{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6TVWB2TUQDWLJRLNBLLNZJJEQX","short_pith_number":"pith:6TVWB2TU","canonical_record":{"source":{"id":"2309.01327","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T03:06:04Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"5f40a5cb6f66b6a1e34ed35eb5ea38dcd2d0e87126a66caf0c762e152b825a14","abstract_canon_sha256":"2747da37d9995b8d92428bfcdd9a4ae297b6a44af3da97444ad65953e23e76d1"},"schema_version":"1.0"},"canonical_sha256":"f4eb60ea7480ecb4c56d0ad6dca52485e080eb3397f45cf7d541fd76e026aa98","source":{"kind":"arxiv","id":"2309.01327","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.01327","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2309.01327v2","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01327","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"6TVWB2TUQDWL","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"6TVWB2TUQDWLJRLN","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"6TVWB2TU","created_at":"2026-07-05T08:02:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6TVWB2TUQDWLJRLNBLLNZJJEQX","target":"record","payload":{"canonical_record":{"source":{"id":"2309.01327","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T03:06:04Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"5f40a5cb6f66b6a1e34ed35eb5ea38dcd2d0e87126a66caf0c762e152b825a14","abstract_canon_sha256":"2747da37d9995b8d92428bfcdd9a4ae297b6a44af3da97444ad65953e23e76d1"},"schema_version":"1.0"},"canonical_sha256":"f4eb60ea7480ecb4c56d0ad6dca52485e080eb3397f45cf7d541fd76e026aa98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:21.236726Z","signature_b64":"A3w0vRuIrChlyFELeXSKY92UqubjSRfAothCl4xz6ctArLCAb0toykFqwsGVn6jeTsHPk2v3Rr3Xkpj/q8pXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4eb60ea7480ecb4c56d0ad6dca52485e080eb3397f45cf7d541fd76e026aa98","last_reissued_at":"2026-07-05T08:02:21.236237Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:21.236237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.01327","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":"2026-07-05T08:02:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fRBq6N7evDEFXbn6LFxC21+BqTPrB5QZuBvCBsvqb1bUnJM9ZaYOsXm1NQ4yRznntUEa5pkVKUT6apIVTCjIBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:19:16.794548Z"},"content_sha256":"b2ac08a30e0a2316782e8980adcba4e75d82f8d4a77239b91556182c2e7bc112","schema_version":"1.0","event_id":"sha256:b2ac08a30e0a2316782e8980adcba4e75d82f8d4a77239b91556182c2e7bc112"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6TVWB2TUQDWLJRLNBLLNZJJEQX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Angela Yao, Junbin Xiao, Tat Seng Chua, Yicong Li","submitted_at":"2023-09-04T03:06:04Z","abstract_excerpt":"We study visually grounded VideoQA in response to the emerging trends of utilizing pretraining techniques for video-language understanding. Specifically, by forcing vision-language models (VLMs) to answer questions and simultaneously provide visual evidence, we seek to ascertain the extent to which the predictions of such techniques are genuinely anchored in relevant video content, versus spurious correlations from language or irrelevant visual context. Towards this, we construct NExT-GQA -- an extension of NExT-QA with 10.5$K$ temporal grounding (or location) labels tied to the original QA pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01327","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/2309.01327/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":"2026-07-05T08:02:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fAEWGXDppvx5MNkRQgmrhOoOA2i3zSnpFNx1FDKtLAZgpds+0p+DTwfwTkdvwD8xuXLeRF4mRn5Y7lmgOJUDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:19:16.795126Z"},"content_sha256":"41ea8077b63168aaae4aae5c204d7e06ea0fdc54fadf1d479a14eb74bdd50e50","schema_version":"1.0","event_id":"sha256:41ea8077b63168aaae4aae5c204d7e06ea0fdc54fadf1d479a14eb74bdd50e50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6TVWB2TUQDWLJRLNBLLNZJJEQX/bundle.json","state_url":"https://pith.science/pith/6TVWB2TUQDWLJRLNBLLNZJJEQX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6TVWB2TUQDWLJRLNBLLNZJJEQX/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":"2026-08-22T00:19:16Z","links":{"resolver":"https://pith.science/pith/6TVWB2TUQDWLJRLNBLLNZJJEQX","bundle":"https://pith.science/pith/6TVWB2TUQDWLJRLNBLLNZJJEQX/bundle.json","state":"https://pith.science/pith/6TVWB2TUQDWLJRLNBLLNZJJEQX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6TVWB2TUQDWLJRLNBLLNZJJEQX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6TVWB2TUQDWLJRLNBLLNZJJEQX","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":"2747da37d9995b8d92428bfcdd9a4ae297b6a44af3da97444ad65953e23e76d1","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T03:06:04Z","title_canon_sha256":"5f40a5cb6f66b6a1e34ed35eb5ea38dcd2d0e87126a66caf0c762e152b825a14"},"schema_version":"1.0","source":{"id":"2309.01327","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.01327","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2309.01327v2","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01327","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"6TVWB2TUQDWL","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"6TVWB2TUQDWLJRLN","created_at":"2026-07-05T08:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"6TVWB2TU","created_at":"2026-07-05T08:02:21Z"}],"graph_snapshots":[{"event_id":"sha256:41ea8077b63168aaae4aae5c204d7e06ea0fdc54fadf1d479a14eb74bdd50e50","target":"graph","created_at":"2026-07-05T08:02:21Z","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/2309.01327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study visually grounded VideoQA in response to the emerging trends of utilizing pretraining techniques for video-language understanding. Specifically, by forcing vision-language models (VLMs) to answer questions and simultaneously provide visual evidence, we seek to ascertain the extent to which the predictions of such techniques are genuinely anchored in relevant video content, versus spurious correlations from language or irrelevant visual context. Towards this, we construct NExT-GQA -- an extension of NExT-QA with 10.5$K$ temporal grounding (or location) labels tied to the original QA pa","authors_text":"Angela Yao, Junbin Xiao, Tat Seng Chua, Yicong Li","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T03:06:04Z","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01327","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:b2ac08a30e0a2316782e8980adcba4e75d82f8d4a77239b91556182c2e7bc112","target":"record","created_at":"2026-07-05T08:02:21Z","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":"2747da37d9995b8d92428bfcdd9a4ae297b6a44af3da97444ad65953e23e76d1","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T03:06:04Z","title_canon_sha256":"5f40a5cb6f66b6a1e34ed35eb5ea38dcd2d0e87126a66caf0c762e152b825a14"},"schema_version":"1.0","source":{"id":"2309.01327","kind":"arxiv","version":2}},"canonical_sha256":"f4eb60ea7480ecb4c56d0ad6dca52485e080eb3397f45cf7d541fd76e026aa98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4eb60ea7480ecb4c56d0ad6dca52485e080eb3397f45cf7d541fd76e026aa98","first_computed_at":"2026-07-05T08:02:21.236237Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:21.236237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A3w0vRuIrChlyFELeXSKY92UqubjSRfAothCl4xz6ctArLCAb0toykFqwsGVn6jeTsHPk2v3Rr3Xkpj/q8pXDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:21.236726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.01327","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2ac08a30e0a2316782e8980adcba4e75d82f8d4a77239b91556182c2e7bc112","sha256:41ea8077b63168aaae4aae5c204d7e06ea0fdc54fadf1d479a14eb74bdd50e50"],"state_sha256":"d3a5de2b3c5c991a56e860f7d97992800d7cffa37dfa52ef90cea31978d38fd6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NhVYKytCBGHEg6+YQnwEEOR2nuaGWSjMHytimfkL1ZzCUMB4KbLPMQ9j8pGSTqdXxalvVK9Uee8LkFidNo5rBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T00:19:16.801542Z","bundle_sha256":"ec042df862d17d1e8709c877df09a5d2bf0381127bf2adf6aae226aa6ae06af7"}}