{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GZZ7URUPCMU5OLEDIARGVCDLD2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"df86fe26d9a15c1b7309bbfbfd95ff35b484a28a950f4bce283224f78f4cf37d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T15:03:59Z","title_canon_sha256":"1d815796b5a726410821790967ec57dd708b3a13c3095abe9ea730c637a72047"},"schema_version":"1.0","source":{"id":"2505.23524","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23524","created_at":"2026-07-05T11:16:08Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23524v2","created_at":"2026-07-05T11:16:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23524","created_at":"2026-07-05T11:16:08Z"},{"alias_kind":"pith_short_12","alias_value":"GZZ7URUPCMU5","created_at":"2026-07-05T11:16:08Z"},{"alias_kind":"pith_short_16","alias_value":"GZZ7URUPCMU5OLED","created_at":"2026-07-05T11:16:08Z"},{"alias_kind":"pith_short_8","alias_value":"GZZ7URUP","created_at":"2026-07-05T11:16:08Z"}],"graph_snapshots":[{"event_id":"sha256:59763b3dfe8916111c4dba0ec4b3e51ae7557c92953bbe89003357f83b786cb9","target":"graph","created_at":"2026-07-05T11:16:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.23524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Temporal Action Localization (TAL) has garnered significant attention in information retrieval. Existing supervised or weakly supervised methods heavily rely on labeled temporal boundaries and action categories, which are labor-intensive and time-consuming. Consequently, unsupervised temporal action localization (UTAL) has gained popularity. However, current methods face two main challenges: 1) Classification pre-trained features overly focus on highly discriminative regions; 2) Solely relying on visual modality information makes it difficult to determine contextual boundaries. To address thes","authors_text":"Chun Yuan, Dan Jiang, Ke Zhang, Quan Zhang, Rui Xia","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T15:03:59Z","title":"CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23524","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ef62a806d117a9ffc8fea24bc05278e110081edbb763a2fb33fc635b37cf6a0f","target":"record","created_at":"2026-07-05T11:16:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"df86fe26d9a15c1b7309bbfbfd95ff35b484a28a950f4bce283224f78f4cf37d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T15:03:59Z","title_canon_sha256":"1d815796b5a726410821790967ec57dd708b3a13c3095abe9ea730c637a72047"},"schema_version":"1.0","source":{"id":"2505.23524","kind":"arxiv","version":2}},"canonical_sha256":"3673fa468f1329d72c8340226a886b1eb4a25fdde53da6a91b88c462ec41e40f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3673fa468f1329d72c8340226a886b1eb4a25fdde53da6a91b88c462ec41e40f","first_computed_at":"2026-07-05T11:16:08.831551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:08.831551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2LZQhg5t7qxU4NcxZUaBLx92c+hSVL3cA05NAvOQfaA+yhAlO+FNjpUS6F5kRa4HreVTS3TIBsdX/XZiuWczCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:08.832097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23524","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef62a806d117a9ffc8fea24bc05278e110081edbb763a2fb33fc635b37cf6a0f","sha256:59763b3dfe8916111c4dba0ec4b3e51ae7557c92953bbe89003357f83b786cb9"],"state_sha256":"9ac5ddb11af6f7f9f7561abe7e91f35c5e9a6e79419dda927c9438fb9a0c2b74"}