":2022},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.644969Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:e90307e495c2111c3cdf4c04ed6c64f6c7babfee330590146d07a295d650afc0","observation_id":"aee42267-c4fd-4808-bf44-51a689d76d2f","resolution":{"observed_at":"2026-08-15T21:43:07.052567Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.221736Z","title":"Bach, and Jure Leskovec","venue":null,"work_id":"616ea7d4-cb9d-421e-a093-4afe2442f3a1","year":2016},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.649733Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:faa01f66ec3e848bf34c0a307e18bc6569293e98d53448cf29679aa868db1a14","observation_id":"8590d356-62f4-4199-836a-73fc34378d4a","resolution":{"observed_at":"2026-08-15T21:43:09.226752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.197785Z","title":"How we analyzed the compas recidivism algorithm, 2016","venue":null,"work_id":"24ef89ef-4439-4e41-a0b8-3ec045413fe1","year":2016},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.654046Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:e829b4cb158ddc101fb267b25c2a4239e68ddf93da2c5b39d2717bf662900d98","observation_id":"2241337c-8449-4304-9503-ad3eeb20cca0","resolution":{"observed_at":"2026-08-15T21:43:09.203371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.177177Z","title":"Randomized quasi-monte carlo: An introduction for practitioners","venue":null,"work_id":"08623f15-6e3d-4524-8e5e-0ddcdf8b5785","year":2018},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.658161Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:59d23e5a8fd7c8bc069d2af845a397443404407be0cbafd02a837a4b7a0aeece","observation_id":"d38b6697-7b0d-4cb1-9444-3d806cf496e1","resolution":{"observed_at":"2026-08-15T21:43:09.184610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/0-306-48102-2_20","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-17T11:03:46.409680Z","title":"Recent Advances in Randomized Quasi-Monte Carlo Methods, pages 419--474","venue":"International series in management science/operations research/International series in operations research & management science","work_id":"13a5c494-980a-4c4e-aeab-cf3c15d2086b","year":2002},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.662527Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:fe3623662ae864d3a89a6a62a3aa099730808f82a46c0c8f022c3bf8e447af49","observation_id":"461eae08-e45a-4558-afa3-031b93030713","resolution":{"observed_at":"2026-08-15T21:43:07.036524Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.158064Z","title":"Yelvington, Oluwayemisi O","venue":null,"work_id":"5d07e823-5b46-4d36-b618-d6977203661d","year":2010},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.666829Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:dbfb7faa1cfc9696ee008c167baa86af713fe7b4cc240e112dd238434ef92a51","observation_id":"4aa0b5ee-67a3-475c-a573-7c116166c1fb","resolution":{"observed_at":"2026-08-15T21:43:09.162315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.142456Z","title":"Lundberg and Su-In Lee","venue":null,"work_id":"ca4cceb7-5925-4603-99c6-62b0fa1d0c64","year":2017},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.671105Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:f0904903b54e8df78070fbda6d7da635edd83d92bed80f405b4cc9c085587e89","observation_id":"a870a180-ec6c-4efb-9510-3aed75bca0d5","resolution":{"observed_at":"2026-08-15T21:43:09.147515Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.03277","last_updated":"2020-06-12T23:46:46Z","snapshot_observed_at":"2026-08-17T21:47:44.641296Z","submitted_at":"2019-12-06T18:16:29Z","title":"Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.03277","snapshot_observed_at":"2026-08-15T21:43:06.675767Z","title":"Preserving causal constraints in counterfactual explanations for machine learning classifiers","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.675767Z"},"links":{"cited_paper":"/paper/1912.03277","citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:59414dff48088642bbc505435e678c36ae812bcea914519b1baddb24cdcc5c66","observation_id":"94294f8d-e34d-4879-80f0-a9fb3f24067f","resolution":{"observed_at":"2026-08-15T21:43:06.675767Z","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":"2026-08-15T21:43:09.126892Z","title":"Sampling permutations for shapley value