{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:W7TUPEH5Z7BWAG7H74DFDLXDUS","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":"5503627f5bcb3fa208b5590f8c2e5b7eca84e4580d4c265f9e0f084f6f9adff2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-11T13:04:59Z","title_canon_sha256":"1229b24036eddb4081730b8f82a43ec68549f6119f06764221eec8c3c807971b"},"schema_version":"1.0","source":{"id":"2210.05423","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05423","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05423v4","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05423","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"pith_short_12","alias_value":"W7TUPEH5Z7BW","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"pith_short_16","alias_value":"W7TUPEH5Z7BWAG7H","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"pith_short_8","alias_value":"W7TUPEH5","created_at":"2026-07-05T06:54:13Z"}],"graph_snapshots":[{"event_id":"sha256:9e0ebff6e769ff22dd9b59785273826dd1b4addf083d0d0c35d0cc0b59a1e0be","target":"graph","created_at":"2026-07-05T06:54:13Z","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/2210.05423/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a new task, named video corpus visual answer localization (VCVAL), which aims to locate the visual answer in a large collection of untrimmed instructional videos using a natural language question. This task requires a range of skills - the interaction between vision and language, video retrieval, passage comprehension, and visual answer localization. In this paper, we propose a cross-modal contrastive global-span (CCGS) method for the VCVAL, jointly training the video corpus retrieval and visual answer localization subtasks with the global-span matrix. We have reconstructed a data","authors_text":"Bin Li, Bin Sun, Shutao Li, Yixuan Weng","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-11T13:04:59Z","title":"Learning to Locate Visual Answer in Video Corpus Using Question"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05423","kind":"arxiv","version":4},"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":"sha256:0bb359c5028f8451f9565aa7b43b06f791b7ebaa5e37010221397c1cae8fb216","target":"record","created_at":"2026-07-05T06:54:13Z","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":"5503627f5bcb3fa208b5590f8c2e5b7eca84e4580d4c265f9e0f084f6f9adff2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-11T13:04:59Z","title_canon_sha256":"1229b24036eddb4081730b8f82a43ec68549f6119f06764221eec8c3c807971b"},"schema_version":"1.0","source":{"id":"2210.05423","kind":"arxiv","version":4}},"canonical_sha256":"b7e74790fdcfc3601be7ff0651aee3a4b334d4528fd81b9d7b782dedf642b40a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7e74790fdcfc3601be7ff0651aee3a4b334d4528fd81b9d7b782dedf642b40a","first_computed_at":"2026-07-05T06:54:13.376722Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:13.376722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/tVD+0BdsY3J8y0Q3jtn/tEMgVHjxL5d6CpND4QON4fqcgnaWFJmJG2+xvtt5nuEATw13wL5Wn0+NLDkiT9ADQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:13.377142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05423","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bb359c5028f8451f9565aa7b43b06f791b7ebaa5e37010221397c1cae8fb216","sha256:9e0ebff6e769ff22dd9b59785273826dd1b4addf083d0d0c35d0cc0b59a1e0be"],"state_sha256":"de9779653e2aa9ec2c45df7fb5b466c9e9c14e04820e21d378d538c69d3e841d"}