{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XZGKK6QSK6DNQ5B2ODSN3UY3CN","short_pith_number":"pith:XZGKK6QS","canonical_record":{"source":{"id":"2503.14504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"91fb2f9d37e1c2495f27d02a2711b154acfacff02d0d74a20d4e3696dd7b65f9","abstract_canon_sha256":"3bdc0fcf082b38374d3e539ad56b9e4cbfcf797b834365b8e3f16235da7b5923"},"schema_version":"1.0"},"canonical_sha256":"be4ca57a125786d8743a70e4ddd31b134d7ca91dcce980b00ea127f82941f3f0","source":{"kind":"arxiv","id":"2503.14504","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14504","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14504v2","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14504","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"pith_short_12","alias_value":"XZGKK6QSK6DN","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"pith_short_16","alias_value":"XZGKK6QSK6DNQ5B2","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"pith_short_8","alias_value":"XZGKK6QS","created_at":"2026-07-05T10:37:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XZGKK6QSK6DNQ5B2ODSN3UY3CN","target":"record","payload":{"canonical_record":{"source":{"id":"2503.14504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"91fb2f9d37e1c2495f27d02a2711b154acfacff02d0d74a20d4e3696dd7b65f9","abstract_canon_sha256":"3bdc0fcf082b38374d3e539ad56b9e4cbfcf797b834365b8e3f16235da7b5923"},"schema_version":"1.0"},"canonical_sha256":"be4ca57a125786d8743a70e4ddd31b134d7ca91dcce980b00ea127f82941f3f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:47.943854Z","signature_b64":"yS24luuncnAk61qeQ5xaS9A1ps5pzQEJ0LHORWUUmVGsZPFG10XXaiQwUX0mOEnU7EMvvShmSxPpMLVPY82MAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be4ca57a125786d8743a70e4ddd31b134d7ca91dcce980b00ea127f82941f3f0","last_reissued_at":"2026-07-05T10:37:47.943308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:47.943308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.14504","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":"2026-07-05T10:37:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aj0FhlobRc1tVhal4slaEvVhjlZNXArngT9Bd/iqAheTp9/jYLHgrVBurghX3wSbwH+MifEDSxq7YUAOA+jQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T11:42:11.572262Z"},"content_sha256":"8aa13e79430a3c430af4882a60d69831f78bec83749a2b5b68dbbde2204b9cee","schema_version":"1.0","event_id":"sha256:8aa13e79430a3c430af4882a60d69831f78bec83749a2b5b68dbbde2204b9cee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XZGKK6QSK6DNQ5B2ODSN3UY3CN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Multimodal LLM with Human Preference: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoyou Fu, Dingjie Song, Guibin Zhang, Jinda Lu, Junkang Wu, Kun Wang, Liang Wang, Qingsong Wen, Tao Yu, Tianlong Xu, Tieniu Tan, Xingyu Lu, Yan Huang, Yibo Yan, Yi-Fan Zhang, Yunhang Shen, Zhang Zhang","submitted_at":"2025-03-18T17:59:56Z","abstract_excerpt":"Large language models (LLMs) can handle a wide variety of general tasks with simple prompts, without the need for task-specific training. Multimodal Large Language Models (MLLMs), built upon LLMs, have demonstrated impressive potential in tackling complex tasks involving visual, auditory, and textual data. However, critical issues related to truthfulness, safety, o1-like reasoning, and alignment with human preference remain insufficiently addressed. This gap has spurred the emergence of various alignment algorithms, each targeting different application scenarios and optimization goals. Recent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14504","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/2503.14504/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":"2026-07-05T10:37:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2RFENIRST1HC1Hzh08tSooUU4JgX9ALVpmV8R8ZenfM/siVNgewft1tjwAruIjvAyxTiYbNEV/KEafjhegluDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T11:42:11.573096Z"},"content_sha256":"127c1a91910dd75ad4b24394ef3e8f5261f0bded9c934571c5334e6640232185","schema_version":"1.0","event_id":"sha256:127c1a91910dd75ad4b24394ef3e8f5261f0bded9c934571c5334e6640232185"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XZGKK6QSK6DNQ5B2ODSN3UY3CN/bundle.json","state_url":"https://pith.science/pith/XZGKK6QSK6DNQ5B2ODSN3UY3CN