{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VY7643PBRID3NW2ZVODTFH5MCG","short_pith_number":"pith:VY7643PB","schema_version":"1.0","canonical_sha256":"ae3fee6de18a07b6db59ab87329fac119467c537ce7714096107c53277a0dc6e","source":{"kind":"arxiv","id":"2303.12316","version":1},"attestation_state":"computed","paper":{"title":"TsSHAP: Robust model agnostic feature-based explainability for time series forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arindam Jati, Giridhar Ganapavarapu, Kanthi Sarpatwar, Nupur Aggarwal, Roman Vaculin, Sumanta Mukherjee, Vikas C. Raykar","submitted_at":"2023-03-22T05:14:36Z","abstract_excerpt":"A trustworthy machine learning model should be accurate as well as explainable. Understanding why a model makes a certain decision defines the notion of explainability. While various flavors of explainability have been well-studied in supervised learning paradigms like classification and regression, literature on explainability for time series forecasting is relatively scarce.\n  In this paper, we propose a feature-based explainability algorithm, TsSHAP, that can explain the forecast of any black-box forecasting model. The method is agnostic of the forecasting model and can provide 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":"2303.12316","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-22T05:14:36Z","cross_cats_sorted":[],"title_canon_sha256":"76e5a379479899e5835cc8bdfb06aec0505909e1b6001d63175f332d66a4ea08","abstract_canon_sha256":"d48d3d4635a730f6dc49c96c844940dfd8337f906fb351faedd7df4d4ad65986"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:39.808623Z","signature_b64":"Z2W0LqFpoWCu4C7QDhTdYiaUsj5A0ZjKCv6LUr1Tt4+E4eFLGy/O7KOv8U81zLsU+Sb50QvBEaDWXPc0HLr+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae3fee6de18a07b6db59ab87329fac119467c537ce7714096107c53277a0dc6e","last_reissued_at":"2026-07-05T05:53:39.808105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:39.808105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TsSHAP: Robust model agnostic feature-based explainability for time series forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arindam Jati, Giridhar Ganapavarapu, Kanthi Sarpatwar, Nupur Aggarwal, Roman Vaculin, Sumanta Mukherjee, Vikas C. Raykar","submitted_at":"2023-03-22T05:14:36Z","abstract_excerpt":"A trustworthy machine learning model should be accurate as well as explainable. Understanding why a model makes a certain decision defines the notion of explainability. While various flavors of explainability have been well-studied in supervised learning paradigms like classification and regression, literature on explainability for time series forecasting is relatively scarce.\n  In this paper, we propose a feature-based explainability algorithm, TsSHAP, that can explain the forecast of any black-box forecasting model. The method is agnostic of the forecasting model and can provide explanations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12316","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/2303.12316/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":"2303.12316","created_at":"2026-07-05T05:53:39.808168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.12316v1","created_at":"2026-07-05T05:53:39.808168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12316","created_at":"2026-07-05T05:53:39.808168+00:00"},{"alias_kind":"pith_short_12","alias_value":"VY7643PBRID3","created_at":"2026-07-05T05:53:39.808168+00:00"},{"alias_kind":"pith_short_16","alias_value":"VY7643PBRID3NW2Z","created_at":"2026-07-05T05:53:39.808168+00:00"},{"alias_kind":"pith_short_8","alias_value":"VY7643PB","created_at":"2026-07-05T05:53:39.808168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18849","citing_title":"INSIGHTS: Demonstration-Based Summaries of Time Series Predictors","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VY7643PBRID3NW2ZVODTFH5MCG","json":"https://pith.science/pith/VY7643PBRID3NW2ZVODTFH5MCG.json","graph_json":"https://pith.science/api/pith-number/VY7643PBRID3NW2ZVODTFH5MCG/graph.json","events_json":"https://pith.science/api/pith-number/VY7643PBRID3NW2ZVODTFH5MCG/events.json","paper":"https://pith.science/paper/VY7643PB"},"agent_actions":{"view_html":"https://pith.science/pith/VY7643PBRID3NW2ZVODTFH5MCG","download_json":"https://pith.science/pith/VY7643PBRID3NW2ZVODTFH5MCG.json","view_paper":"https://pith.science/paper/VY7643PB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.12316&json=true","fetch_graph":"https://pith.science/api/pith-number/VY7643PBRID3NW2ZVODTFH5MCG/graph.json","fetch_events":"https://pith.science/api/pith-number/VY7643PBRID3NW2ZVODTFH5MCG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VY7643PBRID3NW2ZVODTFH5MCG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VY7643PBRID3NW2ZVODTFH5MCG/action/storage_attestation","attest_author":"https://pith.science/pith/VY7643PBRID3NW2ZVODTFH5MCG/action/author_attestation","sign_citation":"https://pith.science/pith/VY7643PBRID3NW2ZVODTFH5MCG/action/citation_signature","submit_replication":"https://pith.science/pith/VY7643PBRID3NW2ZVODTFH5MCG/action/replication_record"}},"created_at":"2026-07-05T05:53:39.808168+00:00","updated_at":"2026-07-05T05:53:39.808168+00:00"}