{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZSTGOBZWMS6EMHS3EYX55GKGPJ","short_pith_number":"pith:ZSTGOBZW","schema_version":"1.0","canonical_sha256":"cca667073664bc461e5b262fde99467a525ac16777c3e44baf5c5cfa92294228","source":{"kind":"arxiv","id":"2506.05035","version":1},"attestation_state":"computed","paper":{"title":"TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changhun Kim, Eunho Yang, Hyeongwon Jang","submitted_at":"2025-06-05T13:40:40Z","abstract_excerpt":"Recent explainable artificial intelligence (XAI) methods for time series primarily estimate point-wise attribution magnitudes, while overlooking the directional impact on predictions, leading to suboptimal identification of significant points. Our analysis shows that conventional Integrated Gradients (IG) effectively capture critical points with both positive and negative impacts on predictions. However, current evaluation metrics fail to assess this capability, as they inadvertently cancel out opposing feature contributions. To address this limitation, we propose novel evaluation metrics-Cumu"},"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":"2506.05035","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T13:40:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"72901dc2bae48648147c112649acae7dda4db6a0d2ade7c073a31d029d4a7109","abstract_canon_sha256":"84a533e8cce54375775f2252f83d202ea6693ae42345d1cc4824929a609daa07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:41.379291Z","signature_b64":"FKwwq6kzeqd/l3VAGXeQWDx6iWl+w8R6vIS412KHntiihz9wTlqNIEnupNTh2Z7k32PFkUElX0FVSXqkphcsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cca667073664bc461e5b262fde99467a525ac16777c3e44baf5c5cfa92294228","last_reissued_at":"2026-07-05T11:16:41.378812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:41.378812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changhun Kim, Eunho Yang, Hyeongwon Jang","submitted_at":"2025-06-05T13:40:40Z","abstract_excerpt":"Recent explainable artificial intelligence (XAI) methods for time series primarily estimate point-wise attribution magnitudes, while overlooking the directional impact on predictions, leading to suboptimal identification of significant points. Our analysis shows that conventional Integrated Gradients (IG) effectively capture critical points with both positive and negative impacts on predictions. However, current evaluation metrics fail to assess this capability, as they inadvertently cancel out opposing feature contributions. To address this limitation, we propose novel evaluation metrics-Cumu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05035","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/2506.05035/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":"2506.05035","created_at":"2026-07-05T11:16:41.378880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05035v1","created_at":"2026-07-05T11:16:41.378880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05035","created_at":"2026-07-05T11:16:41.378880+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSTGOBZWMS6E","created_at":"2026-07-05T11:16:41.378880+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSTGOBZWMS6EMHS3","created_at":"2026-07-05T11:16:41.378880+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSTGOBZW","created_at":"2026-07-05T11:16:41.378880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSTGOBZWMS6EMHS3EYX55GKGPJ","json":"https://pith.science/pith/ZSTGOBZWMS6EMHS3EYX55GKGPJ.json","graph_json":"https://pith.science/api/pith-number/ZSTGOBZWMS6EMHS3EYX55GKGPJ/graph.json","events_json":"https://pith.science/api/pith-number/ZSTGOBZWMS6EMHS3EYX55GKGPJ/events.json","paper":"https://pith.science/paper/ZSTGOBZW"},"agent_actions":{"view_html":"https://pith.science/pith/ZSTGOBZWMS6EMHS3EYX55GKGPJ","download_json":"https://pith.science/pith/ZSTGOBZWMS6EMHS3EYX55GKGPJ.json","view_paper":"https://pith.science/paper/ZSTGOBZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05035&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSTGOBZWMS6EMHS3EYX55GKGPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSTGOBZWMS6EMHS3EYX55GKGPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSTGOBZWMS6EMHS3EYX55GKGPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSTGOBZWMS6EMHS3EYX55GKGPJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZSTGOBZWMS6EMHS3EYX55GKGPJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZSTGOBZWMS6EMHS3EYX55GKGPJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZSTGOBZWMS6EMHS3EYX55GKGPJ/action/replication_record"}},"created_at":"2026-07-05T11:16:41.378880+00:00","updated_at":"2026-07-05T11:16:41.378880+00:00"}