{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4DVCTW4GNIVTSO4QUOE4EBAZZU","short_pith_number":"pith:4DVCTW4G","schema_version":"1.0","canonical_sha256":"e0ea29db866a2b393b90a389c20419cd0c992e2139cd8cacbee86dbb6b9864d7","source":{"kind":"arxiv","id":"2501.07972","version":1},"attestation_state":"computed","paper":{"title":"Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Benxiang Zhai, Ming Li, Sidan Du, Wenxin Liang, Yang Li, Yifang Xu, Yunzhuo Sun","submitted_at":"2025-01-14T09:45:10Z","abstract_excerpt":"The target of video moment retrieval (VMR) is predicting temporal spans within a video that semantically match a given linguistic query. Existing VMR methods based on multimodal large language models (MLLMs) overly rely on expensive high-quality datasets and time-consuming fine-tuning. Although some recent studies introduce a zero-shot setting to avoid fine-tuning, they overlook inherent language bias in the query, leading to erroneous localization. To tackle the aforementioned challenges, this paper proposes Moment-GPT, a tuning-free pipeline for zero-shot VMR utilizing frozen MLLMs. Specific"},"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":"2501.07972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-01-14T09:45:10Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"038bd743c9876de434f754ad2c44e43fdf99aa1d263e267de921cf6a99fa6a93","abstract_canon_sha256":"9f6200e097277c33fbfbf19283f76cf142377157dfbcbf4c1cbfa053c587cc45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:53.219817Z","signature_b64":"4FoZ63/Pzfr4aYFl6/7wB4OM4tGjtNthD2dKleSTUaVMyoO8mydNnYm78HnI7OqLRzHowi9z4rFXhftfFn7rAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0ea29db866a2b393b90a389c20419cd0c992e2139cd8cacbee86dbb6b9864d7","last_reissued_at":"2026-07-05T10:00:53.219413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:53.219413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Benxiang Zhai, Ming Li, Sidan Du, Wenxin Liang, Yang Li, Yifang Xu, Yunzhuo Sun","submitted_at":"2025-01-14T09:45:10Z","abstract_excerpt":"The target of video moment retrieval (VMR) is predicting temporal spans within a video that semantically match a given linguistic query. Existing VMR methods based on multimodal large language models (MLLMs) overly rely on expensive high-quality datasets and time-consuming fine-tuning. Although some recent studies introduce a zero-shot setting to avoid fine-tuning, they overlook inherent language bias in the query, leading to erroneous localization. To tackle the aforementioned challenges, this paper proposes Moment-GPT, a tuning-free pipeline for zero-shot VMR utilizing frozen MLLMs. Specific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07972","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/2501.07972/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":"2501.07972","created_at":"2026-07-05T10:00:53.219469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07972v1","created_at":"2026-07-05T10:00:53.219469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07972","created_at":"2026-07-05T10:00:53.219469+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DVCTW4GNIVT","created_at":"2026-07-05T10:00:53.219469+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DVCTW4GNIVTSO4Q","created_at":"2026-07-05T10:00:53.219469+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DVCTW4G","created_at":"2026-07-05T10:00:53.219469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23198","citing_title":"StoryTR: Narrative-Centric Video Temporal Retrieval with Theory of Mind Reasoning","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4DVCTW4GNIVTSO4QUOE4EBAZZU","json":"https://pith.science/pith/4DVCTW4GNIVTSO4QUOE4EBAZZU.json","graph_json":"https://pith.science/api/pith-number/4DVCTW4GNIVTSO4QUOE4EBAZZU/graph.json","events_json":"https://pith.science/api/pith-number/4DVCTW4GNIVTSO4QUOE4EBAZZU/events.json","paper":"https://pith.science/paper/4DVCTW4G"},"agent_actions":{"view_html":"https://pith.science/pith/4DVCTW4GNIVTSO4QUOE4EBAZZU","download_json":"https://pith.science/pith/4DVCTW4GNIVTSO4QUOE4EBAZZU.json","view_paper":"https://pith.science/paper/4DVCTW4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07972&json=true","fetch_graph":"https://pith.science/api/pith-number/4DVCTW4GNIVTSO4QUOE4EBAZZU/graph.json","fetch_events":"https://pith.science/api/pith-number/4DVCTW4GNIVTSO4QUOE4EBAZZU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DVCTW4GNIVTSO4QUOE4EBAZZU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DVCTW4GNIVTSO4QUOE4EBAZZU/action/storage_attestation","attest_author":"https://pith.science/pith/4DVCTW4GNIVTSO4QUOE4EBAZZU/action/author_attestation","sign_citation":"https://pith.science/pith/4DVCTW4GNIVTSO4QUOE4EBAZZU/action/citation_signature","submit_replication":"https://pith.science/pith/4DVCTW4GNIVTSO4QUOE4EBAZZU/action/replication_record"}},"created_at":"2026-07-05T10:00:53.219469+00:00","updated_at":"2026-07-05T10:00:53.219469+00:00"}