{"as_of":"2026-08-18T22:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bea74754019c4a376452c95be44b53371194cadc993195335302408a16d030bb","coverage":[{"denominator":300,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:29:54.304076Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"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/2505.15023/citation-record","integrity":"/paper/2505.15023/integrity","json":"/paper/2505.15023/citation-record.json","paper":"/paper/2505.15023"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:29:46.770138Z","title":"Asuncion, Arthur U","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:46.770138Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:45920b9556633f876029ab6a1559aed9ef239a423763035cbfd269e3cc26466a","observation_id":"3e722ac8-7b3c-4666-a6ac-e529c44bb74e","resolution":{"observed_at":"2026-08-07T15:29:46.770138Z","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":"2026-08-07T15:29:46.846108Z","title":"Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:46.846108Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:eeb121f7a45ddf93ccebea0e456287ddf22058042bbb55cf229b3304c7027f29","observation_id":"bed7c5eb-2283-4b4d-ad82-850fa002ea07","resolution":{"observed_at":"2026-08-07T15:29:46.846108Z","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":"2026-08-07T15:29:46.948464Z","title":"Learning to represent programs with graphs","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:46.948464Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:f8d6112a24678a2551654e328acefb5119d46e8a193bfd80f405a2b3b50fe531","observation_id":"80f400f1-edc8-4c4c-b0cf-ca8beaf29658","resolution":{"observed_at":"2026-08-07T15:29:46.948464Z","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":"2026-08-07T15:29:47.063915Z","title":"Information retrieval models for recovering traceability links between code and documentation","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:47.063915Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:c677f885bf7feed86b29a91a7d40261436de49ae1af6e62d761888579e316e50","observation_id":"06bae4f2-6b61-4088-acee-090d726c7654","resolution":{"observed_at":"2026-08-07T15:29:47.063915Z","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":"2026-08-07T15:29:47.164557Z","title":"Unified pre-training for program understanding and generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:47.164557Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:8bc8c1bf7890905d35ee57c720ca07521ebdeab1b836be4e5a89bc025b395358","observation_id":"23f59c43-c3cc-4a54-bb95-0569cb21824a","resolution":{"observed_at":"2026-08-07T15:29:47.164557Z","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":"2026-08-07T15:29:47.268659Z","title":"Albrecht, Filippos Christianos, and Lukas Sch\\\"afer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:47.268659Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:47a753fc2b0c1a2f1b0759144413e2aefcd24f2db0dd0278f084de0d897f3786","observation_id":"c3ffbf13-8430-46c8-89e9-edcb86e1a8f7","resolution":{"observed_at":"2026-08-07T15:29:47.268659Z","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":"2026-08-07T15:29:47.389482Z","title":"A literature review of automatic traceability links recovery for software change impact analysis","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:47.389482Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:8e2005981f59370591d16f6f33ad0f1cbf849aeeab6ed4a766e881fabd2aa388","observation_id":"dd0b6b09-fbd3-4ba3-9e19-fb5ef0cc44ba","resolution":{"observed_at":"2026-08-07T15:29:47.389482Z","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":"2026-08-07T15:29:47.503416Z","title":"The adverse effects of code duplication in machine learning models of code","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:47.503416Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:549e510eb0a1b4d46928bdcf5dc85f45a37cece98247a489d8e5f3bfe1f29a04","observation_id":"f88d7351-901c-4e77-9863-68350270a036","resolution":{"observed_at":"2026-08-07T15:29:47.503416Z","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":"2026-08-07T15:29:47.599058Z","title":"Abu-Mostafa, Malik Magdon-Ismail, and Hsuan-Tien Lin","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:47.599058Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:08a19c8478b2ddace014752907037b69e6ec39aca93ad77beed20118ac245483","observation_id":"f25bd60b-5efa-4470-9703-4678a7d8a89c","resolution":{"observed_at":"2026-08-07T15:29:47.599058Z","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":"2026-08-07T15:29:47.690525Z","title":"The claude 3 model family: Opus, sonnet, haiku, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:47.690525Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:d683387ea2c6dccbf836797cdb16d9964e5257c1026fb5123244140673211e8b","observation_id":"2213d293-2110-4db1-9dea-d7aa5a4e95e0","resolution":{"observed_at":"2026-08-07T15:29:47.690525Z","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":"2026-08-07T15:29:47.757443Z","title":"Program synthesis with large language models, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:47.757443Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:6c03097e4b305a0a1afaaec0d941849db24e46a340ea59b245521718617a5187","observation_id":"155526d2-dbb1-43d9-b323-507c94c9b8e0","resolution":{"observed_at":"2026-08-07T15:29:47.757443Z","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":"2026-08-07T15:29:47.819706Z","title":"Bishop and Hugh Bishop","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:47.819706Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:1fdef0bb27d1587f2deb1030f2a8f811859e5f9e1d085550a95963b1016e8e20","observation_id":"22fe03d1-58d2-45c7-9b80-0172bd44accd","resolution":{"observed_at":"2026-08-07T15:29:47.819706Z","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":"2026-08-07T15:29:47.879750Z","title":"Gpt-neox-20b: An open-source autoregressive language model, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:47.879750Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:75d3ea80a132eaba0e98560c9f84c4321db1e542c4cba90b4632ca51eeb7cae1","observation_id":"4d66507c-e0b6-4540-85b9-3a8b22b881ca","resolution":{"observed_at":"2026-08-07T15:29:47.879750Z","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":"2026-08-07T15:29:47.956207Z","title":"Maximum a posteriori estimators as a limit of Bayes estimators , 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:47.956207Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:7182d8918dbc8435dc28e651106ee1ba226edb19da19846538194824e67ba4bd","observation_id":"4ffabdb6-6f90-45a3-bd04-496ea5dca13f","resolution":{"observed_at":"2026-08-07T15:29:47.956207Z","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":"2026-08-07T15:29:48.020400Z","title":"A neural probabilistic language model","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.020400Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:c84bbedf4205131c81f281385420410baf3f2962f0f9cc31b57fe3db7fc09c8d","observation_id":"c8a172ea-ed64-4d66-8e8f-8f3b841dcef1","resolution":{"observed_at":"2026-08-07T15:29:48.020400Z","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":"2026-08-07T15:29:48.083556Z","title":"Artificial Life","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.083556Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:1a9a4b519bea6027ae0fbb71a3be973b75cd8dfa8f73dfee335061404fb71bbc","observation_id":"35b68ac2-1817-4d97-a624-15e61fb13f0c","resolution":{"observed_at":"2026-08-07T15:29:48.083556Z","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":"2026-08-07T15:29:48.165212Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.165212Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:2a4fd28470ed6e3bd0cb3ed44667fe474f0cebf1932b362357d2f127ed44448a","observation_id":"c5a1762a-e9bd-4780-9eaf-38a34a9b9615","resolution":{"observed_at":"2026-08-07T15:29:48.165212Z","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":"2026-08-07T15:29:48.232306Z","title":"Bender, Timnit Gebru, Angelina McMillan-Major, and Margaret Mitchell","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.232306Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:9fd6e565485875c923eb21947ee7b6791ea70d9469c894ab839bcc0745f7873d","observation_id":"7a0ec2f2-2880-4da7-9037-eea865922ac5","resolution":{"observed_at":"2026-08-07T15:29:48.232306Z","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":"2026-08-07T15:29:48.316270Z","title":null,"venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.316270Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:5d22e7747700d661d046d88f02c3a25ea00f4239e34de4543348b3e394fe300a","observation_id":"3eaabff7-bfc8-4ad5-8e4e-2106ec93d5c1","resolution":{"observed_at":"2026-08-07T15:29:48.316270Z","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":"2026-08-07T15:29:48.391048Z","title":"Natural Language Processing with Python","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.391048Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:d64337eb5526448545525b2aa1d165b236d5ed9973c7b924e4a589fc8631cdf9","observation_id":"193a32d8-1ad8-43f2-a22c-ed572ca52985","resolution":{"observed_at":"2026-08-07T15:29:48.391048Z","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":"2026-08-07T15:29:48.437921Z","title":"NLTK : The natural language toolkit","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.437921Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:dad1f29853ab144579420575daf96d5a3b07abb936967448804534af19aa2c72","observation_id":"5e74113e-10c1-4843-a28c-89a869a41f39","resolution":{"observed_at":"2026-08-07T15:29:48.437921Z","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":"2026-08-07T15:29:48.468409Z","title":"API design for machine learning software: experiences from the scikit-learn project","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.468409Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:827a5e31b116cdb481d443f7700d83cb6462d1fa291b4c2e1742fa8efadc568c","observation_id":"93f2c443-9caa-4d33-bed2-efd7f9a25a54","resolution":{"observed_at":"2026-08-07T15:29:48.468409Z","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":"2026-08-07T15:29:48.511404Z","title":"A model-driven architecture approach to accelerate software code generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.511404Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:6570dc66b5033253eaf73d7315418b90dedbd33384cc33a25d6b526e30837209","observation_id":"69c5b8a7-735b-49e1-a6cf-bf28d522166b","resolution":{"observed_at":"2026-08-07T15:29:48.511404Z","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":"2026-08-07T15:29:48.550484Z","title":"On identifiability in transformers, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.550484Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:89874727d6d71285c3509a18bf8d5542544b9e24dee3bdba70c263ecadfec455","observation_id":"939a3f70-ada1-4069-87da-8e23860999cc","resolution":{"observed_at":"2026-08-07T15:29:48.550484Z","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":"2026-08-07T15:29:48.593806Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.593806Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:c0e6a8562d15830f0a81947a06162efb85f41fe8d63f9ad48500b34f582eacec","observation_id":"48ddcedc-72cf-4504-877e-8b9dddaeb37e","resolution":{"observed_at":"2026-08-07T15:29:48.593806Z","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":"2026-08-07T15:29:48.634671Z","title":"Biggerstaff, Bharat G","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.634671Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:1572dd85816bec01e6e81bd2fbeefc4b0b708876e3430227aec320b894ffe3c6","observation_id":"ebad0ad8-1ab8-4c2d-8c57-ed133545829c","resolution":{"observed_at":"2026-08-07T15:29:48.634671Z","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":"2026-08-07T15:29:48.683167Z","title":"tree-sitter/tree-sitter: v0.25.3, March 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.683167Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:6bce907f602285f5b555a613d372cb3e09a3d1e16bcff4cca85b80d5b4e9cce2","observation_id":"9d0c35a2-660a-4f8c-9d6b-d207985244f2","resolution":{"observed_at":"2026-08-07T15:29:48.683167Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07764","last_updated":"2021-10-20T18:32:48Z","snapshot_observed_at":"2026-08-13T20:13:16.218360Z","submitted_at":"2020-02-18T17:53:55Z","title":"Sampling