{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DELEF2EV4435AUXFDJEWHNKHBZ","short_pith_number":"pith:DELEF2EV","canonical_record":{"source":{"id":"2409.07747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T04:42:51Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4a9f60705d6b3ada9dc6081609b5178fa2b7165207e0eb15e61ea1352b40f615","abstract_canon_sha256":"13323834163f5c4823e5cadb9551b8223e7be190c0a09f550dd6144c07e0772c"},"schema_version":"1.0"},"canonical_sha256":"191642e895e737d052e51a4963b5470e44aa79139042376908ca527b0235ab8c","source":{"kind":"arxiv","id":"2409.07747","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07747","created_at":"2026-07-05T09:06:14Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07747v1","created_at":"2026-07-05T09:06:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07747","created_at":"2026-07-05T09:06:14Z"},{"alias_kind":"pith_short_12","alias_value":"DELEF2EV4435","created_at":"2026-07-05T09:06:14Z"},{"alias_kind":"pith_short_16","alias_value":"DELEF2EV4435AUXF","created_at":"2026-07-05T09:06:14Z"},{"alias_kind":"pith_short_8","alias_value":"DELEF2EV","created_at":"2026-07-05T09:06:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DELEF2EV4435AUXFDJEWHNKHBZ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.07747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T04:42:51Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4a9f60705d6b3ada9dc6081609b5178fa2b7165207e0eb15e61ea1352b40f615","abstract_canon_sha256":"13323834163f5c4823e5cadb9551b8223e7be190c0a09f550dd6144c07e0772c"},"schema_version":"1.0"},"canonical_sha256":"191642e895e737d052e51a4963b5470e44aa79139042376908ca527b0235ab8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:14.521198Z","signature_b64":"ofAgOY5sVqvPvst4E9gl1x8zVQUPP+ywVuJ3Zvcw6snecwqchx8n1BzzBMfVxgCBUh49/ELU5gA54FrNRJXvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"191642e895e737d052e51a4963b5470e44aa79139042376908ca527b0235ab8c","last_reissued_at":"2026-07-05T09:06:14.520782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:14.520782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.07747","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":"2026-07-05T09:06:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XnqjPHrAFBRJq0d2qHJgX4hjdBtC5SXW+CL896CbB/9zItm+OKJ9dh/I5oxmfWv03wd+1kB21fatx43fxf5xCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:22:47.816212Z"},"content_sha256":"4df8cac71cfe0dfec4845db5ccc919b514fed3dd62a0903c63d3f52aa0481fa9","schema_version":"1.0","event_id":"sha256:4df8cac71cfe0dfec4845db5ccc919b514fed3dd62a0903c63d3f52aa0481fa9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DELEF2EV4435AUXFDJEWHNKHBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-object event graph representation learning for Video Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Donghuo Zeng, Julio Vizcarra, Mori Kurokawa, Shuichiro Haruta, Yanan Wang","submitted_at":"2024-09-12T04:42:51Z","abstract_excerpt":"Video question answering (VideoQA) is a task to predict the correct answer to questions posed about a given video. The system must comprehend spatial and temporal relationships among objects extracted from videos to perform causal and temporal reasoning. While prior works have focused on modeling individual object movements using transformer-based methods, they falter when capturing complex scenarios involving multiple objects (e.g., \"a boy is throwing a ball in a hoop\"). We propose a contrastive language event graph representation learning method called CLanG to address this limitation. Aimin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07747","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/2409.07747/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":"2026-07-05T09:06:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"molvSi0ZuQPs9bSU2yqIVNEGV1vhFlCsMArvgFUm0G7oaGpEtniFIb0e8PSS7IGbayMO+6AqTCD2StitdNFfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:22:47.816721Z"},"content_sha256":"1ba41eff43db1926fff627a912874bcc0fe0f15e99ac7fb07032ac3ad85bbe62","schema_version":"1.0","event_id":"sha256:1ba41eff43db1926fff627a912874bcc0fe0f15e99ac7fb07032ac3ad85bbe62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DELEF2EV4435AUXFDJEWHNKHBZ/bundle.json","state_url":"https://pith.science