{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KNPZRAXJ4L5SUDK7GM3KBW62CD","short_pith_number":"pith:KNPZRAXJ","schema_version":"1.0","canonical_sha256":"535f9882e9e2fb2a0d5f3336a0dbda10f790e11603c30e9ff9fa775d5ecfed67","source":{"kind":"arxiv","id":"2504.13460","version":6},"attestation_state":"computed","paper":{"title":"Chain-of-Evidence Multimodal Reasoning for Few-shot Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"HongWei Ji, Huadong Ma, Mengshi Qi, Wulian Yun, Xianlin Zhang","submitted_at":"2025-04-18T04:35:35Z","abstract_excerpt":"Traditional temporal action localization (TAL) methods rely on large amounts of detailed annotated data, whereas few-shot TAL reduces this dependence by using only a few training samples to identify unseen action categories. However, existing few-shot TAL methods typically focus solely on video-level information, neglecting textual information, which can provide valuable semantic support for the action localization task. To address these issues, in this work, we propose a new few-shot temporal action localization method by Chain-of-Evidence multimodal reasoning to improve localization performa"},"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":"2504.13460","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-18T04:35:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"584a3a77f236b7dfcee1cac9b3fc52f7d4938d03a63f6b852f8879320508f276","abstract_canon_sha256":"c4cff33def1d4e5327951c12dec608a0dc983120108542150375175e46ad77ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-18T00:11:46.638915Z","signature_b64":"wD2uVcF1FljslgGsAQV8y4BopQcF54E4wHQS/cSH9Q6HEsIpC6+p0r6/urU2PBtifOSGXwtIeglAkGDuBi5fAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"535f9882e9e2fb2a0d5f3336a0dbda10f790e11603c30e9ff9fa775d5ecfed67","last_reissued_at":"2026-08-18T00:11:46.636741Z","signature_status":"signed_v1","first_computed_at":"2026-08-18T00:11:46.636741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chain-of-Evidence Multimodal Reasoning for Few-shot Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"HongWei Ji, Huadong Ma, Mengshi Qi, Wulian Yun, Xianlin Zhang","submitted_at":"2025-04-18T04:35:35Z","abstract_excerpt":"Traditional temporal action localization (TAL) methods rely on large amounts of detailed annotated data, whereas few-shot TAL reduces this dependence by using only a few training samples to identify unseen action categories. However, existing few-shot TAL methods typically focus solely on video-level information, neglecting textual information, which can provide valuable semantic support for the action localization task. To address these issues, in this work, we propose a new few-shot temporal action localization method by Chain-of-Evidence multimodal reasoning to improve localization performa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13460","kind":"arxiv","version":6},"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/2504.13460/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":"2504.13460","created_at":"2026-08-18T00:11:46.640120+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13460v6","created_at":"2026-08-18T00:11:46.640120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13460","created_at":"2026-08-18T00:11:46.640120+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNPZRAXJ4L5S","created_at":"2026-08-18T00:11:46.640120+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNPZRAXJ4L5SUDK7","created_at":"2026-08-18T00:11:46.640120+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNPZRAXJ","created_at":"2026-08-18T00:11:46.640120+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17482","citing_title":"LTLZinc: a Benchmarking Framework for Continual Learning and Neuro-Symbolic Temporal Reasoning","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNPZRAXJ4L5SUDK7GM3KBW62CD","json":"https://pith.science/pith/KNPZRAXJ4L5SUDK7GM3KBW62CD.json","graph_json":"https://pith.science/api/pith-number/KNPZRAXJ4L5SUDK7GM3KBW62CD/graph.json","events_json":"https://pith.science/api/pith-number/KNPZRAXJ4L5SUDK7GM3KBW62CD/events.json","paper":"https://pith.science/paper/KNPZRAXJ"},"agent_actions":{"view_html":"https://pith.science/pith/KNPZRAXJ4L5SUDK7GM3KBW62CD","download_json":"https://pith.science/pith/KNPZRAXJ4L5SUDK7GM3KBW62CD.json","view_paper":"https://pith.science/paper/KNPZRAXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13460&json=true","fetch_graph":"https://pith.science/api/pith-number/KNPZRAXJ4L5SUDK7GM3KBW62CD/graph.json","fetch_events":"https://pith.science/api/pith-number/KNPZRAXJ4L5SUDK7GM3KBW62CD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNPZRAXJ4L5SUDK7GM3KBW62CD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNPZRAXJ4L5SUDK7GM3KBW62CD/action/storage_attestation","attest_author":"https://pith.science/pith/KNPZRAXJ4L5SUDK7GM3KBW62CD/action/author_attestation","sign_citation":"https://pith.science/pith/KNPZRAXJ4L5SUDK7GM3KBW62CD/action/citation_signature","submit_replication":"https://pith.science/pith/KNPZRAXJ4L5SUDK7GM3KBW62CD/action/replication_record"}},"created_at":"2026-08-18T00:11:46.640120+00:00","updated_at":"2026-08-18T00:11:46.640120+00:00"}