in Software Engineering Research: A Critical Review and Guidelines","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07764","snapshot_observed_at":"2026-08-07T15:29:48.726361Z","title":"Sampling in Software Engineering Research : A Critical Review and Guidelines , October 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.726361Z"},"links":{"cited_paper":"/paper/2002.07764","citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:c4d4e714fd7c395816c63e5ef38ad275857607130ec0ef52ec75d491e01d3de8","observation_id":"c68894a5-8c6d-4776-9104-84b0aa853ad6","resolution":{"observed_at":"2026-08-07T15:29:48.726361Z","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":"2026-08-07T15:29:48.766253Z","title":null,"venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.766253Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:65ceb69548840e0fcf12afbee688bfa03314c7b7a3a56b4e93a68f6662c21b61","observation_id":"78f52fdd-a08f-4c49-8045-02b0078aa3ea","resolution":{"observed_at":"2026-08-07T15:29:48.766253Z","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":"2026-08-07T15:29:48.798978Z","title":"Ullman, Fernando Martinez-Plumed, Joshua B","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.798978Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:29a7d524e359a727c75dbf2128a15ae60027d02587f4bb1572e449b601b93d19","observation_id":"728d78b2-6134-4937-93d1-fc2c53c4ceed","resolution":{"observed_at":"2026-08-07T15:29:48.798978Z","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":"2026-08-07T15:29:48.865707Z","title":"Causality: The Place of the Causal Principle in Modern Science","venue":null,"work_id":null,"year":1959},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.865707Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:e82e23064e13060ead79687153e82b7eb0a5c9fd7d227a745f6f1fdf329fd7a4","observation_id":"5bb044df-3ab9-4a0c-b5e8-c80785ed4a2a","resolution":{"observed_at":"2026-08-07T15:29:48.865707Z","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":"2026-08-07T15:29:48.925446Z","title":"Emergence and Convergence: Qualitative Novelty and the Unity of Knowledge","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.925446Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:d874d4beada3e3558e49e48816ce00559ddd6992d536df94c9b05df923efdf29","observation_id":"8a735b1c-07f9-4e39-8bd1-d471ae2c4698","resolution":{"observed_at":"2026-08-07T15:29:48.925446Z","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":"2026-08-07T15:29:48.987035Z","title":"Philosophy of Science: Volume 1 and 2","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:48.987035Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:004939e86c9290f4926ba0d0a815c6bc493100ee47756f8ab16e40f2e1548786","observation_id":"3f7483dc-78c9-481b-91e9-29c78bfb0713","resolution":{"observed_at":"2026-08-07T15:29:48.987035Z","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":"2026-08-07T15:29:49.069925Z","title":"The care and feeding of wild-caught mutants","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.069925Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:afd4e9799269cb02ece8fe881f1e54c2bc9e98be9d278575d3a508ffc690e673","observation_id":"b2f7228e-7178-4b0d-8d55-ef48c80abe05","resolution":{"observed_at":"2026-08-07T15:29:49.069925Z","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":"2026-08-07T15:29:49.141019Z","title":"An empirical exploration of trust dynamics in llm supply chains, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.141019Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:42c4ce4ad003810b45517073f426429a4ddae08bb7898c0cf38148121866d3fb","observation_id":"1bf0d687-4483-44c4-babf-2cf703040b48","resolution":{"observed_at":"2026-08-07T15:29:49.141019Z","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":"2026-08-07T15:29:49.215736Z","title":"Nature’s Capacities and Their Measurement","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.215736Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:927f3601fff2c6c130d7ed97c1f13a5326d6c9162df516b63a8c0740f1f38482","observation_id":"39e8eb37-533a-459e-b8db-b3c44c4330ae","resolution":{"observed_at":"2026-08-07T15:29:49.215736Z","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":"2026-08-07T15:29:49.292921Z","title":"The Dappled World: A Study of the Boundaries of Science","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.292921Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:de00292fbff77644dc4f5fb856b139647484c48091889e63834cbde4a7b059cb","observation_id":"738a59d0-7f51-47f2-a544-3f9944736dcd","resolution":{"observed_at":"2026-08-07T15:29:49.292921Z","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":"2026-08-07T15:29:49.400177Z","title":"Hunting Causes and Using Them: Approaches in Philosophy and Economics","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.400177Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:0a739a186c8500d0f91603c5c20125d26ed4e453bdf0a370c694ad6af0c97d2b","observation_id":"1b8683a6-742c-4933-9571-5a5c33f63b8c","resolution":{"observed_at":"2026-08-07T15:29:49.400177Z","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":"2026-08-07T15:29:49.450990Z","title":"An empirical study on the usage of bert models for code completion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.450990Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:1b101801928dc9def89b879926baa7a007a20d41c525fcb251c7e60ad871cc6f","observation_id":"52c59e40-ce57-4ad0-98a1-952b61a19f27","resolution":{"observed_at":"2026-08-07T15:29:49.450990Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.07115","last_updated":"2021-03-12T07:26:25Z","snapshot_observed_at":"2026-08-16T18:39:25.850505Z","submitted_at":"2021-03-12T07:26:25Z","title":"An Empirical Study on the Usage of BERT Models for Code Completion","version":1},"cited_work":{"arxiv_id":"2103.07115","doi":null,"metadata_source":"pith","pith_arxiv_id":"2103.07115","snapshot_observed_at":"2026-08-07T15:30:11.164493Z","title":"An Empirical Study