{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MKJJNU27PS7KOIQIPUA53YZLR5","short_pith_number":"pith:MKJJNU27","schema_version":"1.0","canonical_sha256":"629296d35f7cbea722087d01dde32b8f55b366a2e15514bf0866b7d04187a771","source":{"kind":"arxiv","id":"2305.14582","version":1},"attestation_state":"computed","paper":{"title":"Interpretation of Time-Series Deep Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fan Yang, Ninghao Liu, Shushan Wu, Wenzhan Song, Yucheng Shi, Ziqi Zhao","submitted_at":"2023-05-23T23:43:26Z","abstract_excerpt":"Deep learning models developed for time-series associated tasks have become more widely researched nowadays. However, due to the unintuitive nature of time-series data, the interpretability problem -- where we understand what is under the hood of these models -- becomes crucial. The advancement of similar studies in computer vision has given rise to many post-hoc methods, which can also shed light on how to explain time-series models. In this paper, we present a wide range of post-hoc interpretation methods for time-series models based on backpropagation, perturbation, and approximation. We al"},"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":"2305.14582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T23:43:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c541ed5e4cbb9a038c434952370858e8d26ca47853ba69fae88343798a2f80c0","abstract_canon_sha256":"f83c5b024b43d1f9d144a7c42ae14a009656a60519bf6f19587cea0dd0afe2bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:25.268901Z","signature_b64":"fGs+K/lnkogCEeRlciSKXW68Zf+zb/MjMmwM/OnrlA0/jFxlZYUKMS3kwVP1VhmcWzD+R8NE3El59D9LmqqICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"629296d35f7cbea722087d01dde32b8f55b366a2e15514bf0866b7d04187a771","last_reissued_at":"2026-07-05T06:13:25.268465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:25.268465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretation of Time-Series Deep Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fan Yang, Ninghao Liu, Shushan Wu, Wenzhan Song, Yucheng Shi, Ziqi Zhao","submitted_at":"2023-05-23T23:43:26Z","abstract_excerpt":"Deep learning models developed for time-series associated tasks have become more widely researched nowadays. However, due to the unintuitive nature of time-series data, the interpretability problem -- where we understand what is under the hood of these models -- becomes crucial. The advancement of similar studies in computer vision has given rise to many post-hoc methods, which can also shed light on how to explain time-series models. In this paper, we present a wide range of post-hoc interpretation methods for time-series models based on backpropagation, perturbation, and approximation. We al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14582","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/2305.14582/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":"2305.14582","created_at":"2026-07-05T06:13:25.268522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14582v1","created_at":"2026-07-05T06:13:25.268522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14582","created_at":"2026-07-05T06:13:25.268522+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKJJNU27PS7K","created_at":"2026-07-05T06:13:25.268522+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKJJNU27PS7KOIQI","created_at":"2026-07-05T06:13:25.268522+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKJJNU27","created_at":"2026-07-05T06:13:25.268522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.23036","citing_title":"Delta-XAI: A Unified Framework for Explaining Prediction Changes in Online Time Series Monitoring","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MKJJNU27PS7KOIQIPUA53YZLR5","json":"https://pith.science/pith/MKJJNU27PS7KOIQIPUA53YZLR5.json","graph_json":"https://pith.science/api/pith-number/MKJJNU27PS7KOIQIPUA53YZLR5/graph.json","events_json":"https://pith.science/api/pith-number/MKJJNU27PS7KOIQIPUA53YZLR5/events.json","paper":"https://pith.science/paper/MKJJNU27"},"agent_actions":{"view_html":"https://pith.science/pith/MKJJNU27PS7KOIQIPUA53YZLR5","download_json":"https://pith.science/pith/MKJJNU27PS7KOIQIPUA53YZLR5.json","view_paper":"https://pith.science/paper/MKJJNU27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14582&json=true","fetch_graph":"https://pith.science/api/pith-number/MKJJNU27PS7KOIQIPUA53YZLR5/graph.json","fetch_events":"https://pith.science/api/pith-number/MKJJNU27PS7KOIQIPUA53YZLR5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKJJNU27PS7KOIQIPUA53YZLR5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKJJNU27PS7KOIQIPUA53YZLR5/action/storage_attestation","attest_author":"https://pith.science/pith/MKJJNU27PS7KOIQIPUA53YZLR5/action/author_attestation","sign_citation":"https://pith.science/pith/MKJJNU27PS7KOIQIPUA53YZLR5/action/citation_signature","submit_replication":"https://pith.science/pith/MKJJNU27PS7KOIQIPUA53YZLR5/action/replication_record"}},"created_at":"2026-07-05T06:13:25.268522+00:00","updated_at":"2026-07-05T06:13:25.268522+00:00"}