{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LH3P4JH54RCF4Z5IJ3RKIMBWRI","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":"dfd71c15ded03fbe18ac91c220d05d7ccfe20dc5ba79208434c755830d1e164f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T14:20:30Z","title_canon_sha256":"cd88c5e8e5829015660246e2e348e44901591b98ff7208df48fce72681379fb8"},"schema_version":"1.0","source":{"id":"2404.12216","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12216","created_at":"2026-07-05T08:10:27Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12216v2","created_at":"2026-07-05T08:10:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12216","created_at":"2026-07-05T08:10:27Z"},{"alias_kind":"pith_short_12","alias_value":"LH3P4JH54RCF","created_at":"2026-07-05T08:10:27Z"},{"alias_kind":"pith_short_16","alias_value":"LH3P4JH54RCF4Z5I","created_at":"2026-07-05T08:10:27Z"},{"alias_kind":"pith_short_8","alias_value":"LH3P4JH5","created_at":"2026-07-05T08:10:27Z"}],"graph_snapshots":[{"event_id":"sha256:e062e3f478dcc3ecc124b327aaf467eead1d4264e3092c203f3e49de13ca7ac2","target":"graph","created_at":"2026-07-05T08:10:27Z","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/2404.12216/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-video retrieval aims to find the most relevant cross-modal samples for a given query. Recent methods focus on modeling the whole spatial-temporal relations. However, since video clips contain more diverse content than captions, the model aligning these asymmetric video-text pairs has a high risk of retrieving many false positive results. In this paper, we propose Probabilistic Token Aggregation (ProTA) to handle cross-modal interaction with content asymmetry. Specifically, we propose dual partial-related aggregation to disentangle and re-aggregate token representations in both low-dimensi","authors_text":"Chao Ban, Han Fang, Hao Sun, Lanxiang Zhou, Xianghao Zang, Yongxiang Li, Zerun Feng, Zhongjiang He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T14:20:30Z","title":"ProTA: Probabilistic Token Aggregation for Text-Video Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12216","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:f7fc1d9d39586e780e50e0c38bad1ff21ca2bea4143d607692d2d990b5400070","target":"record","created_at":"2026-07-05T08:10:27Z","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":"dfd71c15ded03fbe18ac91c220d05d7ccfe20dc5ba79208434c755830d1e164f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T14:20:30Z","title_canon_sha256":"cd88c5e8e5829015660246e2e348e44901591b98ff7208df48fce72681379fb8"},"schema_version":"1.0","source":{"id":"2404.12216","kind":"arxiv","version":2}},"canonical_sha256":"59f6fe24fde4445e67a84ee2a430368a17305432ffa55e0e20004a82299f3a24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59f6fe24fde4445e67a84ee2a430368a17305432ffa55e0e20004a82299f3a24","first_computed_at":"2026-07-05T08:10:27.096124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:27.096124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"78q+8RUiLfTzyxuxyfk29flibEuXW0XOvE/3q/h0UdXTddXtAyP/fmsu8grs3pnCLLzGy+8yHEoyMk+OGHgjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:27.096627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.12216","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7fc1d9d39586e780e50e0c38bad1ff21ca2bea4143d607692d2d990b5400070","sha256:e062e3f478dcc3ecc124b327aaf467eead1d4264e3092c203f3e49de13ca7ac2"],"state_sha256":"89fbf65c4e00e915037b065d1f781cc2176c2ab878dbcc05ccbc7ab2bdd206c2"}