estimation","venue":null,"work_id":"81d6bf4d-8035-4e38-a14a-4cefb8d2db88","year":2022},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.680484Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:4d50219a6e829bb658cc9089feb86990022692a8c3b5b544b72efa8feba789ee","observation_id":"f90c674d-0a1b-48e8-83d5-71c058875212","resolution":{"observed_at":"2026-08-15T21:43:09.132078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:06.684840Z","title":null,"venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.684840Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:f93290821a9be707d8bfbf347056e138b89ed1f5eaf8bf4a877d2f4454e5b091","observation_id":"13583ba9-499c-43d4-9932-0256b349c431","resolution":{"observed_at":"2026-08-15T21:43:06.684840Z","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":"2026-08-15T21:43:06.689254Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.689254Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:539a423604706ceb5b448967ea390ecafea973557e31717ce90c343be655655d","observation_id":"cc837ccd-b39d-4d76-9032-485d4abf4147","resolution":{"observed_at":"2026-08-15T21:43:06.689254Z","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":"10.1137/20m1320535","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:07.004154Z","title":"Owen and Daniel Rudolf","venue":null,"work_id":"5211c606-de90-4de8-88f1-85112cbc131a","year":2021},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.693787Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:73aba568a7f34c4f4b6ab36115c211d1649c2f0208f7f7fa01eb1882997722e3","observation_id":"168f7fe6-595c-4b5a-ae74-32f83bbd3961","resolution":{"observed_at":"2026-08-15T21:43:07.010021Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.110158Z","title":"Masked autoregressive flow for density estimation","venue":null,"work_id":"6b614f6b-20e6-47ea-baad-a4911d3c5e72","year":2017},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.699380Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:c943887cec9243aff6655672c81d13fcf6dd9214295977c8658302dbce694cc2","observation_id":"86847d8d-dd02-41d0-b289-8967df55277c","resolution":{"observed_at":"2026-08-15T21:43:09.115488Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.092466Z","title":"Normalizing flows for probabilistic modeling and inference","venue":null,"work_id":"72c8c137-5627-4ec0-b99b-575de66526a7","year":2021},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.704178Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:a4e808fa001cb3eeb377c4f8576079c824a4ea6990c572e88b0bf1034c06efb7","observation_id":"e4a1d408-4d56-4274-b183-dfa2a8dd6b98","resolution":{"observed_at":"2026-08-15T21:43:09.098343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:06.708739Z","title":"Castro, and Ben Glocker","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.708739Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:a761aab02a86bb5a67b86cad134816f2906da8e2b9ea9d0d892cd30fc4254dbc","observation_id":"bc976dc5-e87f-4263-a9d0-418a921c7d53","resolution":{"observed_at":"2026-08-15T21:43:06.708739Z","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":"2026-08-15T21:43:06.713476Z","title":"Causality","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.713476Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:d11a999fb6e2723eba9350962223d62a5f8f574d0de8d41100e95903b8fefd29","observation_id":"a21a0040-259e-45f2-a07f-2a7d9a64bfff","resolution":{"observed_at":"2026-08-15T21:43:06.713476Z","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":"2026-08-15T21:43:09.043993Z","title":"RISE: randomized input sampling for explanation of black-box models","venue":null,"work_id":"5a2dd299-21b8-467e-85b1-d41a2e0c7ed2","year":2018},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.718623Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:29c6a096a584b26549f8caff094c895bbd60d4757734a2fed638740dbc9d6445","observation_id":"3af22e13-24b9-4159-83b2-895e039c13fc","resolution":{"observed_at":"2026-08-15T21:43:09.049575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:09.024917Z","title":"Counterfactual data augmentation using locally factored dynamics","venue":null,"work_id":"c7e28146-154a-4485-9c95-3cd12bd7a0ee","year":2020},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.723194Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:73be49dff2dd2bdc14d2023e560117284814c327873a894fe8ba7a234ef6fee1","observation_id":"53ed2ba2-b7b9-4809-ade5-b406649aa8e6","resolution":{"observed_at":"2026-08-15T21:43:09.030749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:06.727761Z","title":"Causal fairness analysis: A causal toolkit for fair machine learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.727761Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:a040614a226d1fd8618cdb4a405733ee45c9c7f0618a1d97f1a3b5882ef4f0f4","observation_id":"d550dc90-905d-4e8d-9695-86c5853dd8d5","resolution":{"observed_at":"2026-08-15T21:43:06.727761Z","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":"2026-08-15T21:43:08.999876Z","title":"A comprehensive comparison of total-order estimators for global sensitivity