{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5FKOORJONT7DU4IXZH3SSE56PL","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":"d50b23f3775b99ba3866213be94bbd639c6a143311d726244bc596f1ea3f8c91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-31T13:53:37Z","title_canon_sha256":"d0dda2143575ae2e47aa54ab5937aa8788b1b1b68c32e3b1ae88b2b69be34fd5"},"schema_version":"1.0","source":{"id":"2401.00901","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00901","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00901v2","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00901","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"5FKOORJONT7D","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"5FKOORJONT7DU4IX","created_at":"2026-07-05T08:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"5FKOORJO","created_at":"2026-07-05T08:02:23Z"}],"graph_snapshots":[{"event_id":"sha256:b704e0f91d131162c99e6b2aaf9bf8b74a035f843deb3b2dac1564596670f2c7","target":"graph","created_at":"2026-07-05T08:02:23Z","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/2401.00901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video grounding aims to localize a spatio-temporal section in a video corresponding to an input text query. This paper addresses a critical limitation in current video grounding methodologies by introducing an Open-Vocabulary Spatio-Temporal Video Grounding task. Unlike prevalent closed-set approaches that struggle with open-vocabulary scenarios due to limited training data and predefined vocabularies, our model leverages pre-trained representations from foundational spatial grounding models. This empowers it to effectively bridge the semantic gap between natural language and diverse visual co","authors_text":"Fahad Shahbaz Khan, Ming-Hsuan Yang, Muzammal Naseer, Salman Khan, Syed Talal Wasim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-31T13:53:37Z","title":"Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00901","kind":"arxiv","version":2},"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:a3ac925647cc10fed794123abb2ca635c0460bde10c6ea5a44e9da6fe6691413","target":"record","created_at":"2026-07-05T08:02:23Z","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":"d50b23f3775b99ba3866213be94bbd639c6a143311d726244bc596f1ea3f8c91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-31T13:53:37Z","title_canon_sha256":"d0dda2143575ae2e47aa54ab5937aa8788b1b1b68c32e3b1ae88b2b69be34fd5"},"schema_version":"1.0","source":{"id":"2401.00901","kind":"arxiv","version":2}},"canonical_sha256":"e954e7452e6cfe3a7117c9f72913be7ae2fd42288761896b517d15e05162a434","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e954e7452e6cfe3a7117c9f72913be7ae2fd42288761896b517d15e05162a434","first_computed_at":"2026-07-05T08:02:23.698054Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:23.698054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lUeMmHIbnxXDPK+UGQvzI69C1YASPh4z3ojG/YmutsS7mblqTbV7yzCUE8WBRJyiTXoYkRpIm3eDnAEykZ18AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:23.698551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00901","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3ac925647cc10fed794123abb2ca635c0460bde10c6ea5a44e9da6fe6691413","sha256:b704e0f91d131162c99e6b2aaf9bf8b74a035f843deb3b2dac1564596670f2c7"],"state_sha256":"20939fa5c13073da3815003b324a32266bb0ea4da1d7fb0c6078b088628566ce"}