{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4DVCTW4GNIVTSO4QUOE4EBAZZU","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":"9f6200e097277c33fbfbf19283f76cf142377157dfbcbf4c1cbfa053c587cc45","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-01-14T09:45:10Z","title_canon_sha256":"038bd743c9876de434f754ad2c44e43fdf99aa1d263e267de921cf6a99fa6a93"},"schema_version":"1.0","source":{"id":"2501.07972","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07972","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07972v1","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07972","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_12","alias_value":"4DVCTW4GNIVT","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_16","alias_value":"4DVCTW4GNIVTSO4Q","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_8","alias_value":"4DVCTW4G","created_at":"2026-07-05T10:00:53Z"}],"graph_snapshots":[{"event_id":"sha256:4d8e34793a1debc7055a2f059979d18a3ee0837c4fabb0019fd16574e3017395","target":"graph","created_at":"2026-07-05T10:00:53Z","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/2501.07972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Benxiang Zhai, Ming Li, Sidan Du, Wenxin Liang, Yang Li, Yifang Xu, Yunzhuo Sun","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-01-14T09:45:10Z","title":"Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07972","kind":"arxiv","version":1},"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":"sha256:7773067169de4463b6bc65237883ae47e3fa809904cba52f8f7ddf686e5adb60","target":"record","created_at":"2026-07-05T10:00:53Z","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":"9f6200e097277c33fbfbf19283f76cf142377157dfbcbf4c1cbfa053c587cc45","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-01-14T09:45:10Z","title_canon_sha256":"038bd743c9876de434f754ad2c44e43fdf99aa1d263e267de921cf6a99fa6a93"},"schema_version":"1.0","source":{"id":"2501.07972","kind":"arxiv","version":1}},"canonical_sha256":"e0ea29db866a2b393b90a389c20419cd0c992e2139cd8cacbee86dbb6b9864d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0ea29db866a2b393b90a389c20419cd0c992e2139cd8cacbee86dbb6b9864d7","first_computed_at":"2026-07-05T10:00:53.219413Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:53.219413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4FoZ63/Pzfr4aYFl6/7wB4OM4tGjtNthD2dKleSTUaVMyoO8mydNnYm78HnI7OqLRzHowi9z4rFXhftfFn7rAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:53.219817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07972","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7773067169de4463b6bc65237883ae47e3fa809904cba52f8f7ddf686e5adb60","sha256:4d8e34793a1debc7055a2f059979d18a3ee0837c4fabb0019fd16574e3017395"],"state_sha256":"525dc40c47879ac0bf540a60de3d2e7c4fe3327b207e3b5f33893dc292c2941e"}