{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WYWY66P7RROBEQG345QM2LSG64","short_pith_number":"pith:WYWY66P7","canonical_record":{"source":{"id":"2311.07766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-13T21:32:37Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"cbdebbc848b83d858f606460fda160d0911281c59f3a448e9a1aaf5a84b60c65","abstract_canon_sha256":"4183bc88bf1018f9ea3c709865a23f9f07a4b06f193a0afaeed021d8fdecb5b6"},"schema_version":"1.0"},"canonical_sha256":"b62d8f79ff8c5c1240dbe760cd2e46f72ab517c010ff462a3de06db348fe8cfc","source":{"kind":"arxiv","id":"2311.07766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07766","created_at":"2026-07-05T07:12:23Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07766v1","created_at":"2026-07-05T07:12:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07766","created_at":"2026-07-05T07:12:23Z"},{"alias_kind":"pith_short_12","alias_value":"WYWY66P7RROB","created_at":"2026-07-05T07:12:23Z"},{"alias_kind":"pith_short_16","alias_value":"WYWY66P7RROBEQG3","created_at":"2026-07-05T07:12:23Z"},{"alias_kind":"pith_short_8","alias_value":"WYWY66P7","created_at":"2026-07-05T07:12:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WYWY66P7RROBEQG345QM2LSG64","target":"record","payload":{"canonical_record":{"source":{"id":"2311.07766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-13T21:32:37Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"cbdebbc848b83d858f606460fda160d0911281c59f3a448e9a1aaf5a84b60c65","abstract_canon_sha256":"4183bc88bf1018f9ea3c709865a23f9f07a4b06f193a0afaeed021d8fdecb5b6"},"schema_version":"1.0"},"canonical_sha256":"b62d8f79ff8c5c1240dbe760cd2e46f72ab517c010ff462a3de06db348fe8cfc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:23.429830Z","signature_b64":"OnbXKBwdqE4WtGqxT8AgeHg6B/pdSEnfhRBedktqT83nVchCpIInU0RGhAW2Cyye/y7WslnK/JO6R9ggvnaJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b62d8f79ff8c5c1240dbe760cd2e46f72ab517c010ff462a3de06db348fe8cfc","last_reissued_at":"2026-07-05T07:12:23.429367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:23.429367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.07766","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":"2026-07-05T07:12:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"akh2eXc+RrSgHFkJen01dxXjXb9sF7uNIXa1N9FSOE5RXAMJ2tq024QJxfpqnvAJyCvS6KCGjYQGE+mvWekBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:48:37.112455Z"},"content_sha256":"d28d6b081f691405e541750d5f9172a8d9ccee7e0b3aa5e7c97baf477b0217e1","schema_version":"1.0","event_id":"sha256:d28d6b081f691405e541750d5f9172a8d9ccee7e0b3aa5e7c97baf477b0217e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WYWY66P7RROBEQG345QM2LSG64","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision-Language Integration in Multimodal Video Transformers (Partially) Aligns with the Brain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dota Tianai Dong, Mariya Toneva","submitted_at":"2023-11-13T21:32:37Z","abstract_excerpt":"Integrating information from multiple modalities is arguably one of the essential prerequisites for grounding artificial intelligence systems with an understanding of the real world. Recent advances in video transformers that jointly learn from vision, text, and sound over time have made some progress toward this goal, but the degree to which these models integrate information from modalities still remains unclear. In this work, we present a promising approach for probing a pre-trained multimodal video transformer model by leveraging neuroscientific evidence of multimodal information processin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07766","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/2311.07766/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":"2026-07-05T07:12:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qeGA/we/9H6gnUZ15cSwACUzG6jgHtKZTLDRuzHIKUzZkKbwAi/xPUt+t04s0JAJ5avrwPPa3lpxIkRwrpAGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:48:37.113456Z"},"content_sha256":"a06f51d5417df5d0e8a6b6e3fc30148c76a0dbb32fa147916c978feda3b4de1b","schema_version":"1.0","event_id":"sha256:a06f51d5417df5d0e8a6b6e3fc30148c76a0dbb32fa147916c978feda3b4de1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WYWY66P7RROBEQG345QM2LSG64/bundle.json