analysis","venue":null,"work_id":"09442bfc-683f-49db-8081-9d4c401d7bdc","year":2022},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.732302Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:5570d43b629a2f7bbcea5a970be782dddaac876cc080ab107be447fc0b2ff715","observation_id":"203b6b73-f6d2-4f21-8b77-5860d0d9fb75","resolution":{"observed_at":"2026-08-15T21:43:09.006664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:06.736940Z","title":null,"venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.736940Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:b7815c938b8042553e0bb659c1d69ae6843ad6c923779bf5f4fea715823b3be7","observation_id":"cf78a76a-e4a6-491d-b861-f1059c891284","resolution":{"observed_at":"2026-08-15T21:43:06.736940Z","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":"2026-08-15T21:43:06.741506Z","title":"A generalized anova dimensional decomposition for dependent probability measures","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.741506Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:3263fc48c4d955120aabb7434eac03923b5169b801d5024163a6e6cbe1dec47b","observation_id":"6a3b9773-3345-4c7c-922e-5df938f32561","resolution":{"observed_at":"2026-08-15T21:43:06.741506Z","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":"2026-08-15T21:43:08.979122Z","title":"Balasubramanian, V Varshaneya, and Satya Narayanan Kar","venue":null,"work_id":"bb13fd5a-4f87-4b73-8d2f-4f313f0440f9","year":2023},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.746032Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:8cec5893e299e90134945fb8b308cb7862b9ce44cc7739e73b7265e5e758a2ff","observation_id":"d44dfe52-37d4-448b-8f19-d3f385e88892","resolution":{"observed_at":"2026-08-15T21:43:08.987246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.18183","last_updated":"2023-11-21T09:11:38Z","snapshot_observed_at":"2026-08-18T15:32:49.153499Z","submitted_at":"2023-05-29T16:20:23Z","title":"On Counterfactual Data Augmentation Under Confounding","version":2},"cited_work":{"arxiv_id":"2305.18183","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.18183","snapshot_observed_at":"2026-08-15T21:43:08.087656Z","title":"On Counterfactual Data Augmentation Under Confounding","venue":"cs.LG","work_id":"6b2856e2-058c-4221-8a27-f76f962a7bc7","year":2023},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.751242Z"},"links":{"cited_paper":"/paper/2305.18183","citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:35005ab91a452fee8df3aaee30312e807dd0eefb0c39f483fe854634593a3f82","observation_id":"b06b8007-9637-4091-bd9d-93cdac1b5eb6","resolution":{"observed_at":"2026-08-15T21:43:08.094648Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:06.756119Z","title":"Retzlaff, Alessa Angerschmid, Anna Saranti, David Schneeberger, Richard Röttger, Heimo Müller, and Andreas Holzinger","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.756119Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:255b67d784eba27118bb8e1b964850b6465e07dc65f3af4c8ef91d465827fa6a","observation_id":"b9efcbbe-829c-4143-9f69-6061cbd38ac9","resolution":{"observed_at":"2026-08-15T21:43:06.756119Z","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":"2026-08-15T21:43:06.765113Z","title":"why should i trust you?","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.765113Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:6e1467c1e458e7fc43afde641046a547ff0172f99fa6c81f0da8c1cddcd66df4","observation_id":"10eefc78-f97b-4966-88e3-89ca5305ebd2","resolution":{"observed_at":"2026-08-15T21:43:06.765113Z","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":"2026-08-15T21:43:08.959863Z","title":"On noise abduction for answering counterfactual queries: A practical outlook","venue":null,"work_id":"fd71fbb8-7c7e-4408-a76f-e3887837fc56","year":2022},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.769647Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:ff0a13af78f4ff92667b7ae6a394a234fed97862f73cfcf3b4da717a439a47bd","observation_id":"4f051315-64da-445a-a185-26450df0dadc","resolution":{"observed_at":"2026-08-15T21:43:08.965455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.00276","last_updated":"2023-12-30T16:30:52Z","snapshot_observed_at":"2026-08-16T14:30:44.396787Z","submitted_at":"2023-12-30T16:30:52Z","title":"Second-Order Uncertainty Quantification: Variance-Based Measures","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.00276","snapshot_observed_at":"2026-08-15T21:43:06.774042Z","title":"Second-order uncertainty quantification: Variance-based measures","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.774042Z"},"links":{"cited_paper":"/paper/2401.00276","citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:86bca2ce52a4540eaecd2d1fcd6720e64afa3946a92ebbded6b8bce7607dfb56","observation_id":"c5be89da-5c9d-4f2e-b116-33d393ea4d50","resolution":{"observed_at":"2026-08-15T21:43:06.774042Z","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":"2026-08-15T21:43:08.938872Z","title":"Global sensitivity analysis: The