{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VEJYCBSZMUOGN6Z723FFDVYI7F","short_pith_number":"pith:VEJYCBSZ","canonical_record":{"source":{"id":"2305.03347","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T08:00:14Z","cross_cats_sorted":[],"title_canon_sha256":"71b063464350f1b6dd785448a2563dc4bd6f5e049ec40262439faf9cc4cdc293","abstract_canon_sha256":"7a467b3f67713c5b79259d634a6f00c902e6fe0a09b5ca8cf08388af53042ac7"},"schema_version":"1.0"},"canonical_sha256":"a913810659651c66fb3fd6ca51d708f94c2a9e5dcb042db8e076a26dd9e2be0a","source":{"kind":"arxiv","id":"2305.03347","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03347","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03347v1","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03347","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_12","alias_value":"VEJYCBSZMUOG","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_16","alias_value":"VEJYCBSZMUOGN6Z7","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_8","alias_value":"VEJYCBSZ","created_at":"2026-07-05T06:07:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VEJYCBSZMUOGN6Z723FFDVYI7F","target":"record","payload":{"canonical_record":{"source":{"id":"2305.03347","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T08:00:14Z","cross_cats_sorted":[],"title_canon_sha256":"71b063464350f1b6dd785448a2563dc4bd6f5e049ec40262439faf9cc4cdc293","abstract_canon_sha256":"7a467b3f67713c5b79259d634a6f00c902e6fe0a09b5ca8cf08388af53042ac7"},"schema_version":"1.0"},"canonical_sha256":"a913810659651c66fb3fd6ca51d708f94c2a9e5dcb042db8e076a26dd9e2be0a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:22.214719Z","signature_b64":"AOcNknPjrB2yX3r8jBJnhsLKzuJ/2dZ5TaWcEnH/s3nPT/vRkPWLJRl4NrWbFWh8l7/Ufgd+AW/OxAwTg2/FBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a913810659651c66fb3fd6ca51d708f94c2a9e5dcb042db8e076a26dd9e2be0a","last_reissued_at":"2026-07-05T06:07:22.214270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:22.214270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.03347","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:07:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mg4pRm8c6Be+q41smRPvOp3Rj3EKnBeZHIGbmwZvZDAsqepMeDcks2lGNYNFPIBWMCkWFQCHzEgU+Iab3xOhDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:13:28.810544Z"},"content_sha256":"838dfed0c45cd9afefb8264af4d88b26bf99bf4c125d30d7e742d6dcd614ae11","schema_version":"1.0","event_id":"sha256:838dfed0c45cd9afefb8264af4d88b26bf99bf4c125d30d7e742d6dcd614ae11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VEJYCBSZMUOGN6Z723FFDVYI7F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Zhou, Jiahong Li, Mike Zheng Shou, Weijia Wu, Xiang Bai, Yuzhong Zhao, Zhuang Li","submitted_at":"2023-05-05T08:00:14Z","abstract_excerpt":"Most existing cross-modal language-to-video retrieval (VR) research focuses on single-modal input from video, i.e., visual representation, while the text is omnipresent in human environments and frequently critical to understand video. To study how to retrieve video with both modal inputs, i.e., visual and text semantic representations, we first introduce a large-scale and cross-modal Video Retrieval dataset with text reading comprehension, TextVR, which contains 42.2k sentence queries for 10.5k videos of 8 scenario domains, i.e., Street View (indoor), Street View (outdoor), Games, Sports, Dri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03347","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/2305.03347/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:07:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kMvTxgToPrB/6s99HITuOP178yaRUiwef7NCJA0/dBuGLw4EobHTIYKzEPc9s+7zgElrEkULrx8gj0mi7hwSDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:13:28.811190Z"},"content_sha256":"81415093672141fa179ae4d39a8e24e487b13b2437ad820b23bd3699022b3265","schema_version":"1.0","event_id":"sha256:81415093672141fa179ae4d39a8e24e487b13b2437ad820b23bd3699022b3265"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VEJYCBSZMUOGN6Z723FFDVYI7F/bundle.json","state_url":"https://pith.science/pith/VEJYCBSZMUOGN6Z723FFDVYI7F