{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YWDZMGT2Q2TEMCAPQ56ZSC6FZB","short_pith_number":"pith:YWDZMGT2","schema_version":"1.0","canonical_sha256":"c587961a7a86a646080f877d990bc5c856f43bfa1684c33317988298bca8b3e1","source":{"kind":"arxiv","id":"2309.00661","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Video Moment Retrieval from Frozen Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dezhao Luo, Hailin Jin, Jiabo Huang, Shaogang Gong, Yang Liu","submitted_at":"2023-09-01T13:06:50Z","abstract_excerpt":"Accurate video moment retrieval (VMR) requires universal visual-textual correlations that can handle unknown vocabulary and unseen scenes. However, the learned correlations are likely either biased when derived from a limited amount of moment-text data which is hard to scale up because of the prohibitive annotation cost (fully-supervised), or unreliable when only the video-text pairwise relationships are available without fine-grained temporal annotations (weakly-supervised). Recently, the vision-language models (VLM) demonstrate a new transfer learning paradigm to benefit different vision tas"},"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":"2309.00661","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-01T13:06:50Z","cross_cats_sorted":[],"title_canon_sha256":"65918bdb2f712a2372dab7378e3db1f2a0a42869f699e704874aa409329b01c2","abstract_canon_sha256":"0df4572b0097a869eee1ebbc1e30615caa72ac34c5cd3574931c0fbe092b12f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:03.555040Z","signature_b64":"mNASYlyzBiIPVEakMIPQMo+DpfgKX1RaT41qiDd/OhykL9iE4s2mDg0YYUjadXr9HRPX9RLGFQY6OT+gze0EDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c587961a7a86a646080f877d990bc5c856f43bfa1684c33317988298bca8b3e1","last_reissued_at":"2026-07-05T06:47:03.554583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:03.554583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Video Moment Retrieval from Frozen Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dezhao Luo, Hailin Jin, Jiabo Huang, Shaogang Gong, Yang Liu","submitted_at":"2023-09-01T13:06:50Z","abstract_excerpt":"Accurate video moment retrieval (VMR) requires universal visual-textual correlations that can handle unknown vocabulary and unseen scenes. However, the learned correlations are likely either biased when derived from a limited amount of moment-text data which is hard to scale up because of the prohibitive annotation cost (fully-supervised), or unreliable when only the video-text pairwise relationships are available without fine-grained temporal annotations (weakly-supervised). Recently, the vision-language models (VLM) demonstrate a new transfer learning paradigm to benefit different vision tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00661","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/2309.00661/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":"2309.00661","created_at":"2026-07-05T06:47:03.554641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.00661v1","created_at":"2026-07-05T06:47:03.554641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00661","created_at":"2026-07-05T06:47:03.554641+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWDZMGT2Q2TE","created_at":"2026-07-05T06:47:03.554641+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWDZMGT2Q2TEMCAP","created_at":"2026-07-05T06:47:03.554641+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWDZMGT2","created_at":"2026-07-05T06:47:03.554641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07972","citing_title":"Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YWDZMGT2Q2TEMCAPQ56ZSC6FZB","json":"https://pith.science/pith/YWDZMGT2Q2TEMCAPQ56ZSC6FZB.json","graph_json":"https://pith.science/api/pith-number/YWDZMGT2Q2TEMCAPQ56ZSC6FZB/graph.json","events_json":"https://pith.science/api/pith-number/YWDZMGT2Q2TEMCAPQ56ZSC6FZB/events.json","paper":"https://pith.science/paper/YWDZMGT2"},"agent_actions":{"view_html":"https://pith.science/pith/YWDZMGT2Q2TEMCAPQ56ZSC6FZB","download_json":"https://pith.science/pith/YWDZMGT2Q2TEMCAPQ56ZSC6FZB.json","view_paper":"https://pith.science/paper/YWDZMGT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.00661&json=true","fetch_graph":"https://pith.science/api/pith-number/YWDZMGT2Q2TEMCAPQ56ZSC6FZB/graph.json","fetch_events":"https://pith.science/api/pith-number/YWDZMGT2Q2TEMCAPQ56ZSC6FZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWDZMGT2Q2TEMCAPQ56ZSC6FZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWDZMGT2Q2TEMCAPQ56ZSC6FZB/action/storage_attestation","attest_author":"https://pith.science/pith/YWDZMGT2Q2TEMCAPQ56ZSC6FZB/action/author_attestation","sign_citation":"https://pith.science/pith/YWDZMGT2Q2TEMCAPQ56ZSC6FZB/action/citation_signature","submit_replication":"https://pith.science/pith/YWDZMGT2Q2TEMCAPQ56ZSC6FZB/action/replication_record"}},"created_at":"2026-07-05T06:47:03.554641+00:00","updated_at":"2026-07-05T06:47:03.554641+00:00"}