on the Usage of BERT Models for Code Completion","venue":"cs.SE","work_id":"e96307f8-84ab-4383-b16d-ec68606adcdc","year":2021},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.502211Z"},"links":{"cited_paper":"/paper/2103.07115","citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:c063e33b40a1f20769b81699e3c914c6a68cecccd075690ac473e28eb4c3dca2","observation_id":"17f7f866-7732-4a00-9012-dbbf02b1b9e3","resolution":{"observed_at":"2026-08-07T15:30:11.245738Z","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":"2026-08-07T15:29:49.546949Z","title":"An empirical study on the usage of transformer models for code completion","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.546949Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:b2f10f0e02cf57f5b10dac3e884297196bdf04e0b40d8649fed8bf0a251b04dc","observation_id":"4eca3282-80fc-478f-8e33-fe497e37dd76","resolution":{"observed_at":"2026-08-07T15:29:49.546949Z","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":"2026-08-07T15:29:49.600323Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.600323Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:6743a580e44352ff0cccc14cb6e0d38e8a9329099614bf4a26706d45f85cc943","observation_id":"79a64c81-4102-4109-8fd5-3e8354710ebe","resolution":{"observed_at":"2026-08-07T15:29:49.600323Z","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":"2026-08-07T15:29:49.631135Z","title":"Counterfactual explanations for models of code","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.631135Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:15bd9b899ba16d4c87eaf80951f6fe4cbd85316f0a3bd650f249802ef94106dc","observation_id":"8140c885-a985-4270-b17f-11be57b7d693","resolution":{"observed_at":"2026-08-07T15:29:49.631135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.08227","last_updated":"2022-12-19T10:30:12Z","snapshot_observed_at":"2026-08-16T16:38:41.027426Z","submitted_at":"2022-08-17T11:16:52Z","title":"MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.08227","snapshot_observed_at":"2026-08-07T15:29:49.670235Z","title":"Feldman, Arjun Guha, Michael Greenberg, and Abhinav Jangda","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.670235Z"},"links":{"cited_paper":"/paper/2208.08227","citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:21b47617de8867b540593ded3201767c079bf1fe93387c977bd462af2c269758","observation_id":"b433847b-73ec-43e4-95e8-cdc00ff52f7f","resolution":{"observed_at":"2026-08-07T15:29:49.670235Z","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":"2026-08-07T15:29:49.712433Z","title":"Constructing Grounded Theory: A Practical Guide through Qualitative Analysis","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.712433Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:e5046d554724252f81aaa5c32de40a0cd6b90a14fa608af8f0fb24f28df20a64","observation_id":"7a513190-2f09-448e-ada5-79c3d5e1ea99","resolution":{"observed_at":"2026-08-07T15:29:49.712433Z","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":"2026-08-07T15:29:49.746463Z","title":"Chang, and Mark Christensen","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.746463Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:f6d232573218b6ee61afb71ed5eb59bfda4a86a632bcb9476b846663e6a6c83a","observation_id":"5ba19121-3262-4e5e-8204-ccb4e904fc50","resolution":{"observed_at":"2026-08-07T15:29:49.746463Z","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":"2026-08-07T15:29:49.789091Z","title":"A machine learning approach for tracing regulatory codes to product specific requirements","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.789091Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:225b0b32a6cbdba565fefa82804237a3d198ad6ee3ca708888b85b2e489e4562","observation_id":"5912d103-110e-481c-bde5-57756c7747db","resolution":{"observed_at":"2026-08-07T15:29:49.789091Z","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":"2026-08-07T15:29:49.819948Z","title":"Connor, A","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.819948Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:e67fbd743b1757a056918864f0fc5d8257d0604ea523076571a23dde76f979d0","observation_id":"66213aa2-cd41-451c-bf4f-2a636f9d80ce","resolution":{"observed_at":"2026-08-07T15:29:49.819948Z","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":"2026-08-07T15:29:49.846843Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.846843Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:c1ae2b1aa2114308236bc43dfb93fdc3293410d3d5072569c23560266477f1b8","observation_id":"dcddaf45-f62c-4300-94da-3b3962b50a37","resolution":{"observed_at":"2026-08-07T15:29:49.846843Z","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":"2026-08-07T15:29:49.886071Z","title":"Software and Systems Traceability","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.886071Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:fc19e1649b3a485f2782cbee1a961bc29e4954fa9400afd6e412186c6aaaf525","observation_id":"9e2245eb-9036-4ec6-97d4-99dae54408e6","resolution":{"observed_at":"2026-08-07T15:29:49.886071Z","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":"2026-08-07T15:29:49.934106Z","title":"Achieving lightweight trustworthy traceability","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.934106Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:edb5b97abb696b2f8fe7ae6502606816fb40d8fa5a89574f7641af8127d564dc","observation_id":"b62b5c67-f5af-406e-83e2-3a88a77f4757","resolution":{"observed_at":"2026-08-07T15:29:49.934106Z","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":"2026-08-07T15:29:49.965814Z","title":"Sequencer: Sequence-to-sequence learning for end-to-end program repair","venue":null,"work_id":null,"year":1943},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.965814Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:b1b646ce4b968991e233a27ced0d7a6682a9e7a71e0f2e741fd829dc5401af63","observation_id":"d810da11-a2cf-4802-a635-c0036f117bad","resolution":{"observed_at":"2026-08-07T15:29:49.965814Z","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":"2026-08-07T15:29:49.999264Z","title":"Clement, Shuai Lu, Xiaoyu Liu, Michele Tufano, Dawn