{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JJTY3BFVYZQG6BGDDGIGOOQGF5","short_pith_number":"pith:JJTY3BFV","schema_version":"1.0","canonical_sha256":"4a678d84b5c6606f04c31990673a062f64ffb776d2e614e74a46eb4c7fdb5f3b","source":{"kind":"arxiv","id":"2211.02178","version":1},"attestation_state":"computed","paper":{"title":"Zero-shot Video Moment Retrieval With Off-the-Shelf Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anuj Diwan, Puyuan Peng, Raymond J. Mooney","submitted_at":"2022-11-03T23:11:04Z","abstract_excerpt":"For the majority of the machine learning community, the expensive nature of collecting high-quality human-annotated data and the inability to efficiently finetune very large state-of-the-art pretrained models on limited compute are major bottlenecks for building models for new tasks. We propose a zero-shot simple approach for one such task, Video Moment Retrieval (VMR), that does not perform any additional finetuning and simply repurposes off-the-shelf models trained on other tasks. Our three-step approach consists of moment proposal, moment-query matching and postprocessing, all using only of"},"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":"2211.02178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-03T23:11:04Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"732706e5544ba4b1692702c5e48d4a7f0799fa7319e26a352065b1ba152ecf18","abstract_canon_sha256":"3518b131d5b538c17ac5712a3125832340b2ebfbd8bc146924d588cd3743d327"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:12.439491Z","signature_b64":"3bH4ul6VaNGyMB++uXD5jNX7ApBp4+SHVVGIbJYRrJLZGRkNkyEJUkXVdDJ0bj12MkBu9EO40MrIyTCuvMbeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a678d84b5c6606f04c31990673a062f64ffb776d2e614e74a46eb4c7fdb5f3b","last_reissued_at":"2026-07-05T05:13:12.439143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:12.439143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-shot Video Moment Retrieval With Off-the-Shelf Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anuj Diwan, Puyuan Peng, Raymond J. Mooney","submitted_at":"2022-11-03T23:11:04Z","abstract_excerpt":"For the majority of the machine learning community, the expensive nature of collecting high-quality human-annotated data and the inability to efficiently finetune very large state-of-the-art pretrained models on limited compute are major bottlenecks for building models for new tasks. We propose a zero-shot simple approach for one such task, Video Moment Retrieval (VMR), that does not perform any additional finetuning and simply repurposes off-the-shelf models trained on other tasks. Our three-step approach consists of moment proposal, moment-query matching and postprocessing, all using only of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02178","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/2211.02178/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":"2211.02178","created_at":"2026-07-05T05:13:12.439205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.02178v1","created_at":"2026-07-05T05:13:12.439205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02178","created_at":"2026-07-05T05:13:12.439205+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJTY3BFVYZQG","created_at":"2026-07-05T05:13:12.439205+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJTY3BFVYZQG6BGD","created_at":"2026-07-05T05:13:12.439205+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJTY3BFV","created_at":"2026-07-05T05:13:12.439205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJTY3BFVYZQG6BGDDGIGOOQGF5","json":"https://pith.science/pith/JJTY3BFVYZQG6BGDDGIGOOQGF5.json","graph_json":"https://pith.science/api/pith-number/JJTY3BFVYZQG6BGDDGIGOOQGF5/graph.json","events_json":"https://pith.science/api/pith-number/JJTY3BFVYZQG6BGDDGIGOOQGF5/events.json","paper":"https://pith.science/paper/JJTY3BFV"},"agent_actions":{"view_html":"https://pith.science/pith/JJTY3BFVYZQG6BGDDGIGOOQGF5","download_json":"https://pith.science/pith/JJTY3BFVYZQG6BGDDGIGOOQGF5.json","view_paper":"https://pith.science/paper/JJTY3BFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.02178&json=true","fetch_graph":"https://pith.science/api/pith-number/JJTY3BFVYZQG6BGDDGIGOOQGF5/graph.json","fetch_events":"https://pith.science/api/pith-number/JJTY3BFVYZQG6BGDDGIGOOQGF5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJTY3BFVYZQG6BGDDGIGOOQGF5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJTY3BFVYZQG6BGDDGIGOOQGF5/action/storage_attestation","attest_author":"https://pith.science/pith/JJTY3BFVYZQG6BGDDGIGOOQGF5/action/author_attestation","sign_citation":"https://pith.science/pith/JJTY3BFVYZQG6BGDDGIGOOQGF5/action/citation_signature","submit_replication":"https://pith.science/pith/JJTY3BFVYZQG6BGDDGIGOOQGF5/action/replication_record"}},"created_at":"2026-07-05T05:13:12.439205+00:00","updated_at":"2026-07-05T05:13:12.439205+00:00"}