{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LRDIAXDSFHX5NDJQGG7NWCYA6P","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":"016363b3bfce7dc3ae3b8a74677f581cee312b554e169558054ca70db22bc3fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-21T08:43:51Z","title_canon_sha256":"9d5ba09834711165edbcc376c6cf88bcf5e158cc76ad109b7241deb391453537"},"schema_version":"1.0","source":{"id":"2207.10362","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.10362","created_at":"2026-07-05T04:42:24Z"},{"alias_kind":"arxiv_version","alias_value":"2207.10362v1","created_at":"2026-07-05T04:42:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10362","created_at":"2026-07-05T04:42:24Z"},{"alias_kind":"pith_short_12","alias_value":"LRDIAXDSFHX5","created_at":"2026-07-05T04:42:24Z"},{"alias_kind":"pith_short_16","alias_value":"LRDIAXDSFHX5NDJQ","created_at":"2026-07-05T04:42:24Z"},{"alias_kind":"pith_short_8","alias_value":"LRDIAXDS","created_at":"2026-07-05T04:42:24Z"}],"graph_snapshots":[{"event_id":"sha256:cbf7e7ec6d8091dd6f28289cdf4bd311b7ec9b3c651a10a5c619b577981413d6","target":"graph","created_at":"2026-07-05T04:42:24Z","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/2207.10362/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-Text Pre-training (VTP) aims to learn transferable representations for various downstream tasks from large-scale web videos. To date, almost all existing VTP methods are limited to retrieval-based downstream tasks, e.g., video retrieval, whereas their transfer potentials on localization-based tasks, e.g., temporal grounding, are under-explored. In this paper, we experimentally analyze and demonstrate the incompatibility of current VTP methods with localization tasks, and propose a novel Localization-oriented Video-Text Pre-training framework, dubbed as LocVTP. Specifically, we perform th","authors_text":"Can Zhang, Jue Wang, Junwu Weng, Meng Cao, Tianyu Yang, Yuexian Zou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-21T08:43:51Z","title":"LocVTP: Video-Text Pre-training for Temporal Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10362","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:ad62c17ea904a87dd719da77fd936dfb3cca4aa933beed47d8c62f60333b1324","target":"record","created_at":"2026-07-05T04:42:24Z","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":"016363b3bfce7dc3ae3b8a74677f581cee312b554e169558054ca70db22bc3fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-21T08:43:51Z","title_canon_sha256":"9d5ba09834711165edbcc376c6cf88bcf5e158cc76ad109b7241deb391453537"},"schema_version":"1.0","source":{"id":"2207.10362","kind":"arxiv","version":1}},"canonical_sha256":"5c46805c7229efd68d3031bedb0b00f3d376bd6307e198fbabcafac672af4d0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c46805c7229efd68d3031bedb0b00f3d376bd6307e198fbabcafac672af4d0a","first_computed_at":"2026-07-05T04:42:24.309852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:24.309852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kFduTVEF3T2+bBVKvvSxGvMp2sXD9US2mO3+cdbja5hKSiPBEofQylxH7MOnFR/u0hOdRxTMZu+yR3ZJfYPCBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:24.310376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.10362","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad62c17ea904a87dd719da77fd936dfb3cca4aa933beed47d8c62f60333b1324","sha256:cbf7e7ec6d8091dd6f28289cdf4bd311b7ec9b3c651a10a5c619b577981413d6"],"state_sha256":"8478b7711c018250c4675304101e217dd8a72b218ecb0c4a9ad5ee853f25eaa7"}