Drain, Nan Duan, Neel Sundaresan, and Alexey Svyatkovskiy","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:49.999264Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:e14f42cda1d1a19fdd641b8104034dbc60788ccb1074848f3ea138634f30a8f7","observation_id":"f0c52eee-0374-4a6d-af26-9c95ee1bee6e","resolution":{"observed_at":"2026-08-07T15:29:49.999264Z","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":"2026-08-07T15:29:50.068614Z","title":"Bigquery: Serverless, highly scalable, and cost-effective multi-cloud data warehouse, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:50.068614Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:cac4d289d03d8298519ddaae7a22244b33c8ba98126196fcec349ea6b1855fd5","observation_id":"ee61284d-4dde-4461-a85d-54454fd06415","resolution":{"observed_at":"2026-08-07T15:29:50.068614Z","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":"2026-08-07T15:29:50.153789Z","title":"Debugging tool for code generation neural language models, March 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:50.153789Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:d015742a1fb66b79df1c9673aaab4ac268bfdbff83a8bcdf0d6632a04aae0e7f","observation_id":"d79db10f-68f7-4bd9-a8b8-a05cef64130d","resolution":{"observed_at":"2026-08-07T15:29:50.153789Z","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":"2026-08-07T15:29:50.205749Z","title":"Cisco Systems","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:50.205749Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:32e590c453045215dca251ea463eb34d1f3e898ea6529caf1b9312fb41a1b1b5","observation_id":"2892dd3d-571e-4e5a-9c6c-1a75c6ec324f","resolution":{"observed_at":"2026-08-07T15:29:50.205749Z","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":"2026-08-07T15:29:50.220913Z","title":"Improving smart contract security with contrastive learning-based vulnerability detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:50.220913Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:a24df4f65679991b0e604a67e473b657349c03218a63443cb6a68fa66ef7732d","observation_id":"154ccf3a-2c1c-4dee-bb1d-7fde6fcd326a","resolution":{"observed_at":"2026-08-07T15:29:50.220913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.05667","last_updated":"2024-07-12T15:34:29Z","snapshot_observed_at":"2026-08-16T16:17:09.769747Z","submitted_at":"2022-11-10T16:04:28Z","title":"What Makes a Good Explanation?: A Harmonized View of Properties of Explanations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.05667","snapshot_observed_at":"2026-08-07T15:29:50.308670Z","title":"What Makes a Good Explanation ?: A Harmonized View of Properties of Explanations , December 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:50.308670Z"},"links":{"cited_paper":"/paper/2211.05667","citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:78f6de8addd93cf154d99993a1471c4ce3c5aa8d1f1599a7bbb2ab7e113e020b","observation_id":"9e2f10e5-26fc-4b6f-a3fc-5023498f6650","resolution":{"observed_at":"2026-08-07T15:29:50.308670Z","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":"2026-08-07T15:29:50.457607Z","title":"Snopy: Bridging sample denoising with causal graph learning for effective vulnerability detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:50.457607Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:e32e9f3f1227f36c292356c85a894e2cb34148e499bdff19f215c21d2e1a4796","observation_id":"965ddb7b-aace-4983-a94c-c3d6b85c2a43","resolution":{"observed_at":"2026-08-07T15:29:50.457607Z","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":"2026-08-07T15:29:50.518459Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:50.518459Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:0b828df5248e39c5d501dd487814457bf63c17aededf39129aedc259f4811f8e","observation_id":"20d8090e-6ca5-4605-94e2-5adf0900edc8","resolution":{"observed_at":"2026-08-07T15:29:50.518459Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1259","last_updated":"2014-10-07T18:08:30Z","snapshot_observed_at":"2026-08-14T23:20:50.864190Z","submitted_at":"2014-09-03T21:03:41Z","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1259","snapshot_observed_at":"2026-08-07T15:29:50.572445Z","title":"On the Properties of Neural Machine Translation : Encoder - Decoder Approaches , October 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:50.572445Z"},"links":{"cited_paper":"/paper/1409.1259","citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:ee75a791902a923c25c6ef447ea80d09b5f20bd6fe61ada64c76b3cc66255b40","observation_id":"fa67bcfd-ff6c-459b-a217-876eccc082b7","resolution":{"observed_at":"2026-08-07T15:29:50.572445Z","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":"2026-08-07T15:29:50.662212Z","title":"A survey on open source software trustworthiness","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:50.662212Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:caa18ef1ec90fd5c15b4eca12f8df3fe227dabfb82bd8bebde403cace984a541","observation_id":"907423ae-a612-4de5-be04-0358fce9209a","resolution":{"observed_at":"2026-08-07T15:29:50.662212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08696","last_updated":"2022-03-10T02:28:59Z","snapshot_observed_at":"2026-08-18T21:13:11.433434Z","submitted_at":"2021-04-18T03:38:26Z","title":"Knowledge Neurons in Pretrained Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08696","snapshot_observed_at":"2026-08-07T15:29:50.727326Z","title":"Knowledge neurons in pretrained transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:50.727326Z"},"links":{"cited_paper":"/paper/2104.08696","citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:fab68bab64a449786d2203a08c53db1019a0a1f0201b1c2d2278907964d944cf","observation_id":"471b2b56-b5ad-45cc-92e4-9259004b0f83","resolution":{"observed_at":"2026-08-07T15:29:50.727326Z","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":"2026-08-07T15:29:50.796028Z","title":"Enhancing software traceability by automatically expanding corpora with relevant