{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VEK5F3QCA2NHFQVBLTYYKHFQHX","short_pith_number":"pith:VEK5F3QC","canonical_record":{"source":{"id":"2302.13668","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-27T11:09:13Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"b776a2841154c8a05708840ef82e7ba67ab58afc7336c8666468fa19bbbbba41","abstract_canon_sha256":"7e6d6a3745616ea2ac5a22c62d549b3a223afd61ab17b48db883a3745e292d47"},"schema_version":"1.0"},"canonical_sha256":"a915d2ee02069a72c2a15cf1851cb03de983a22dc0a64deffbbf097229e1e7ab","source":{"kind":"arxiv","id":"2302.13668","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.13668","created_at":"2026-07-05T06:29:20Z"},{"alias_kind":"arxiv_version","alias_value":"2302.13668v2","created_at":"2026-07-05T06:29:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13668","created_at":"2026-07-05T06:29:20Z"},{"alias_kind":"pith_short_12","alias_value":"VEK5F3QCA2NH","created_at":"2026-07-05T06:29:20Z"},{"alias_kind":"pith_short_16","alias_value":"VEK5F3QCA2NHFQVB","created_at":"2026-07-05T06:29:20Z"},{"alias_kind":"pith_short_8","alias_value":"VEK5F3QC","created_at":"2026-07-05T06:29:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VEK5F3QCA2NHFQVBLTYYKHFQHX","target":"record","payload":{"canonical_record":{"source":{"id":"2302.13668","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-27T11:09:13Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"b776a2841154c8a05708840ef82e7ba67ab58afc7336c8666468fa19bbbbba41","abstract_canon_sha256":"7e6d6a3745616ea2ac5a22c62d549b3a223afd61ab17b48db883a3745e292d47"},"schema_version":"1.0"},"canonical_sha256":"a915d2ee02069a72c2a15cf1851cb03de983a22dc0a64deffbbf097229e1e7ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:20.036742Z","signature_b64":"VMnilIb+QL//8gsnJW7ZeyoQV90ttKq/XF/sw5MMV4ivhNpFEbKGef5uOIySVh7Mby/rkKEo/H1wEb4UWlsoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a915d2ee02069a72c2a15cf1851cb03de983a22dc0a64deffbbf097229e1e7ab","last_reissued_at":"2026-07-05T06:29:20.036337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:20.036337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.13668","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:29:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AXGPcw6Pf5Vc3FLAbwkLMNI3mvMFkJxGQveJn5+01gH+OKEuOeBsTrO4uMinrzVqtTe4r6szw/7cJliu3SnNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:18:13.048752Z"},"content_sha256":"92fc5143bd167a428048f186b116f05ca27f151b38d62fb7290d9cd1f127f9f4","schema_version":"1.0","event_id":"sha256:92fc5143bd167a428048f186b116f05ca27f151b38d62fb7290d9cd1f127f9f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VEK5F3QCA2NHFQVBLTYYKHFQHX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contrastive Video Question Answering via Video Graph Transformer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Angela Yao, Junbin Xiao, Pan Zhou, Richang Hong, Shuicheng Yan, Tat-Seng Chua, Yicong Li","submitted_at":"2023-02-27T11:09:13Z","abstract_excerpt":"We propose to perform video question answering (VideoQA) in a Contrastive manner via a Video Graph Transformer model (CoVGT). CoVGT's uniqueness and superiority are three-fold: 1) It proposes a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations and dynamics, for complex spatio-temporal reasoning. 2) It designs separate video and text transformers for contrastive learning between the video and text to perform QA, instead of multi-modal transformer for answer classification. Fine-grained video-text communication is done by additional "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13668","kind":"arxiv","version":2},"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/2302.13668/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":"2026-07-05T06:29:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EVpnvEK6SW3+lm8yv8BmwlnpkUUF3ufX1eQk4FUGxQNK1qedux8G/aM+5PqPaRGpAC7Lk9HB+udZcjKIP4D3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:18:13.049823Z"},"content_sha256":"da54747445cd7679a2511b5d7b868dc85e22d46ac1c51cc044a43508f9f1f4a3","schema_version":"1.0","event_id":"sha256:da54747445cd7679a2511b5d7b868dc85e22d46ac1c51cc044a43508f9f1f4a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX/bundle.json","state_url":"https://pith.science/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX/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":"2026-08-05T12:18:13Z","links":{"resolver":"https://pith.science/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX","bundle":"https://pith.science/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX/bundle.json","state":"https://pith.science/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VEK5F3QCA2NHFQVBLTYYKHFQHX","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":"7e6d6a3745616ea2ac5a22c62d549b3a223afd61ab17b48db883a3745e292d47","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-27T11:09:13Z","title_canon_sha256":"b776a2841154c8a05708840ef82e7ba67ab58afc7336c8666468fa19bbbbba41"},"schema_version":"1.0","source":{"id":"2302.13668","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.13668","created_at":"2026-07-05T06:29:20Z"},{"alias_kind":"arxiv_version","alias_value":"2302.13668v2","created_at":"2026-07-05T06:29:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13668","created_at":"2026-07-05T06:29:20Z"},{"alias_kind":"pith_short_12","alias_value":"VEK5F3QCA2NH","created_at":"2026-07-05T06:29:20Z"},{"alias_kind":"pith_short_16","alias_value":"VEK5F3QCA2NHFQVB","created_at":"2026-07-05T06:29:20Z"},{"alias_kind":"pith_short_8","alias_value":"VEK5F3QC","created_at":"2026-07-05T06:29:20Z"}],"graph_snapshots":[{"event_id":"sha256:da54747445cd7679a2511b5d7b868dc85e22d46ac1c51cc044a43508f9f1f4a3","target":"graph","created_at":"2026-07-05T06:29:20Z","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/2302.13668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose to perform video question answering (VideoQA) in a Contrastive manner via a Video Graph Transformer model (CoVGT). CoVGT's uniqueness and superiority are three-fold: 1) It proposes a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations and dynamics, for complex spatio-temporal reasoning. 2) It designs separate video and text transformers for contrastive learning between the video and text to perform QA, instead of multi-modal transformer for answer classification. Fine-grained video-text communication is done by additional ","authors_text":"Angela Yao, Junbin Xiao, Pan Zhou, Richang Hong, Shuicheng Yan, Tat-Seng Chua, Yicong Li","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-27T11:09:13Z","title":"Contrastive Video Question Answering via Video Graph Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13668","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":"sha256:92fc5143bd167a428048f186b116f05ca27f151b38d62fb7290d9cd1f127f9f4","target":"record","created_at":"2026-07-05T06:29:20Z","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":"7e6d6a3745616ea2ac5a22c62d549b3a223afd61ab17b48db883a3745e292d47","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-27T11:09:13Z","title_canon_sha256":"b776a2841154c8a05708840ef82e7ba67ab58afc7336c8666468fa19bbbbba41"},"schema_version":"1.0","source":{"id":"2302.13668","kind":"arxiv","version":2}},"canonical_sha256":"a915d2ee02069a72c2a15cf1851cb03de983a22dc0a64deffbbf097229e1e7ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a915d2ee02069a72c2a15cf1851cb03de983a22dc0a64deffbbf097229e1e7ab","first_computed_at":"2026-07-05T06:29:20.036337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:29:20.036337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VMnilIb+QL//8gsnJW7ZeyoQV90ttKq/XF/sw5MMV4ivhNpFEbKGef5uOIySVh7Mby/rkKEo/H1wEb4UWlsoAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:29:20.036742Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.13668","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92fc5143bd167a428048f186b116f05ca27f151b38d62fb7290d9cd1f127f9f4","sha256:da54747445cd7679a2511b5d7b868dc85e22d46ac1c51cc044a43508f9f1f4a3"],"state_sha256":"5e71bce632699569b369424e33559f94455408aa96c89a1d522efd82472c3f87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rw143apKlqblGLJ8YmRNuVe0FLfPgdf6pl3YFgyAE7xRciyPEWlMT+8ZV0WLqnWeAKycXJuFPArqyMhhDEo5AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:18:13.055606Z","bundle_sha256":"ab39ec3b6989086470bff4528cae9afb637389e12e7b2930fb0af7a85c839571"}}