{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UFLH42CJ4DTXJYMGJFFP655AZD","short_pith_number":"pith:UFLH42CJ","canonical_record":{"source":{"id":"2503.02597","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T13:18:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"740bfc66993cc6fd411af7d5a73e6e208a15998810e24df9c7cc9601dedd67d5","abstract_canon_sha256":"4792b28691c338cbdf9e4a0f5dc56779d6d5ccb6ee569c5d7a4fc0ec55828a7b"},"schema_version":"1.0"},"canonical_sha256":"a1567e6849e0e774e186494aff77a0c8f7997eb17a1dce309213f42ccb45eaa6","source":{"kind":"arxiv","id":"2503.02597","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02597","created_at":"2026-05-20T00:00:18Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02597v3","created_at":"2026-05-20T00:00:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02597","created_at":"2026-05-20T00:00:18Z"},{"alias_kind":"pith_short_12","alias_value":"UFLH42CJ4DTX","created_at":"2026-05-20T00:00:18Z"},{"alias_kind":"pith_short_16","alias_value":"UFLH42CJ4DTXJYMG","created_at":"2026-05-20T00:00:18Z"},{"alias_kind":"pith_short_8","alias_value":"UFLH42CJ","created_at":"2026-05-20T00:00:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UFLH42CJ4DTXJYMGJFFP655AZD","target":"record","payload":{"canonical_record":{"source":{"id":"2503.02597","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T13:18:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"740bfc66993cc6fd411af7d5a73e6e208a15998810e24df9c7cc9601dedd67d5","abstract_canon_sha256":"4792b28691c338cbdf9e4a0f5dc56779d6d5ccb6ee569c5d7a4fc0ec55828a7b"},"schema_version":"1.0"},"canonical_sha256":"a1567e6849e0e774e186494aff77a0c8f7997eb17a1dce309213f42ccb45eaa6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:18.029213Z","signature_b64":"mXf/cxfG96+MulvE+ptxVYBxSN8R9TcDyU812E+zqTGNf1KU225GnAYCHKKTdf2Ox1c1NXIy7YcBS/hNjX+8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1567e6849e0e774e186494aff77a0c8f7997eb17a1dce309213f42ccb45eaa6","last_reissued_at":"2026-05-20T00:00:18.028445Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:18.028445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.02597","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B/dL+DgDyuBcOYuFNQ+MPjDHSLrRe/qgX3/4aYk7Ie3VnpMJMN9Uohuneh/Z1JokaMFpY1Wzwv41TlqrAJbIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:44:31.662431Z"},"content_sha256":"3306fd989bb2a34dc49ea8253ddf876396aa9459792692d2df6debee323f7b67","schema_version":"1.0","event_id":"sha256:3306fd989bb2a34dc49ea8253ddf876396aa9459792692d2df6debee323f7b67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UFLH42CJ4DTXJYMGJFFP655AZD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Helen Suzuki, Wei-Yao Wang, Yoshiyuki Kobayashi, Zhao Wang","submitted_at":"2025-03-04T13:18:33Z","abstract_excerpt":"Recent Multimodal Large Language Models (MLLMs) have demonstrated significant progress in perceiving and reasoning over multimodal inquiries, ushering in a new research era for foundation models. However, vision-language misalignment in MLLMs has emerged as a critical challenge, where the textual responses generated by these models are not factually aligned with the given text-image inputs. Existing efforts to address vision-language misalignment have focused on developing specialized vision-language connectors or leveraging visual instruction tuning from diverse domains. In this paper, we tac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02597","kind":"arxiv","version":3},"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/2503.02597/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":"2026-05-20T00:00:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AIB4Jyu8LmWf3Pi1pGWB8gbaWUR9f7TORFkjsW12pAZw8EoZpa+UrYJi2vMALf5ZfSxoATzFPJ2Kr1U9q54nCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:44:31.663007Z"},"content_sha256":"747525ca93c6327ad8d01809db8779fd3a7f620626f7a8ec24966468f4c96c23","schema_version":"1.0","event_id":"sha256:747525ca93c6327ad8d01809db8779fd3a7f620626f7a8ec24966468f4c96c23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UFLH42CJ4DTXJYMGJFFP655AZD/bundle.json","state_url":"https://pith.science/pith/UFLH42CJ4DTXJYMGJFFP655AZD