documentation","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:50.796028Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:6b304790810bdaddb4f02ed2c6e7a306249202690db6b0b408be26b8a1b377a7","observation_id":"1a84db26-2bd4-4a86-9859-b7cff6158264","resolution":{"observed_at":"2026-08-07T15:29:50.796028Z","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":"2026-08-07T15:29:50.867777Z","title":"Technique integration for requirements assessment","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:50.867777Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:5705d03b070afa3811c66edb9c00494058b29211d1708b0f0bd7f8658f2287fb","observation_id":"5690e52e-a7a8-4692-bc31-66e7eaea2318","resolution":{"observed_at":"2026-08-07T15:29:50.867777Z","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":"2026-08-07T15:29:50.939093Z","title":"Automatic traceability link recovery via active learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:50.939093Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:9cfbbaa4f932b9565562e5297a96922de717fd7206f83bc7e6e3ad9e326fd941","observation_id":"3b39ebb7-4ab8-403f-a0fe-fd8352bc7b95","resolution":{"observed_at":"2026-08-07T15:29:50.939093Z","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":"2026-08-07T15:29:51.067635Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:51.067635Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:0367e6e2a58b94f1bae15e878052ad7f390ec9a1b6dbae8cd710ad11f585a12d","observation_id":"8ce18b71-b2b6-40b6-921f-588b23120bed","resolution":{"observed_at":"2026-08-07T15:29:51.067635Z","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":"2026-08-07T15:29:51.172524Z","title":"Incremental approach and user feedbacks: a silver bullet for traceability recovery","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:51.172524Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:a829e585c601d7a51104352be11f29d2becffd80acaf9503634fd6cf7963c7e4","observation_id":"b71a5cea-dfe1-45a3-bb34-34addc6ca393","resolution":{"observed_at":"2026-08-07T15:29:51.172524Z","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":"2026-08-07T15:29:51.313595Z","title":"Ir-based traceability recovery processes: An empirical comparison of one-shot and incremental processes","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:51.313595Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:903ac93c879d0076438c1a5ad52ac13a4fd8acdb27d94c40de8e7f48ae940180","observation_id":"bc1e51c9-f52a-46a8-a6b6-eb65157d747c","resolution":{"observed_at":"2026-08-07T15:29:51.313595Z","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":"2026-08-07T15:29:51.439764Z","title":"Assessing ir-based traceability recovery tools through controlled experiments","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:51.439764Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:393d42dcba2a97367d1ef6c80eaafca7d5214a452b213546cee368c10d9cb600","observation_id":"b680a074-f97c-4821-8891-3e2cc6e91073","resolution":{"observed_at":"2026-08-07T15:29:51.439764Z","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":"2026-08-07T15:29:51.576467Z","title":"Supporting and accelerating reproducible research in software maintenance using tracelab component library","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:51.576467Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:b388188842b079f3e44f2c716cbb3579aab939811b5373c5dd644b329e32dc8d","observation_id":"610e85f6-10e0-4d7a-85b7-febce6077f5f","resolution":{"observed_at":"2026-08-07T15:29:51.576467Z","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":"2026-08-07T15:29:51.694410Z","title":"Configuring topic models for software engineering tasks in tracelab","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:51.694410Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:3f79597f64a9eed7f5359e6f830736304a37793506f760fd547d4c3a5999d983","observation_id":"b6d604c1-ab65-4dd1-ac66-07aa3db1549f","resolution":{"observed_at":"2026-08-07T15:29:51.694410Z","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":"2026-08-07T15:29:51.805400Z","title":"Integrating information retrieval, execution and link analysis algorithms to improve feature location in software","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:51.805400Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:9905b8339d0340a7c4220b6727499a0192ff3a1c3fe676bac9df05cb8baf21b5","observation_id":"9bc01895-c604-4747-af81-6e2e37141289","resolution":{"observed_at":"2026-08-07T15:29:51.805400Z","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":"2026-08-07T15:29:51.935992Z","title":"What is artificial life today, and where should it go? Artificial Life , 30(1):1--15, 02 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:51.935992Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:6d62c4d69141f4cdd122c57f0724bc19307c086a6c55bd0da57642c45baf4540","observation_id":"ce61d141-02e4-4de6-b823-004e01240d8a","resolution":{"observed_at":"2026-08-07T15:29:51.935992Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.07002","last_updated":"2021-07-14T21:08:30Z","snapshot_observed_at":"2026-08-16T18:09:57.505755Z","submitted_at":"2021-07-14T21:08:30Z","title":"The Benchmark Lottery","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.07002","snapshot_observed_at":"2026-08-07T15:29:52.087848Z","title":"Gritsenko, Zhe Zhao, Neil Houlsby, Fernando Diaz, Donald Metzler, and Oriol Vinyals","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:52.087848Z"},"links":{"cited_paper":"/paper/2107.07002","citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:e251a5b48f7d4748df60b9d378d1259fbb7f91d4cd828f9949290605df82e94e","observation_id":"f704146b-2dd2-44a1-a6b9-0d52f27482c7","resolution":{"observed_at":"2026-08-07T15:29:52.087848Z","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":"2026-08-07T15:29:52.206517Z","title":"Towards a rigorous science of interpretable machine learning, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:52.206517Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:c89d2918156d14f7caff4aa719ef11e3cf737fb1661c0faaf45d1248a814c515","observation_id":"2e174a4b-5f49-4fbd-b541-182639832149","resolution":{"observed_at":"2026-08-07T15:29:52.206517Z","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":"2026-08-07T15:29:52.367343Z","title":"Considerations