{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ATAACLCFOELNJOHDJVWYV2TOMT","short_pith_number":"pith:ATAACLCF","schema_version":"1.0","canonical_sha256":"04c0012c457116d4b8e34d6d8aea6e64c836a135490b40e410942c112b706f75","source":{"kind":"arxiv","id":"2104.00950","version":1},"attestation_state":"computed","paper":{"title":"Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Filliat, Javier Del Ser, Natalia D\\'iaz-Rodr\\'iguez, Rapha\\\"el Puget, Rodolphe Gelin, Thomas Rojat","submitted_at":"2021-04-02T09:14:00Z","abstract_excerpt":"Most of state of the art methods applied on time series consist of deep learning methods that are too complex to be interpreted. This lack of interpretability is a major drawback, as several applications in the real world are critical tasks, such as the medical field or the autonomous driving field. The explainability of models applied on time series has not gather much attention compared to the computer vision or the natural language processing fields. In this paper, we present an overview of existing explainable AI (XAI) methods applied on time series and illustrate the type of explanations "},"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":"2104.00950","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-02T09:14:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"726cb3d1f6953c75f2fafe1316c4ed9d00b0b09cd5d7655529651677b71094fa","abstract_canon_sha256":"4f366807b2eb03357689959491fe03c157bbed35100cf649c9a75f8b7c692735"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:37.907640Z","signature_b64":"W2WUGNYXLkBL1+zFsGAPOIVHdgvBHFiXxBOM/8Hn1bhLFGxJNmjeUKI03cNZ6+gwnW8Eg30Ia/nJ/PI8wbVdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04c0012c457116d4b8e34d6d8aea6e64c836a135490b40e410942c112b706f75","last_reissued_at":"2026-07-05T02:28:37.907156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:37.907156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Filliat, Javier Del Ser, Natalia D\\'iaz-Rodr\\'iguez, Rapha\\\"el Puget, Rodolphe Gelin, Thomas Rojat","submitted_at":"2021-04-02T09:14:00Z","abstract_excerpt":"Most of state of the art methods applied on time series consist of deep learning methods that are too complex to be interpreted. This lack of interpretability is a major drawback, as several applications in the real world are critical tasks, such as the medical field or the autonomous driving field. The explainability of models applied on time series has not gather much attention compared to the computer vision or the natural language processing fields. In this paper, we present an overview of existing explainable AI (XAI) methods applied on time series and illustrate the type of explanations "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00950","kind":"arxiv","version":1},"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/2104.00950/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":"2104.00950","created_at":"2026-07-05T02:28:37.907209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.00950v1","created_at":"2026-07-05T02:28:37.907209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00950","created_at":"2026-07-05T02:28:37.907209+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATAACLCFOELN","created_at":"2026-07-05T02:28:37.907209+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATAACLCFOELNJOHD","created_at":"2026-07-05T02:28:37.907209+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATAACLCF","created_at":"2026-07-05T02:28:37.907209+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18849","citing_title":"INSIGHTS: Demonstration-Based Summaries of Time Series Predictors","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12168","citing_title":"On What We Can Learn from Low-Resolution Data","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08625","citing_title":"Reasoning-Aware Training for Time Series Forecasting","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05685","citing_title":"Temporal Functional Circuits: From Spline Plots to Faithful Explanations in KAN Forecasting","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06943","citing_title":"ProtoSSL: Interpretable Prototype Learning from Unlabeled Time-Series Data","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05364","citing_title":"TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ATAACLCFOELNJOHDJVWYV2TOMT","json":"https://pith.science/pith/ATAACLCFOELNJOHDJVWYV2TOMT.json","graph_json":"https://pith.science/api/pith-number/ATAACLCFOELNJOHDJVWYV2TOMT/graph.json","events_json":"https://pith.science/api/pith-number/ATAACLCFOELNJOHDJVWYV2TOMT/events.json","paper":"https://pith.science/paper/ATAACLCF"},"agent_actions":{"view_html":"https://pith.science/pith/ATAACLCFOELNJOHDJVWYV2TOMT","download_json":"https://pith.science/pith/ATAACLCFOELNJOHDJVWYV2TOMT.json","view_paper":"https://pith.science/paper/ATAACLCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.00950&json=true","fetch_graph":"https://pith.science/api/pith-number/ATAACLCFOELNJOHDJVWYV2TOMT/graph.json","fetch_events":"https://pith.science/api/pith-number/ATAACLCFOELNJOHDJVWYV2TOMT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATAACLCFOELNJOHDJVWYV2TOMT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATAACLCFOELNJOHDJVWYV2TOMT/action/storage_attestation","attest_author":"https://pith.science/pith/ATAACLCFOELNJOHDJVWYV2TOMT/action/author_attestation","sign_citation":"https://pith.science/pith/ATAACLCFOELNJOHDJVWYV2TOMT/action/citation_signature","submit_replication":"https://pith.science/pith/ATAACLCFOELNJOHDJVWYV2TOMT/action/replication_record"}},"created_at":"2026-07-05T02:28:37.907209+00:00","updated_at":"2026-07-05T02:28:37.907209+00:00"}