{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GDDTOX6MEWUYRHKVHWALPFFR6T","short_pith_number":"pith:GDDTOX6M","canonical_record":{"source":{"id":"2412.04903","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T09:59:47Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"1733356ddd25efca0595e32219068a749b581a91c9bc0029131fc318ef8014e1","abstract_canon_sha256":"36e417e90df3ac37ae3f54f2426209b664fecd5cab83f665693b1c1703e2794d"},"schema_version":"1.0"},"canonical_sha256":"30c7375fcc25a9889d553d80b794b1f4c4889da75b77742a4cf30edecbcf6881","source":{"kind":"arxiv","id":"2412.04903","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04903","created_at":"2026-07-05T09:49:47Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04903v2","created_at":"2026-07-05T09:49:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04903","created_at":"2026-07-05T09:49:47Z"},{"alias_kind":"pith_short_12","alias_value":"GDDTOX6MEWUY","created_at":"2026-07-05T09:49:47Z"},{"alias_kind":"pith_short_16","alias_value":"GDDTOX6MEWUYRHKV","created_at":"2026-07-05T09:49:47Z"},{"alias_kind":"pith_short_8","alias_value":"GDDTOX6M","created_at":"2026-07-05T09:49:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GDDTOX6MEWUYRHKVHWALPFFR6T","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04903","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T09:59:47Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"1733356ddd25efca0595e32219068a749b581a91c9bc0029131fc318ef8014e1","abstract_canon_sha256":"36e417e90df3ac37ae3f54f2426209b664fecd5cab83f665693b1c1703e2794d"},"schema_version":"1.0"},"canonical_sha256":"30c7375fcc25a9889d553d80b794b1f4c4889da75b77742a4cf30edecbcf6881","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:47.143092Z","signature_b64":"3mcv5NGirAFoU6p8dTnE/x70AYBYPCvxs7aqnTQ6nDLIPlM8SymNBfi+VmGY40xbAkVz2/kSqSC64TMv5aNsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30c7375fcc25a9889d553d80b794b1f4c4889da75b77742a4cf30edecbcf6881","last_reissued_at":"2026-07-05T09:49:47.142581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:47.142581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04903","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":"2026-07-05T09:49:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OG6d4DU4td2kk3HHXDUWJFKI0GlfL2RZw1wYrZmbTkCFcD+wAQS6X5UmbTxEMJuLXi6Hi0lgJuu+tYukBd1mDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:18:00.547902Z"},"content_sha256":"d882d44c5e3b6c53fb35b4000379e3a0d4900c4e25c4717f572fc592b372599d","schema_version":"1.0","event_id":"sha256:d882d44c5e3b6c53fb35b4000379e3a0d4900c4e25c4717f572fc592b372599d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GDDTOX6MEWUYRHKVHWALPFFR6T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EACO: Enhancing Alignment in Multimodal LLMs via Critical Observation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Haokun Lin, Jin Jiang, Liang Ma, Meng Cao, Mingfei Han, Xiaodan Liang, Yongxin Wang, Yuhao Cheng","submitted_at":"2024-12-06T09:59:47Z","abstract_excerpt":"Multimodal large language models (MLLMs) have achieved remarkable progress on various visual question answering and reasoning tasks leveraging instruction fine-tuning specific datasets. They can also learn from preference data annotated by human to enhance their reasoning ability and mitigate hallucinations. Most of preference data is generated from the model itself. However, existing methods require high-quality critical labels, which are costly and rely on human or proprietary models like GPT-4V. In this work, we propose Enhancing Alignment in MLLMs via Critical Observation (EACO), which ali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04903","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/2412.04903/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":"2026-07-05T09:49:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v+jNIKA2DI7XLacQMszyD+eYA0irXO0fRI1IUBIqEzVBnz0WVRELswUzujgl+n0vL1cmO2ucYCzC6EnsjVUvDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:18:00.548788Z"},"content_sha256":"7db778da88a9bb811d0410e3c738e974fa3f94e7fc02657a084619f4d392f9f6","schema_version":"1.0","event_id":"sha256:7db778da88a9bb811d0410e3c738e974fa3f94e7fc02657a084619f4d392f9f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GDDTOX6MEWUYRHKVHWALPFFR6T/bundle.json","state_url