for Evaluation and Generalization in Interpretable Machine Learning , pages 3--17","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:52.367343Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:261499c97006de1b1bddb46e7fa3e6b6a777ff894236c2a80247f140c4d13b2e","observation_id":"e3121f35-eb46-41d5-9809-02386be565c5","resolution":{"observed_at":"2026-08-07T15:29:52.367343Z","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":"2026-08-07T15:29:52.502289Z","title":"Eick, T.L","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:52.502289Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:87e08bea2494bf0e77709aedff8c1bead141f8e258ff221c682feba5ce4cdf6b","observation_id":"2703bfa0-1055-473d-9ae4-057e5580590f","resolution":{"observed_at":"2026-08-07T15:29:52.502289Z","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":"2026-08-07T15:29:52.563408Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:52.563408Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:5677821438b80354d3a03e1dfda3e16a9686c3baa411b0abc4444d319cee8fc6","observation_id":"09bfe1b5-f761-4417-b179-7a4d20f7fc56","resolution":{"observed_at":"2026-08-07T15:29:52.563408Z","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":"2026-08-07T15:29:52.630274Z","title":"Estimating the number of remaining links in traceability recovery","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:52.630274Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:cf87dd42a850c85765a9c468f55fc05cec3c5446cc0f5e2314f5a9cc0ce22a8c","observation_id":"dfc84b97-1162-4097-96cf-d24809f0faa2","resolution":{"observed_at":"2026-08-07T15:29:52.630274Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.05422","last_updated":"2019-08-26T08:41:43Z","snapshot_observed_at":"2026-08-14T17:59:52.654749Z","submitted_at":"2018-11-13T17:24:51Z","title":"Bayesian Data Analysis in Empirical Software Engineering Research","version":5},"cited_work":{"arxiv_id":"1811.05422","doi":null,"metadata_source":"pith","pith_arxiv_id":"1811.05422","snapshot_observed_at":"2026-08-07T15:30:10.925636Z","title":"Bayesian Data Analysis in Empirical Software Engineering Research","venue":"cs.SE","work_id":"2d525721-38ff-4f3c-9683-9756278addd4","year":2018},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:52.733952Z"},"links":{"cited_paper":"/paper/1811.05422","citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:f1de08db4e471dbddd246fda16f9418a59d33ab0f57b23ce0c6332918d567be4","observation_id":"608afb84-f239-4a12-a162-5dfa13449f93","resolution":{"observed_at":"2026-08-07T15:30:11.022900Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:29:52.813611Z","title":"Automated repair of programs from large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:52.813611Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:01e48cd52c0ed367c4f5643c6c1d18150e371a0ed9c1aec0d2a89c4e1f4ddbfe","observation_id":"b8d49597-f324-4860-ab3c-5b9c4e649dc9","resolution":{"observed_at":"2026-08-07T15:29:52.813611Z","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":"2026-08-07T15:29:52.905261Z","title":"C ode BERT : A pre-trained model for programming and natural languages","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:52.905261Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:4095a779bace8457ee617cbfb74ef373d1ded737dc29bb3c3e3670cfaad15ef2","observation_id":"a0214937-7ddb-4b83-bf25-6a6c59df04b0","resolution":{"observed_at":"2026-08-07T15:29:52.905261Z","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":"2026-08-07T15:29:52.965335Z","title":"Vulexplainer: A transformer-based hierarchical distillation for explaining vulnerability types","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:52.965335Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:2b7aaf5a37da887bc6c24f60c52d5ccf9c2fa6b646e0ef50cd5a4a09a3083784","observation_id":"63405cf1-8d4f-495e-956d-f4c987da82b6","resolution":{"observed_at":"2026-08-07T15:29:52.965335Z","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":"2026-08-07T15:29:53.017185Z","title":"Comparing explanation methods for traditional machine learning models part 1: An overview of current methods and quantifying their disagreement","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:53.017185Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:30a54db430a8e5e5502e6bd4157134fa198dd73ef9b661bb598b00ce4f7be180","observation_id":"c7b90ff6-20ab-4781-b90f-36ca05f583b1","resolution":{"observed_at":"2026-08-07T15:29:53.017185Z","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":"2026-08-07T15:29:53.099721Z","title":"Can cooperative multi-agent reinforcement learning boost automatic web testing? an exploratory study","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:53.099721Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:97ffd6c35aaea0186300111d730f715b5f80653a26e7e69435bb811268aa5798","observation_id":"ec00674b-f141-4065-9da7-bc725c2ce53b","resolution":{"observed_at":"2026-08-07T15:29:53.099721Z","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":"2026-08-07T15:29:53.188353Z","title":"Trace++: A traceability approach to support transitioning to agile software engineering","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:53.188353Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:ab078cc4f40ce352582c7c254f7e4f8546d5bd31489cae505c13af0703550e71","observation_id":"f6ea6b11-9000-43c4-ab94-feb04279c21d","resolution":{"observed_at":"2026-08-07T15:29:53.188353Z","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":"2026-08-07T15:29:53.272753Z","title":"The pile: An 800gb dataset of diverse text for language modeling, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:53.272753Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:2fcadf20881d47596b5dd181fc9bcf0c1749b3f831579c3245fd02fe539bd59c","observation_id":"d5979c33-fbd4-4d7a-b7c3-6d6366f4da62","resolution":{"observed_at":"2026-08-07T15:29:53.272753Z","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":"2026-08-07T15:29:53.395901Z","title":"Codeparrot, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:53.395901Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:1a291f60966cfbd1267ed88a697a2805cfbbbb0a2d2be5e2a69fcea2ae5de91d","observation_id":"b344cc9b-120d-4d11-84b4-8f97aa23a447","resolution":{"observed_at":"2026-08-07T15:29:53.395901Z","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":"2026-08-07T15:29:53.525641Z","title":"Semantically