{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MMKYD4URROJ7TA2NFKMI4PAQWM","short_pith_number":"pith:MMKYD4UR","schema_version":"1.0","canonical_sha256":"631581f2918b93f9834d2a988e3c10b30103f4894834122373eec5b5d69e2c93","source":{"kind":"arxiv","id":"2306.02968","version":2},"attestation_state":"computed","paper":{"title":"Time Interpret: a Unified Model Interpretability Library for Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Joseph Enguehard","submitted_at":"2023-06-05T15:31:18Z","abstract_excerpt":"We introduce $\\texttt{time_interpret}$, a library designed as an extension of Captum, with a specific focus on temporal data. As such, this library implements several feature attribution methods that can be used to explain predictions made by any Pytorch model. $\\texttt{time_interpret}$ also provides several synthetic and real world time series datasets, various PyTorch models, as well as a set of methods to evaluate feature attributions. Moreover, while being primarily developed to explain predictions based on temporal data, some of its components have a different application, including for i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.02968","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-05T15:31:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c1f93b6198fdab0f39e53a4e5587c98f6fe7709d1eb84788615cba18fcafc9d1","abstract_canon_sha256":"97e794ee5e9edf19e7551eb3d01bf1553aa01628ed249fa804314cf23dc86c18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:53.458622Z","signature_b64":"RmgKMFzji8S0HcfY7bzhvgc6AvSo/s95m+tgJeywfZrOuJ1X8uRfh/z+mtYKWv4lZVDJIcZqVRSfyLFgq5pwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"631581f2918b93f9834d2a988e3c10b30103f4894834122373eec5b5d69e2c93","last_reissued_at":"2026-07-05T06:17:53.458136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:53.458136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time Interpret: a Unified Model Interpretability Library for Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Joseph Enguehard","submitted_at":"2023-06-05T15:31:18Z","abstract_excerpt":"We introduce $\\texttt{time_interpret}$, a library designed as an extension of Captum, with a specific focus on temporal data. As such, this library implements several feature attribution methods that can be used to explain predictions made by any Pytorch model. $\\texttt{time_interpret}$ also provides several synthetic and real world time series datasets, various PyTorch models, as well as a set of methods to evaluate feature attributions. Moreover, while being primarily developed to explain predictions based on temporal data, some of its components have a different application, including for i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02968","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.02968/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.02968","created_at":"2026-07-05T06:17:53.458194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.02968v2","created_at":"2026-07-05T06:17:53.458194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02968","created_at":"2026-07-05T06:17:53.458194+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMKYD4URROJ7","created_at":"2026-07-05T06:17:53.458194+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMKYD4URROJ7TA2N","created_at":"2026-07-05T06:17:53.458194+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMKYD4UR","created_at":"2026-07-05T06:17:53.458194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.00655","citing_title":"Interpretability-Guided Bi-objective Optimization: Aligning Accuracy and Explainability","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MMKYD4URROJ7TA2NFKMI4PAQWM","json":"https://pith.science/pith/MMKYD4URROJ7TA2NFKMI4PAQWM.json","graph_json":"https://pith.science/api/pith-number/MMKYD4URROJ7TA2NFKMI4PAQWM/graph.json","events_json":"https://pith.science/api/pith-number/MMKYD4URROJ7TA2NFKMI4PAQWM/events.json","paper":"https://pith.science/paper/MMKYD4UR"},"agent_actions":{"view_html":"https://pith.science/pith/MMKYD4URROJ7TA2NFKMI4PAQWM","download_json":"https://pith.science/pith/MMKYD4URROJ7TA2NFKMI4PAQWM.json","view_paper":"https://pith.science/paper/MMKYD4UR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.02968&json=true","fetch_graph":"https://pith.science/api/pith-number/MMKYD4URROJ7TA2NFKMI4PAQWM/graph.json","fetch_events":"https://pith.science/api/pith-number/MMKYD4URROJ7TA2NFKMI4PAQWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMKYD4URROJ7TA2NFKMI4PAQWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMKYD4URROJ7TA2NFKMI4PAQWM/action/storage_attestation","attest_author":"https://pith.science/pith/MMKYD4URROJ7TA2NFKMI4PAQWM/action/author_attestation","sign_citation":"https://pith.science/pith/MMKYD4URROJ7TA2NFKMI4PAQWM/action/citation_signature","submit_replication":"https://pith.science/pith/MMKYD4URROJ7TA2NFKMI4PAQWM/action/replication_record"}},"created_at":"2026-07-05T06:17:53.458194+00:00","updated_at":"2026-07-05T06:17:53.458194+00:00"}