/pith/DELEF2EV4435AUXFDJEWHNKHBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DELEF2EV4435AUXFDJEWHNKHBZ/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":"2026-08-19T04:22:47Z","links":{"resolver":"https://pith.science/pith/DELEF2EV4435AUXFDJEWHNKHBZ","bundle":"https://pith.science/pith/DELEF2EV4435AUXFDJEWHNKHBZ/bundle.json","state":"https://pith.science/pith/DELEF2EV4435AUXFDJEWHNKHBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DELEF2EV4435AUXFDJEWHNKHBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DELEF2EV4435AUXFDJEWHNKHBZ","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":"13323834163f5c4823e5cadb9551b8223e7be190c0a09f550dd6144c07e0772c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T04:42:51Z","title_canon_sha256":"4a9f60705d6b3ada9dc6081609b5178fa2b7165207e0eb15e61ea1352b40f615"},"schema_version":"1.0","source":{"id":"2409.07747","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07747","created_at":"2026-07-05T09:06:14Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07747v1","created_at":"2026-07-05T09:06:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07747","created_at":"2026-07-05T09:06:14Z"},{"alias_kind":"pith_short_12","alias_value":"DELEF2EV4435","created_at":"2026-07-05T09:06:14Z"},{"alias_kind":"pith_short_16","alias_value":"DELEF2EV4435AUXF","created_at":"2026-07-05T09:06:14Z"},{"alias_kind":"pith_short_8","alias_value":"DELEF2EV","created_at":"2026-07-05T09:06:14Z"}],"graph_snapshots":[{"event_id":"sha256:1ba41eff43db1926fff627a912874bcc0fe0f15e99ac7fb07032ac3ad85bbe62","target":"graph","created_at":"2026-07-05T09:06:14Z","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/2409.07747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video question answering (VideoQA) is a task to predict the correct answer to questions posed about a given video. The system must comprehend spatial and temporal relationships among objects extracted from videos to perform causal and temporal reasoning. While prior works have focused on modeling individual object movements using transformer-based methods, they falter when capturing complex scenarios involving multiple objects (e.g., \"a boy is throwing a ball in a hoop\"). We propose a contrastive language event graph representation learning method called CLanG to address this limitation. Aimin","authors_text":"Donghuo Zeng, Julio Vizcarra, Mori Kurokawa, Shuichiro Haruta, Yanan Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T04:42:51Z","title":"Multi-object event graph representation learning for Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07747","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":"sha256:4df8cac71cfe0dfec4845db5ccc919b514fed3dd62a0903c63d3f52aa0481fa9","target":"record","created_at":"2026-07-05T09:06:14Z","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":"13323834163f5c4823e5cadb9551b8223e7be190c0a09f550dd6144c07e0772c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T04:42:51Z","title_canon_sha256":"4a9f60705d6b3ada9dc6081609b5178fa2b7165207e0eb15e61ea1352b40f615"},"schema_version":"1.0","source":{"id":"2409.07747","kind":"arxiv","version":1}},"canonical_sha256":"191642e895e737d052e51a4963b5470e44aa79139042376908ca527b0235ab8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"191642e895e737d052e51a4963b5470e44aa79139042376908ca527b0235ab8c","first_computed_at":"2026-07-05T09:06:14.520782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:14.520782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ofAgOY5sVqvPvst4E9gl1x8zVQUPP+ywVuJ3Zvcw6snecwqchx8n1BzzBMfVxgCBUh49/ELU5gA54FrNRJXvCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:14.521198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.07747","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4df8cac71cfe0dfec4845db5ccc919b514fed3dd62a0903c63d3f52aa0481fa9","sha256:1ba41eff43db1926fff627a912874bcc0fe0f15e99ac7fb07032ac3ad85bbe62"],"state_sha256":"71807a46f8354427450822410718117574814ddddf0f9c953a0cb4cf90aad505"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q22ov2noHowCBV+ufXQwG4kJVDZK3eLhKn5c9dydD5bwEFpqLGxyjWMRSoCnruBYfvt97MXfXGEr9lC2FCOhAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T04:22:47.821846Z","bundle_sha256":"c7dea10dd2c2709fdcd23793909c38713d2af4d177ce1d4b7a12e65cbb7216fc"}}