","state_url":"https://pith.science/pith/WYWY66P7RROBEQG345QM2LSG64/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WYWY66P7RROBEQG345QM2LSG64/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":"2026-08-08T22:48:37Z","links":{"resolver":"https://pith.science/pith/WYWY66P7RROBEQG345QM2LSG64","bundle":"https://pith.science/pith/WYWY66P7RROBEQG345QM2LSG64/bundle.json","state":"https://pith.science/pith/WYWY66P7RROBEQG345QM2LSG64/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WYWY66P7RROBEQG345QM2LSG64/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WYWY66P7RROBEQG345QM2LSG64","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":"4183bc88bf1018f9ea3c709865a23f9f07a4b06f193a0afaeed021d8fdecb5b6","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-13T21:32:37Z","title_canon_sha256":"cbdebbc848b83d858f606460fda160d0911281c59f3a448e9a1aaf5a84b60c65"},"schema_version":"1.0","source":{"id":"2311.07766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07766","created_at":"2026-07-05T07:12:23Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07766v1","created_at":"2026-07-05T07:12:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07766","created_at":"2026-07-05T07:12:23Z"},{"alias_kind":"pith_short_12","alias_value":"WYWY66P7RROB","created_at":"2026-07-05T07:12:23Z"},{"alias_kind":"pith_short_16","alias_value":"WYWY66P7RROBEQG3","created_at":"2026-07-05T07:12:23Z"},{"alias_kind":"pith_short_8","alias_value":"WYWY66P7","created_at":"2026-07-05T07:12:23Z"}],"graph_snapshots":[{"event_id":"sha256:a06f51d5417df5d0e8a6b6e3fc30148c76a0dbb32fa147916c978feda3b4de1b","target":"graph","created_at":"2026-07-05T07:12:23Z","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/2311.07766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Integrating information from multiple modalities is arguably one of the essential prerequisites for grounding artificial intelligence systems with an understanding of the real world. Recent advances in video transformers that jointly learn from vision, text, and sound over time have made some progress toward this goal, but the degree to which these models integrate information from modalities still remains unclear. In this work, we present a promising approach for probing a pre-trained multimodal video transformer model by leveraging neuroscientific evidence of multimodal information processin","authors_text":"Dota Tianai Dong, Mariya Toneva","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-13T21:32:37Z","title":"Vision-Language Integration in Multimodal Video Transformers (Partially) Aligns with the Brain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07766","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:d28d6b081f691405e541750d5f9172a8d9ccee7e0b3aa5e7c97baf477b0217e1","target":"record","created_at":"2026-07-05T07:12:23Z","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":"4183bc88bf1018f9ea3c709865a23f9f07a4b06f193a0afaeed021d8fdecb5b6","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-13T21:32:37Z","title_canon_sha256":"cbdebbc848b83d858f606460fda160d0911281c59f3a448e9a1aaf5a84b60c65"},"schema_version":"1.0","source":{"id":"2311.07766","kind":"arxiv","version":1}},"canonical_sha256":"b62d8f79ff8c5c1240dbe760cd2e46f72ab517c010ff462a3de06db348fe8cfc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b62d8f79ff8c5c1240dbe760cd2e46f72ab517c010ff462a3de06db348fe8cfc","first_computed_at":"2026-07-05T07:12:23.429367Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:23.429367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OnbXKBwdqE4WtGqxT8AgeHg6B/pdSEnfhRBedktqT83nVchCpIInU0RGhAW2Cyye/y7WslnK/JO6R9ggvnaJBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:23.429830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d28d6b081f691405e541750d5f9172a8d9ccee7e0b3aa5e7c97baf477b0217e1","sha256:a06f51d5417df5d0e8a6b6e3fc30148c76a0dbb32fa147916c978feda3b4de1b"],"state_sha256":"69c7c0fb1cfa6ef6df854310daaba2fa616ce2fb2ccbda9e75c775f58156396f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"orPCXi1YzpAsMF3r8GfJD44H/mef7ZKQ38Yfv5Ss7L+/3D9GxvdjCR4kuZW17l+rknNz43Ted/ZafsdiXRdqAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:48:37.118886Z","bundle_sha256":"811c87005e059e482bdf97cb2fbfb3705e2096e0d8e7799ea829601a72f3b70d"}}