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UFLH42CJ4DTXJYMGJFFP655AZD/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":"2026-05-29T15:44:31Z","links":{"resolver":"https://pith.science/pith/UFLH42CJ4DTXJYMGJFFP655AZD","bundle":"https://pith.science/pith/UFLH42CJ4DTXJYMGJFFP655AZD/bundle.json","state":"https://pith.science/pith/UFLH42CJ4DTXJYMGJFFP655AZD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UFLH42CJ4DTXJYMGJFFP655AZD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UFLH42CJ4DTXJYMGJFFP655AZD","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":"4792b28691c338cbdf9e4a0f5dc56779d6d5ccb6ee569c5d7a4fc0ec55828a7b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T13:18:33Z","title_canon_sha256":"740bfc66993cc6fd411af7d5a73e6e208a15998810e24df9c7cc9601dedd67d5"},"schema_version":"1.0","source":{"id":"2503.02597","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02597","created_at":"2026-05-20T00:00:18Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02597v3","created_at":"2026-05-20T00:00:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02597","created_at":"2026-05-20T00:00:18Z"},{"alias_kind":"pith_short_12","alias_value":"UFLH42CJ4DTX","created_at":"2026-05-20T00:00:18Z"},{"alias_kind":"pith_short_16","alias_value":"UFLH42CJ4DTXJYMG","created_at":"2026-05-20T00:00:18Z"},{"alias_kind":"pith_short_8","alias_value":"UFLH42CJ","created_at":"2026-05-20T00:00:18Z"}],"graph_snapshots":[{"event_id":"sha256:747525ca93c6327ad8d01809db8779fd3a7f620626f7a8ec24966468f4c96c23","target":"graph","created_at":"2026-05-20T00:00:18Z","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/2503.02597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Multimodal Large Language Models (MLLMs) have demonstrated significant progress in perceiving and reasoning over multimodal inquiries, ushering in a new research era for foundation models. However, vision-language misalignment in MLLMs has emerged as a critical challenge, where the textual responses generated by these models are not factually aligned with the given text-image inputs. Existing efforts to address vision-language misalignment have focused on developing specialized vision-language connectors or leveraging visual instruction tuning from diverse domains. In this paper, we tac","authors_text":"Helen Suzuki, Wei-Yao Wang, Yoshiyuki Kobayashi, Zhao Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T13:18:33Z","title":"Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02597","kind":"arxiv","version":3},"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":"sha256:3306fd989bb2a34dc49ea8253ddf876396aa9459792692d2df6debee323f7b67","target":"record","created_at":"2026-05-20T00:00:18Z","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":"4792b28691c338cbdf9e4a0f5dc56779d6d5ccb6ee569c5d7a4fc0ec55828a7b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T13:18:33Z","title_canon_sha256":"740bfc66993cc6fd411af7d5a73e6e208a15998810e24df9c7cc9601dedd67d5"},"schema_version":"1.0","source":{"id":"2503.02597","kind":"arxiv","version":3}},"canonical_sha256":"a1567e6849e0e774e186494aff77a0c8f7997eb17a1dce309213f42ccb45eaa6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1567e6849e0e774e186494aff77a0c8f7997eb17a1dce309213f42ccb45eaa6","first_computed_at":"2026-05-20T00:00:18.028445Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:18.028445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mXf/cxfG96+MulvE+ptxVYBxSN8R9TcDyU812E+zqTGNf1KU225GnAYCHKKTdf2Ox1c1NXIy7YcBS/hNjX+8DA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:18.029213Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.02597","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3306fd989bb2a34dc49ea8253ddf876396aa9459792692d2df6debee323f7b67","sha256:747525ca93c6327ad8d01809db8779fd3a7f620626f7a8ec24966468f4c96c23"],"state_sha256":"afd313ad326d02163039c86af84933c99a05f9540badafd6d6355ee3c8116a40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TyPsX93L/eEoOeNCPJ7oSpKbGQEYGABd2I3cZ3IQZI/BsX92JvBEyH6d+LPqjTq2fq4w6RcAltAzn+X9u4ulDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T15:44:31.666140Z","bundle_sha256":"67d9f5a1510dbcf23bc070602eac0564e76aae83e02b74e05fde5093327c7e61"}}