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VEJYCBSZMUOGN6Z723FFDVYI7F/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T20:13:28Z","links":{"resolver":"https://pith.science/pith/VEJYCBSZMUOGN6Z723FFDVYI7F","bundle":"https://pith.science/pith/VEJYCBSZMUOGN6Z723FFDVYI7F/bundle.json","state":"https://pith.science/pith/VEJYCBSZMUOGN6Z723FFDVYI7F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VEJYCBSZMUOGN6Z723FFDVYI7F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VEJYCBSZMUOGN6Z723FFDVYI7F","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":"7a467b3f67713c5b79259d634a6f00c902e6fe0a09b5ca8cf08388af53042ac7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T08:00:14Z","title_canon_sha256":"71b063464350f1b6dd785448a2563dc4bd6f5e049ec40262439faf9cc4cdc293"},"schema_version":"1.0","source":{"id":"2305.03347","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03347","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03347v1","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03347","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_12","alias_value":"VEJYCBSZMUOG","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_16","alias_value":"VEJYCBSZMUOGN6Z7","created_at":"2026-07-05T06:07:22Z"},{"alias_kind":"pith_short_8","alias_value":"VEJYCBSZ","created_at":"2026-07-05T06:07:22Z"}],"graph_snapshots":[{"event_id":"sha256:81415093672141fa179ae4d39a8e24e487b13b2437ad820b23bd3699022b3265","target":"graph","created_at":"2026-07-05T06:07:22Z","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/2305.03347/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most existing cross-modal language-to-video retrieval (VR) research focuses on single-modal input from video, i.e., visual representation, while the text is omnipresent in human environments and frequently critical to understand video. To study how to retrieve video with both modal inputs, i.e., visual and text semantic representations, we first introduce a large-scale and cross-modal Video Retrieval dataset with text reading comprehension, TextVR, which contains 42.2k sentence queries for 10.5k videos of 8 scenario domains, i.e., Street View (indoor), Street View (outdoor), Games, Sports, Dri","authors_text":"Hong Zhou, Jiahong Li, Mike Zheng Shou, Weijia Wu, Xiang Bai, Yuzhong Zhao, Zhuang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T08:00:14Z","title":"A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03347","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":"sha256:838dfed0c45cd9afefb8264af4d88b26bf99bf4c125d30d7e742d6dcd614ae11","target":"record","created_at":"2026-07-05T06:07:22Z","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":"7a467b3f67713c5b79259d634a6f00c902e6fe0a09b5ca8cf08388af53042ac7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T08:00:14Z","title_canon_sha256":"71b063464350f1b6dd785448a2563dc4bd6f5e049ec40262439faf9cc4cdc293"},"schema_version":"1.0","source":{"id":"2305.03347","kind":"arxiv","version":1}},"canonical_sha256":"a913810659651c66fb3fd6ca51d708f94c2a9e5dcb042db8e076a26dd9e2be0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a913810659651c66fb3fd6ca51d708f94c2a9e5dcb042db8e076a26dd9e2be0a","first_computed_at":"2026-07-05T06:07:22.214270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:07:22.214270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AOcNknPjrB2yX3r8jBJnhsLKzuJ/2dZ5TaWcEnH/s3nPT/vRkPWLJRl4NrWbFWh8l7/Ufgd+AW/OxAwTg2/FBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:07:22.214719Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03347","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:838dfed0c45cd9afefb8264af4d88b26bf99bf4c125d30d7e742d6dcd614ae11","sha256:81415093672141fa179ae4d39a8e24e487b13b2437ad820b23bd3699022b3265"],"state_sha256":"094ddc06155d91695a0833eaada5b2d874fc6c2f0edbe7ea80bb0c3e65708cde"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GauRiPZBpNmuc8XaUfr2oomoSo/kl0L9dp32rHTj3gOLv8xJX9rbAyHtSeyMrg1mJvOGt98hVeJpj9MzIwKyDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T20:13:28.818274Z","bundle_sha256":"ae822a8ff91f1b64dbfca7bba1023867deb5a0f4494c678a6763cf24f95c1af6"}}