{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:S62OTSG5CP27IMUCB2OG3H4PXO","short_pith_number":"pith:S62OTSG5","canonical_record":{"source":{"id":"2204.11544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-25T10:42:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"18e9d42600b1e2ac53bfbf157f24b6625b68e3169784a9396625db64ec1924ca","abstract_canon_sha256":"3ba415f6ac8270136008bc13e691077a7580f1557d8f5b83a69ce9854b75b128"},"schema_version":"1.0"},"canonical_sha256":"97b4e9c8dd13f5f432820e9c6d9f8fbb94bca8ba0dec2a11866374c4c733c178","source":{"kind":"arxiv","id":"2204.11544","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.11544","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2204.11544v2","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11544","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"S62OTSG5CP27","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"S62OTSG5CP27IMUC","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"S62OTSG5","created_at":"2026-07-05T05:12:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:S62OTSG5CP27IMUCB2OG3H4PXO","target":"record","payload":{"canonical_record":{"source":{"id":"2204.11544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-25T10:42:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"18e9d42600b1e2ac53bfbf157f24b6625b68e3169784a9396625db64ec1924ca","abstract_canon_sha256":"3ba415f6ac8270136008bc13e691077a7580f1557d8f5b83a69ce9854b75b128"},"schema_version":"1.0"},"canonical_sha256":"97b4e9c8dd13f5f432820e9c6d9f8fbb94bca8ba0dec2a11866374c4c733c178","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:28.639079Z","signature_b64":"QuplWwcrl854NkImILKIyGl57jfLtXbihiPI6GPA4ywgizudBnX6EkoWcofRmneOEAigucjkk47tKFUT1R1hDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97b4e9c8dd13f5f432820e9c6d9f8fbb94bca8ba0dec2a11866374c4c733c178","last_reissued_at":"2026-07-05T05:12:28.638584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:28.638584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.11544","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":"2026-07-05T05:12:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hYYrhAYh0MwPI8e0odyD4QO1c/nJDIq2Uyr43HWZADiYO+K8+lSKo3VYm48ocffwMp0AR0AM/ffhBDdjauiKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:24:11.077287Z"},"content_sha256":"e8e01c502f4155c54d63e91a7a21fdf1ad6a3cfbcfa0d5f46b7a17a8d5173924","schema_version":"1.0","event_id":"sha256:e8e01c502f4155c54d63e91a7a21fdf1ad6a3cfbcfa0d5f46b7a17a8d5173924"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:S62OTSG5CP27IMUCB2OG3H4PXO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jun Xiao, Kaifeng Gao, Long Chen, Shaoning Xiao, Yi Yang, Zhao Wang, Zhimeng Zhang","submitted_at":"2022-04-25T10:42:07Z","abstract_excerpt":"Reasoning about causal and temporal event relations in videos is a new destination of Video Question Answering (VideoQA).The major stumbling block to achieve this purpose is the semantic gap between language and video since they are at different levels of abstraction. Existing efforts mainly focus on designing sophisticated architectures while utilizing frame- or object-level visual representations. In this paper, we reconsider the multi-modal alignment problem in VideoQA from feature and sample perspectives to achieve better performance. From the view of feature,we break down the video into t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11544","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/2204.11544/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":"2026-07-05T05:12:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AJJrYfFNzLpivOJ8pm5ZAlWYfN1hjClDTwHg6JRZmFqUJ8YEfHYphmdT4Y4RvKqYSYU2VYDp+k8gwPRZ+CTfCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:24:11.077789Z"},"content_sha256":"4c93fd41b0d0735a1b6b8e17edec7124a60bda08614d6353e8546e9321e13f98","schema_version":"1.0","event_id":"sha256:4c93fd41b0d0735a1b6b8e17edec7124a60bda08614d6353e8546e9321e13f98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S62OTSG5CP27IMUCB2OG3H4PXO/bundle.json","state_url":"https://pith.science/pith/S62OTSG5CP27IMUCB2OG3H4PXO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S62OTSG5CP27IMUCB2OG3H4PXO/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":"2026-08-08T18:24:11Z","links":{"resolver":"https://pith.science/pith/S62OTSG5CP27IMUCB2OG3H4PXO","bundle":"https://pith.science/pith/S62OTSG5CP27IMUCB2OG3H4PXO/bundle.json","state":"https://pith.science/pith/S62OTSG5CP27IMUCB2OG3H4PXO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S62OTSG5CP27IMUCB2OG3H4PXO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:S62OTSG5CP27IMUCB2OG3H4PXO","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":"3ba415f6ac8270136008bc13e691077a7580f1557d8f5b83a69ce9854b75b128","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-25T10:42:07Z","title_canon_sha256":"18e9d42600b1e2ac53bfbf157f24b6625b68e3169784a9396625db64ec1924ca"},"schema_version":"1.0","source":{"id":"2204.11544","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.11544","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2204.11544v2","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11544","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"S62OTSG5CP27","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"S62OTSG5CP27IMUC","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"S62OTSG5","created_at":"2026-07-05T05:12:28Z"}],"graph_snapshots":[{"event_id":"sha256:4c93fd41b0d0735a1b6b8e17edec7124a60bda08614d6353e8546e9321e13f98","target":"graph","created_at":"2026-07-05T05:12:28Z","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/2204.11544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning about causal and temporal event relations in videos is a new destination of Video Question Answering (VideoQA).The major stumbling block to achieve this purpose is the semantic gap between language and video since they are at different levels of abstraction. Existing efforts mainly focus on designing sophisticated architectures while utilizing frame- or object-level visual representations. In this paper, we reconsider the multi-modal alignment problem in VideoQA from feature and sample perspectives to achieve better performance. From the view of feature,we break down the video into t","authors_text":"Jun Xiao, Kaifeng Gao, Long Chen, Shaoning Xiao, Yi Yang, Zhao Wang, Zhimeng Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-25T10:42:07Z","title":"Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11544","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:e8e01c502f4155c54d63e91a7a21fdf1ad6a3cfbcfa0d5f46b7a17a8d5173924","target":"record","created_at":"2026-07-05T05:12:28Z","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":"3ba415f6ac8270136008bc13e691077a7580f1557d8f5b83a69ce9854b75b128","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-25T10:42:07Z","title_canon_sha256":"18e9d42600b1e2ac53bfbf157f24b6625b68e3169784a9396625db64ec1924ca"},"schema_version":"1.0","source":{"id":"2204.11544","kind":"arxiv","version":2}},"canonical_sha256":"97b4e9c8dd13f5f432820e9c6d9f8fbb94bca8ba0dec2a11866374c4c733c178","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97b4e9c8dd13f5f432820e9c6d9f8fbb94bca8ba0dec2a11866374c4c733c178","first_computed_at":"2026-07-05T05:12:28.638584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:28.638584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QuplWwcrl854NkImILKIyGl57jfLtXbihiPI6GPA4ywgizudBnX6EkoWcofRmneOEAigucjkk47tKFUT1R1hDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:28.639079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.11544","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8e01c502f4155c54d63e91a7a21fdf1ad6a3cfbcfa0d5f46b7a17a8d5173924","sha256:4c93fd41b0d0735a1b6b8e17edec7124a60bda08614d6353e8546e9321e13f98"],"state_sha256":"9cb9a3c2b3e75268f2d51ce6e744048dbb935d13eb573e06dbe86cb1dbe68efb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G/ugaoY0tum9Xayfxg0UtUhs+PaUgWCQtmVs9zPhXdEXpiOirmt4OEGijE9fneTscuSkLL7E4mQJ+jBr08baBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:24:11.081943Z","bundle_sha256":"9025293f4468e190a7a86f9eb59133f9a435a2c6f4315008a18176508eef6a16"}}