enhanced software traceability using deep learning techniques","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:53.525641Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:bf83daebce9186aab1954c211adfec768a6de48a27fc42cc40e7e24a29e44b6b","observation_id":"98a0457f-74a6-4d53-8b01-0664a7c25a49","resolution":{"observed_at":"2026-08-07T15:29:53.525641Z","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":"2026-08-07T15:29:53.660602Z","title":"Foundations for an expert system in domain-specific traceability","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:53.660602Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:d68c2a1cd40c2e07ac2587b3231ccbfe120661c528a6a0f893b66e3930badc56","observation_id":"a75755e0-3d28-4e6d-9c23-84ca5c44b8b9","resolution":{"observed_at":"2026-08-07T15:29:53.660602Z","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":"2026-08-07T15:29:53.747738Z","title":"Reconciling Manual and Automatic Refactoring","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:53.747738Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:f3415605a304250e458935241060c1b1999d7f68dd1ec3a5327c7bb639a557f4","observation_id":"4e85f9d2-aa44-449e-bc43-aa00dd4d5ced","resolution":{"observed_at":"2026-08-07T15:29:53.747738Z","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":"2026-08-07T15:29:53.796208Z","title":"Github, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:53.796208Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:b9d07985d3826e121d4a20edede00f1e284639017fa806326745ebf5992b9a68","observation_id":"1490c9a4-1fd2-40d4-baf2-de3084b8d7d7","resolution":{"observed_at":"2026-08-07T15:29:53.796208Z","resolver_source":null,"status":"parse_uncertain"},"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":"2026-08-07T15:29:53.835458Z","title":"Github copilot, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:53.835458Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:57c69f72e63049b339feeb85c1a9458b832e82844b8af51bf816dfae963bcb07","observation_id":"4cb58e7e-2447-414e-bb5e-0b9b7225a593","resolution":{"observed_at":"2026-08-07T15:29:53.835458Z","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":"2026-08-07T15:29:53.918549Z","title":"Gethers, R","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:53.918549Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:9b08b9b67e19cf2ecb37294ef3bd913ea1f77d162e8c0c674f880c3e5f5c4ac7","observation_id":"77eda7b8-a2b1-4907-9c21-ed9ec4ee8887","resolution":{"observed_at":"2026-08-07T15:29:53.918549Z","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":"2026-08-07T15:29:53.991635Z","title":"On integrating orthogonal information retrieval methods to improve traceability recovery","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":96,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:53.991635Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:a9fdbd5568beccdee319f57710d99cba98ed9168b4e79027b613b64213e6e964","observation_id":"140ba880-61ac-4f65-9fee-86d2b33ef7c1","resolution":{"observed_at":"2026-08-07T15:29:53.991635Z","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":"2026-08-07T15:29:54.049426Z","title":"Cold-start Software Analytics","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":97,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:54.049426Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:629608eef6e451be72c1f1d3581ff3bde046defb389ecd900ed3be33e00eab76","observation_id":"8292c0b0-ad3c-46e3-ad94-da80a9f87b69","resolution":{"observed_at":"2026-08-07T15:29:54.049426Z","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":"2026-08-07T15:29:54.147108Z","title":"Graphcode \\ bert \\ : Pre-training code representations with data flow","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":98,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:54.147108Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:763c0f3b1eff6e48f042b0a86c690879991ca38a002d0ab749a44769034d333c","observation_id":"af5e24e2-d852-47b3-81af-db26c43ba037","resolution":{"observed_at":"2026-08-07T15:29:54.147108Z","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":"2026-08-07T15:29:54.249600Z","title":"Traceability recovery between bug reports and test cases-a mozilla firefox case study","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":99,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:54.249600Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:e69a0ea15a0996d1f5c3fbf809ef3d7189f19efd7bb8638585d4f4db69b0e2ed","observation_id":"b6d078e8-7b63-4568-b285-434a87c572b0","resolution":{"observed_at":"2026-08-07T15:29:54.249600Z","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":"2026-08-07T15:29:54.304076Z","title":"Do automatic test generation tools generate flaky tests?, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering","version":1},"reference_index":100,"source":"arxiv_source","source_observed_at":"2026-08-07T15:29:54.304076Z"},"links":{"citing_paper":"/paper/2505.15023"},"observation_digest":"sha256:61c9bf6baaa753b91279e30da9a27eb647e1dab2776b6b31de4d2a1b61ab7f37","observation_id":"873f1a46-32b2-4463-8c66-696f98bbd4eb","resolution":{"observed_at":"2026-08-07T15:29:54.304076Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.15023","last_updated":"2025-05-21T02:13:11Z","latest_version":1,"primary_category":"cs.SE","snapshot_observed_at":"2026-08-13T19:14:29.211985Z","submitted_at":"2025-05-21T02:13:11Z","title":"Towards a Science of Causal Interpretability in Deep Learning for Software Engineering"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":1,"unresolved":97,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":300},"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 18 August 2026, this Paper Citation Record lists 100 of 300 outbound references and 0 inbound Pith citation observations for arXiv:2505.15023."}