{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ANIPQPOSQZAFO4O7YO46KHKFAY","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":"331586b1c65a9efcba7ea8a852a941d93739749f0b845e7502336640e5b231ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T09:12:35Z","title_canon_sha256":"d5bb031be461b8c4765fde02e2ad9908b0f5602ce3b389ef7fef737a94022bd6"},"schema_version":"1.0","source":{"id":"2312.06729","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06729","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06729v3","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06729","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"ANIPQPOSQZAF","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"pith_short_16","alias_value":"ANIPQPOSQZAFO4O7","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"pith_short_8","alias_value":"ANIPQPOS","created_at":"2026-07-05T08:43:24Z"}],"graph_snapshots":[{"event_id":"sha256:e29165555aad8570f3d578aaa65e361820efa9e2f4a8f0ae71d845f69360ec75","target":"graph","created_at":"2026-07-05T08:43:24Z","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/2312.06729/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Locating specific moments within long videos (20-120 minutes) presents a significant challenge, akin to finding a needle in a haystack. Adapting existing short video (5-30 seconds) grounding methods to this problem yields poor performance. Since most real life videos, such as those on YouTube and AR/VR, are lengthy, addressing this issue is crucial. Existing methods typically operate in two stages: clip retrieval and grounding. However, this disjoint process limits the retrieval module's fine-grained event understanding, crucial for specific moment detection. We propose RGNet which deeply inte","authors_text":"Gedas Bertasius, Md Mohaiminul Islam, Tanveer Hannan, Thomas Seidl","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T09:12:35Z","title":"RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06729","kind":"arxiv","version":3},"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":"sha256:28e60cc645c531cb8a2d74674a553b1c64dc40a81c6298466b6b6ea864c0e81c","target":"record","created_at":"2026-07-05T08:43:24Z","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":"331586b1c65a9efcba7ea8a852a941d93739749f0b845e7502336640e5b231ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T09:12:35Z","title_canon_sha256":"d5bb031be461b8c4765fde02e2ad9908b0f5602ce3b389ef7fef737a94022bd6"},"schema_version":"1.0","source":{"id":"2312.06729","kind":"arxiv","version":3}},"canonical_sha256":"0350f83dd286405771dfc3b9e51d45063e3ab16ba0eef024a7cbd3415059f09b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0350f83dd286405771dfc3b9e51d45063e3ab16ba0eef024a7cbd3415059f09b","first_computed_at":"2026-07-05T08:43:24.730234Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:24.730234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KKYbwWpkiJes1H51HmF5FisGA46wSdfLXRsH4h/efWsiZ2PQ4KPKunvRWNfobqvCrsIzWFnyqhSuX5O0E/G6CA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:24.730646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06729","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28e60cc645c531cb8a2d74674a553b1c64dc40a81c6298466b6b6ea864c0e81c","sha256:e29165555aad8570f3d578aaa65e361820efa9e2f4a8f0ae71d845f69360ec75"],"state_sha256":"d3cb633a705054071275762644cfd3d7f104d5f559b8497d092975d03851ae06"}