primer","venue":null,"work_id":"6fb0436f-519c-4e7e-9641-3f01fa913531","year":2008},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.779047Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:f45e16225d88be8dbf55ffc45d2cc8687d50d3ebb8790dd6d74ca14e57f065bd","observation_id":"e51bb929-1bde-4545-8f56-3a2df9460ec1","resolution":{"observed_at":"2026-08-15T21:43:08.945237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.13234","last_updated":"2024-09-10T19:36:35Z","snapshot_observed_at":"2026-08-16T14:32:52.994055Z","submitted_at":"2023-12-20T17:59:11Z","title":"Position Paper: Bridging the Gap Between Machine Learning and Sensitivity Analysis","version":2},"cited_work":{"arxiv_id":"2312.13234","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.13234","snapshot_observed_at":"2026-08-15T21:43:07.850799Z","title":"Position Paper: Bridging the Gap Between Machine Learning and Sensitivity Analysis","venue":"cs.LG","work_id":"305a497a-0169-446d-b531-dde51614959a","year":2023},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.783699Z"},"links":{"cited_paper":"/paper/2312.13234","citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:b3770aeea7cdaa9f5210045e4d38f5ebd143a884751f9296b8c0dc41bcb81937","observation_id":"bde1ea04-91d1-495b-949e-2c5fbb7640c8","resolution":{"observed_at":"2026-08-15T21:43:07.859817Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:08.912237Z","title":"CXPlain: causal explanations for model interpretation under uncertainty","venue":null,"work_id":"293912f4-615c-47f8-9f54-7315d8899961","year":2019},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.788787Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:c1196b7349f2a660e626596775282128970c15554f69f9370e2a517e4836b51e","observation_id":"9b8b632b-2908-4990-83af-3cbd4d5a08d4","resolution":{"observed_at":"2026-08-15T21:43:08.920338Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:06.793269Z","title":"Toward causal representation learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.793269Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:5c1de4342fec851ff2d4f2ade9dd6b849dec8556627778ad497cdadc24ef9c37","observation_id":"6479600b-6fca-415f-ab89-a53f3f3d707d","resolution":{"observed_at":"2026-08-15T21:43:06.793269Z","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":"2026-08-15T21:43:06.797958Z","title":"Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.797958Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:28806c143203c0f44d67eda9a0d4d7217ecc032e6fa41fce3d84ea1dae7bdfc6","observation_id":"d79afd58-f435-4ced-a7a8-dc4af1f46950","resolution":{"observed_at":"2026-08-15T21:43:06.797958Z","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":"2026-08-15T21:43:06.802695Z","title":null,"venue":null,"work_id":null,"year":1953},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.802695Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:d0e2ee8e975f2cc4ab7f9f422021f41c91e0a1c4f568b18cd5ccac09b4001a3c","observation_id":"a881a012-0408-417c-a3cd-8e4f0099d107","resolution":{"observed_at":"2026-08-15T21:43:06.802695Z","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":"2026-08-15T21:43:08.892443Z","title":"Weakly supervised disentangled generative causal representation learning","venue":null,"work_id":"b0733290-551e-48df-b1a0-dfde1534e4a8","year":2022},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.807460Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:7e5b3395b170bdc704211b3a3fc4a7dfb425bf00c656be3dbc7cbe2d5a014087","observation_id":"cdfa5bdf-4fc3-4bd3-8caf-510b3eb9a873","resolution":{"observed_at":"2026-08-15T21:43:08.899234Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:08.865318Z","title":"Learning important features through propagating activation differences","venue":null,"work_id":"2680a92d-9440-4852-8933-260579f24343","year":2017},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.811861Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:e98db5205186e2c5d1acf1fb8f109121d709627ba5e00eac2894c2db5f96a688","observation_id":"2cf1d5c2-fe66-45d3-b5b2-9040dbde6cff","resolution":{"observed_at":"2026-08-15T21:43:08.877609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:08.841919Z","title":"Semi-autoregressive energy flows: exploring likelihood-free training of normalizing flows","venue":null,"work_id":"6d8c63c3-654a-45d5-a698-a87f7b6c248e","year":2023},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.816233Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:32445e89d5061e21058990e13420cd4377a57037f92a0a05b65d473f378d5f01","observation_id":"70356f59-5ef0-4c50-b267-55ff62e2508e","resolution":{"observed_at":"2026-08-15T21:43:08.848697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"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":"2026-08-15T21:43:06.820429Z","title":"Deep inside convolutional networks: Visualising image classification models and saliency