":"https://pith.science/pith/GDDTOX6MEWUYRHKVHWALPFFR6T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GDDTOX6MEWUYRHKVHWALPFFR6T/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":"2026-08-13T13:18:00Z","links":{"resolver":"https://pith.science/pith/GDDTOX6MEWUYRHKVHWALPFFR6T","bundle":"https://pith.science/pith/GDDTOX6MEWUYRHKVHWALPFFR6T/bundle.json","state":"https://pith.science/pith/GDDTOX6MEWUYRHKVHWALPFFR6T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GDDTOX6MEWUYRHKVHWALPFFR6T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GDDTOX6MEWUYRHKVHWALPFFR6T","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":"36e417e90df3ac37ae3f54f2426209b664fecd5cab83f665693b1c1703e2794d","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T09:59:47Z","title_canon_sha256":"1733356ddd25efca0595e32219068a749b581a91c9bc0029131fc318ef8014e1"},"schema_version":"1.0","source":{"id":"2412.04903","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04903","created_at":"2026-07-05T09:49:47Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04903v2","created_at":"2026-07-05T09:49:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04903","created_at":"2026-07-05T09:49:47Z"},{"alias_kind":"pith_short_12","alias_value":"GDDTOX6MEWUY","created_at":"2026-07-05T09:49:47Z"},{"alias_kind":"pith_short_16","alias_value":"GDDTOX6MEWUYRHKV","created_at":"2026-07-05T09:49:47Z"},{"alias_kind":"pith_short_8","alias_value":"GDDTOX6M","created_at":"2026-07-05T09:49:47Z"}],"graph_snapshots":[{"event_id":"sha256:7db778da88a9bb811d0410e3c738e974fa3f94e7fc02657a084619f4d392f9f6","target":"graph","created_at":"2026-07-05T09:49:47Z","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/2412.04903/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have achieved remarkable progress on various visual question answering and reasoning tasks leveraging instruction fine-tuning specific datasets. They can also learn from preference data annotated by human to enhance their reasoning ability and mitigate hallucinations. Most of preference data is generated from the model itself. However, existing methods require high-quality critical labels, which are costly and rely on human or proprietary models like GPT-4V. In this work, we propose Enhancing Alignment in MLLMs via Critical Observation (EACO), which ali","authors_text":"Haokun Lin, Jin Jiang, Liang Ma, Meng Cao, Mingfei Han, Xiaodan Liang, Yongxin Wang, Yuhao Cheng","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T09:59:47Z","title":"EACO: Enhancing Alignment in Multimodal LLMs via Critical Observation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04903","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:d882d44c5e3b6c53fb35b4000379e3a0d4900c4e25c4717f572fc592b372599d","target":"record","created_at":"2026-07-05T09:49:47Z","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":"36e417e90df3ac37ae3f54f2426209b664fecd5cab83f665693b1c1703e2794d","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T09:59:47Z","title_canon_sha256":"1733356ddd25efca0595e32219068a749b581a91c9bc0029131fc318ef8014e1"},"schema_version":"1.0","source":{"id":"2412.04903","kind":"arxiv","version":2}},"canonical_sha256":"30c7375fcc25a9889d553d80b794b1f4c4889da75b77742a4cf30edecbcf6881","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30c7375fcc25a9889d553d80b794b1f4c4889da75b77742a4cf30edecbcf6881","first_computed_at":"2026-07-05T09:49:47.142581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:47.142581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3mcv5NGirAFoU6p8dTnE/x70AYBYPCvxs7aqnTQ6nDLIPlM8SymNBfi+VmGY40xbAkVz2/kSqSC64TMv5aNsCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:47.143092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04903","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d882d44c5e3b6c53fb35b4000379e3a0d4900c4e25c4717f572fc592b372599d","sha256:7db778da88a9bb811d0410e3c738e974fa3f94e7fc02657a084619f4d392f9f6"],"state_sha256":"b7a29bc9eb5a8693f82d700753e5a3a4a758379e7b61b51b98cb66de1642f992"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pDpI/NEOG7fOzLmAY7tKLrkrn8gbki2x1awwN793uHmRj8YVTSN5L9DYOceHopzfWL+4gQOnvWT625MdCfhsDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T13:18:00.560502Z","bundle_sha256":"c583867c5a9afa4a70525f702cc27e366400719c47a16d9aa07fb179d569df0d"}}