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XZGKK6QSK6DNQ5B2ODSN3UY3CN/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":"2026-08-22T11:42:11Z","links":{"resolver":"https://pith.science/pith/XZGKK6QSK6DNQ5B2ODSN3UY3CN","bundle":"https://pith.science/pith/XZGKK6QSK6DNQ5B2ODSN3UY3CN/bundle.json","state":"https://pith.science/pith/XZGKK6QSK6DNQ5B2ODSN3UY3CN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XZGKK6QSK6DNQ5B2ODSN3UY3CN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XZGKK6QSK6DNQ5B2ODSN3UY3CN","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":"3bdc0fcf082b38374d3e539ad56b9e4cbfcf797b834365b8e3f16235da7b5923","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T17:59:56Z","title_canon_sha256":"91fb2f9d37e1c2495f27d02a2711b154acfacff02d0d74a20d4e3696dd7b65f9"},"schema_version":"1.0","source":{"id":"2503.14504","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14504","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14504v2","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14504","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"pith_short_12","alias_value":"XZGKK6QSK6DN","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"pith_short_16","alias_value":"XZGKK6QSK6DNQ5B2","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"pith_short_8","alias_value":"XZGKK6QS","created_at":"2026-07-05T10:37:47Z"}],"graph_snapshots":[{"event_id":"sha256:127c1a91910dd75ad4b24394ef3e8f5261f0bded9c934571c5334e6640232185","target":"graph","created_at":"2026-07-05T10:37:47Z","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/2503.14504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) can handle a wide variety of general tasks with simple prompts, without the need for task-specific training. Multimodal Large Language Models (MLLMs), built upon LLMs, have demonstrated impressive potential in tackling complex tasks involving visual, auditory, and textual data. However, critical issues related to truthfulness, safety, o1-like reasoning, and alignment with human preference remain insufficiently addressed. This gap has spurred the emergence of various alignment algorithms, each targeting different application scenarios and optimization goals. Recent ","authors_text":"Chaoyou Fu, Dingjie Song, Guibin Zhang, Jinda Lu, Junkang Wu, Kun Wang, Liang Wang, Qingsong Wen, Tao Yu, Tianlong Xu, Tieniu Tan, Xingyu Lu, Yan Huang, Yibo Yan, Yi-Fan Zhang, Yunhang Shen, Zhang Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T17:59:56Z","title":"Aligning Multimodal LLM with Human Preference: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14504","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":"sha256:8aa13e79430a3c430af4882a60d69831f78bec83749a2b5b68dbbde2204b9cee","target":"record","created_at":"2026-07-05T10:37:47Z","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":"3bdc0fcf082b38374d3e539ad56b9e4cbfcf797b834365b8e3f16235da7b5923","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T17:59:56Z","title_canon_sha256":"91fb2f9d37e1c2495f27d02a2711b154acfacff02d0d74a20d4e3696dd7b65f9"},"schema_version":"1.0","source":{"id":"2503.14504","kind":"arxiv","version":2}},"canonical_sha256":"be4ca57a125786d8743a70e4ddd31b134d7ca91dcce980b00ea127f82941f3f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be4ca57a125786d8743a70e4ddd31b134d7ca91dcce980b00ea127f82941f3f0","first_computed_at":"2026-07-05T10:37:47.943308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:47.943308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yS24luuncnAk61qeQ5xaS9A1ps5pzQEJ0LHORWUUmVGsZPFG10XXaiQwUX0mOEnU7EMvvShmSxPpMLVPY82MAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:47.943854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.14504","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8aa13e79430a3c430af4882a60d69831f78bec83749a2b5b68dbbde2204b9cee","sha256:127c1a91910dd75ad4b24394ef3e8f5261f0bded9c934571c5334e6640232185"],"state_sha256":"e1c3043ed49e9576f1fca3308b71857db8e1dcd264364cfb4c883db01a55d232"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hOJJHxPy4X52ZU+SW6J0p+ecoTu6nvDvlw/bMIJIPGUsGVwK2txBmhLxjbCx0jI7G9KiLqntwhE0xbEj8ZYZCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T11:42:11.577454Z","bundle_sha256":"1856919218ad2beb4e39c364712747c00495b36b9dedf479fab0974762dc93c9"}}