maps, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.820429Z"},"links":{"cited_paper":"/paper/1312.6034","citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:965177338df19062096bc14247ed3424a8353ea868325606d3091c3c2991f89e","observation_id":"6e83678d-59ec-41f2-b2b4-d74fcaba32a5","resolution":{"observed_at":"2026-08-15T21:43:06.820429Z","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":"2026-08-15T21:43:06.826024Z","title":"On the distribution of points in a cube and the approximate evaluation of integrals","venue":null,"work_id":null,"year":1967},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.826024Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:6e784bd2cbe8eae45dfe98a4f38acda3d7ddc192a1d70120a0880d35b82bc254","observation_id":"bea202d4-4db2-4e6c-a1b6-2601513dfc2a","resolution":{"observed_at":"2026-08-15T21:43:06.826024Z","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":"2026-08-15T21:43:06.830467Z","title":"Global sensitivity indices for nonlinear mathematical models and their monte carlo estimates","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.830467Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:f19b6040a0c60578f5f5baaf52dff70969b6c48f5d16b86d32a2e80160920622","observation_id":"415bb9f1-fb18-478e-80a9-890b2ff32bd2","resolution":{"observed_at":"2026-08-15T21:43:06.830467Z","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":"2026-08-15T21:43:06.834892Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.834892Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:0050825deabef06d6c5c946718acff5cfeaa68926d0d2b28223c6d65e70e6f0b","observation_id":"9c2e2064-1111-4743-bee5-6dfb03c85e78","resolution":{"observed_at":"2026-08-15T21:43:06.834892Z","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":"2026-08-15T21:43:08.819987Z","title":"Conditional variable importance for random forests","venue":null,"work_id":"7cf6e354-50c8-4098-a947-2acceeb3758a","year":2008},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.839786Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:ae2c4a70be90a4f9ba2f86e23fcbe719c54459abc4cb31da02ef7066b8a50442","observation_id":"343eab1c-4074-4f3c-92c5-212ff1138275","resolution":{"observed_at":"2026-08-15T21:43:08.825461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:06.844477Z","title":"Axiomatic attribution for deep networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.844477Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:0aa086ce3e2a233b85a7a995b22627c1e911ddf3de044722e6b664ee7d8cc41d","observation_id":"5b740bfa-e600-4dd4-9d33-507982adc3c7","resolution":{"observed_at":"2026-08-15T21:43:06.844477Z","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":"2026-08-15T21:43:06.848842Z","title":"Tunkiel, Dan Sui, and Tomasz Wiktorski","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.848842Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:5e768c75b0f36b1b909749199df66d590bee9e242c525567ab203ad3015cc2ca","observation_id":"da8103b3-5519-4b62-a3f5-ad4dff83e08c","resolution":{"observed_at":"2026-08-15T21:43:06.848842Z","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":"2026-08-15T21:43:08.783954Z","title":"Interpretable counterfactual explanations guided by prototypes","venue":null,"work_id":"b332fbbb-c903-454f-96c6-3ac239c35521","year":2021},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.853319Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:d92212a9baf5bedff6851b57d2470f9def47bf72fedbd26c6996af3871b5ef13","observation_id":"7325acbd-63ce-47a3-8cf7-95ca7bae7c69","resolution":{"observed_at":"2026-08-15T21:43:08.790081Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.10596","last_updated":"2022-11-15T20:57:53Z","snapshot_observed_at":"2026-08-18T20:06:29.742645Z","submitted_at":"2020-10-20T20:08:42Z","title":"Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.10596","snapshot_observed_at":"2026-08-15T21:43:06.857966Z","title":"Hines, John P","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.857966Z"},"links":{"cited_paper":"/paper/2010.10596","citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:0a6c92a5f5dde086ceed759c4ed27f563a466c15c44e8893c78bb416705f1651","observation_id":"9393c35a-e83a-496b-993a-9445fecd3d2a","resolution":{"observed_at":"2026-08-15T21:43:06.857966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.00399","last_updated":"2018-03-21T11:43:46Z","snapshot_observed_at":"2026-08-14T20:17:58.265867Z","submitted_at":"2017-11-01T15:39:23Z","title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.00399","snapshot_observed_at":"2026-08-15T21:43:06.862981Z","title":"Counterfactual explanations without opening the black box: Automated decisions and the gdpr, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.862981Z"},"links":{"cited_paper":"/paper/1711.00399","citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:04f21de48c07db47f9129a9fff39277ee01b54b3dd249ceb6e2f93b08a58e744","observation_id":"b880f9dc-1807-4370-919f-919b3f16458d","resolution":{"observed_at":"2026-08-15T21:43:06.862981Z","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":"2026-08-15T21:43:06.868189Z","title":"Contrastive-ace: Domain generalization through alignment of causal mechanisms","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.868189Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:085d87e6a9c94d7391a55418c6e5002a3172b57fdb3ae7f89ae29191bbc09d81","observation_id":"b5838ad7-47b4-417b-9d85-166d66ac3077","resolution":{"observed_at":"2026-08-15T21:43:06.868189Z","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":"2026-08-15T21:43:08.763800Z","title":"Quantifying aleatoric and epistemic uncertainty in machine learning: Are conditional entropy and mutual information appropriate measures? In Robin J","venue":null,"work_id":"2abf003a-ebeb-4a70-b1f9-1b0b8013b9d6","year":2023},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.872777Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:583213f158aa35e16fd3bb4cd24e2298c19b620427af5ea06f999c7f0d35353f","observation_id":"80e59c4a-297c-447d-a854-86dd13935d95","resolution":{"observed_at":"2026-08-15T21:43:08.769007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:08.739803Z","title":"Indeterminacy in generative models: Characterization and strong identifiability","venue":null,"work_id":"3e325886-69cb-467c-a004-749bdf675f8b","year":2023},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.877510Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:d18767e169f492e2d5090cd096985ad77a2a3cea359186a0e6c2741ab6bba3be","observation_id":"a6c36c7b-6504-43e7-bac0-4717e21d1fcc","resolution":{"observed_at":"2026-08-15T21:43:08.745373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:06.882021Z","title":"Class specific interpretability in cnn using causal analysis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.882021Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:4679269abdc5678b6727ea9b807d08e1adf31e9e7e80a26569af344f801a1f52","observation_id":"85a1b7cd-ab4f-45a7-9ed8-6a18a6839bd8","resolution":{"observed_at":"2026-08-15T21:43:06.882021Z","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":"2018.00256","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:07.323105Z","title":"Global model interpretation via recursive partitioning","venue":null,"work_id":"a4e0bf12-d75b-45d7-8e5c-dbc1b241aabd","year":2018},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.886116Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:657e30d688287039a98672457e03af6da7313bb5b3e95ecf3f5617b9ba766105","observation_id":"ed420d45-5371-4792-b602-9625a98248de","resolution":{"observed_at":"2026-08-15T21:43:07.330988Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:43:06.890520Z","title":"Causalvae: Disentangled representation learning via neural structural causal models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.890520Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:2c3344ac0c459c7f76e2dc8ff33fbfd0e9d7ea3a47ddb368c4aca145e2e249cd","observation_id":"823cfa6c-43e7-4b80-bd2f-44adfde59de2","resolution":{"observed_at":"2026-08-15T21:43:06.890520Z","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":"2026-08-15T21:43:06.894814Z","title":"Zeiler and Rob Fergus","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.894814Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:8c10bab6627f110be27635c4ceb7d3ea50a1dfe9eb4331b513071daaed02d42f","observation_id":"623c9b03-017c-49f3-9a32-19e416d0f35a","resolution":{"observed_at":"2026-08-15T21:43:06.894814Z","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":"2026-08-15T21:43:08.701609Z","title":"Causal discovery with reinforcement learning","venue":null,"work_id":"e6b98352-dc2f-4c5c-bcd0-9e20a0dc59ba","year":2020},"citing_paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","version":1},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-15T21:43:06.899716Z"},"links":{"citing_paper":"/paper/2505.09660"},"observation_digest":"sha256:ed8ddfaca9e07d7abb67a2036a3ca86d74e60b1ecd79a5cdb0ba207ddddbe136","observation_id":"0add4a0e-f249-428e-b181-e711e66f7fda","resolution":{"observed_at":"2026-08-15T21:43:08.709025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.09660","last_updated":"2025-05-14T12:59:04Z","latest_version":1,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-19T02:43:54.966023Z","submitted_at":"2025-05-14T12:59:04Z","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks"},"reference_resolution":{"displayed":90,"state_counts":{"malformed_identifier":0,"metadata_mismatch":3,"parse_uncertain":0,"unresolved":46,"verified_exact":8,"verified_fuzzy":33},"total_outbound_references":90},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 90 of 90 outbound references and 0 inbound Pith citation observations for arXiv:2505.09660."}