{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ICL5P7LY6GM4EBISHVHITLFVIC","short_pith_number":"pith:ICL5P7LY","canonical_record":{"source":{"id":"2410.14148","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-18T03:34:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e8a1d69643f2ca6374042d6b3a178ef887dabf93752e107d3df4f965a84dffcc","abstract_canon_sha256":"36c44db0a954eba45d64da8ff0f2e57fc8051a47846109a4df90272a1ab7fdd4"},"schema_version":"1.0"},"canonical_sha256":"4097d7fd78f199c205123d4e89acb5409b0c5566446afa744179aea5912de5ec","source":{"kind":"arxiv","id":"2410.14148","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14148","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14148v4","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14148","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"pith_short_12","alias_value":"ICL5P7LY6GM4","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"pith_short_16","alias_value":"ICL5P7LY6GM4EBIS","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"pith_short_8","alias_value":"ICL5P7LY","created_at":"2026-07-05T10:51:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ICL5P7LY6GM4EBISHVHITLFVIC","target":"record","payload":{"canonical_record":{"source":{"id":"2410.14148","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-18T03:34:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e8a1d69643f2ca6374042d6b3a178ef887dabf93752e107d3df4f965a84dffcc","abstract_canon_sha256":"36c44db0a954eba45d64da8ff0f2e57fc8051a47846109a4df90272a1ab7fdd4"},"schema_version":"1.0"},"canonical_sha256":"4097d7fd78f199c205123d4e89acb5409b0c5566446afa744179aea5912de5ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:26.752564Z","signature_b64":"GdFTVDkCgzLNEGs3SmhWN8WdU/jPSidBfXw4EdufMTHAlv07XUnGFcDZCA04lkXMMizzJhF8sm1kcz7GhIvyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4097d7fd78f199c205123d4e89acb5409b0c5566446afa744179aea5912de5ec","last_reissued_at":"2026-07-05T10:51:26.752083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:26.752083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.14148","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:51:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fl0KJxJ2PPRfbYPn234GuKclELi4t/N8EQhwqYA16g5D3x84XxZs2UzJHHZcSdm2MUZYsnHCKte1UpoeD4ocBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:03:56.604425Z"},"content_sha256":"72ab7e9b2778393440ef142c8522e58fa9ca5259534ac90e80586267b815b597","schema_version":"1.0","event_id":"sha256:72ab7e9b2778393440ef142c8522e58fa9ca5259534ac90e80586267b815b597"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ICL5P7LY6GM4EBISHVHITLFVIC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"An Zhang, Chenhang Cui, Gelei Deng, Huaxiu Yao, Tat-Seng Chua, Yiyang Zhou, Zhaorun Chen","submitted_at":"2024-10-18T03:34:32Z","abstract_excerpt":"The recent advancements in large language models (LLMs) and pre-trained vision models have accelerated the development of vision-language large models (VLLMs), enhancing the interaction between visual and linguistic modalities. Despite their notable success across various domains, VLLMs face challenges in modality alignment, which can lead to issues like hallucinations and unsafe content generation. Current alignment techniques often rely on coarse feedback and external datasets, limiting scalability and performance. In this paper, we propose FiSAO (Fine-Grained Self-Alignment Optimization), a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14148","kind":"arxiv","version":4},"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/2410.14148/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":"2026-07-05T10:51:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PHRv+EAaMOsv1mvFh6H4ZUSEGuhiGS1KIFGUl6MzUCK46kGB1gOODiEIhZgF0wWvl8S8eLTGoOzV+dUympHSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:03:56.605049Z"},"content_sha256":"d8523df58bb6ae75b0d9066ad6131bf1f6900fae3b06cc946cb95d96ab608baa","schema_version":"1.0","event_id":"sha256:d8523df58bb6ae75b0d9066ad6131bf1f6900fae3b06cc946cb95d96ab608baa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ICL5P7LY6GM4EBISHVHITLFVIC/bundle.json","state_url":"https://pith.science/pith/ICL5P7LY6GM4EBISHVHITLFVIC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ICL5P7LY6GM4EBISHVHITLFVIC/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":"2026-08-04T17:03:56Z","links":{"resolver":"https://pith.science/pith/ICL5P7LY6GM4EBISHVHITLFVIC","bundle":"https://pith.science/pith/ICL5P7LY6GM4EBISHVHITLFVIC/bundle.json","state":"https://pith.science/pith/ICL5P7LY6GM4EBISHVHITLFVIC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ICL5P7LY6GM4EBISHVHITLFVIC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ICL5P7LY6GM4EBISHVHITLFVIC","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":"36c44db0a954eba45d64da8ff0f2e57fc8051a47846109a4df90272a1ab7fdd4","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-18T03:34:32Z","title_canon_sha256":"e8a1d69643f2ca6374042d6b3a178ef887dabf93752e107d3df4f965a84dffcc"},"schema_version":"1.0","source":{"id":"2410.14148","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14148","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14148v4","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14148","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"pith_short_12","alias_value":"ICL5P7LY6GM4","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"pith_short_16","alias_value":"ICL5P7LY6GM4EBIS","created_at":"2026-07-05T10:51:26Z"},{"alias_kind":"pith_short_8","alias_value":"ICL5P7LY","created_at":"2026-07-05T10:51:26Z"}],"graph_snapshots":[{"event_id":"sha256:d8523df58bb6ae75b0d9066ad6131bf1f6900fae3b06cc946cb95d96ab608baa","target":"graph","created_at":"2026-07-05T10:51:26Z","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/2410.14148/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent advancements in large language models (LLMs) and pre-trained vision models have accelerated the development of vision-language large models (VLLMs), enhancing the interaction between visual and linguistic modalities. Despite their notable success across various domains, VLLMs face challenges in modality alignment, which can lead to issues like hallucinations and unsafe content generation. Current alignment techniques often rely on coarse feedback and external datasets, limiting scalability and performance. In this paper, we propose FiSAO (Fine-Grained Self-Alignment Optimization), a","authors_text":"An Zhang, Chenhang Cui, Gelei Deng, Huaxiu Yao, Tat-Seng Chua, Yiyang Zhou, Zhaorun Chen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-18T03:34:32Z","title":"Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14148","kind":"arxiv","version":4},"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":"sha256:72ab7e9b2778393440ef142c8522e58fa9ca5259534ac90e80586267b815b597","target":"record","created_at":"2026-07-05T10:51:26Z","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":"36c44db0a954eba45d64da8ff0f2e57fc8051a47846109a4df90272a1ab7fdd4","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-18T03:34:32Z","title_canon_sha256":"e8a1d69643f2ca6374042d6b3a178ef887dabf93752e107d3df4f965a84dffcc"},"schema_version":"1.0","source":{"id":"2410.14148","kind":"arxiv","version":4}},"canonical_sha256":"4097d7fd78f199c205123d4e89acb5409b0c5566446afa744179aea5912de5ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4097d7fd78f199c205123d4e89acb5409b0c5566446afa744179aea5912de5ec","first_computed_at":"2026-07-05T10:51:26.752083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:26.752083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GdFTVDkCgzLNEGs3SmhWN8WdU/jPSidBfXw4EdufMTHAlv07XUnGFcDZCA04lkXMMizzJhF8sm1kcz7GhIvyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:26.752564Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.14148","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72ab7e9b2778393440ef142c8522e58fa9ca5259534ac90e80586267b815b597","sha256:d8523df58bb6ae75b0d9066ad6131bf1f6900fae3b06cc946cb95d96ab608baa"],"state_sha256":"d289af271168419103cf8a6c682a57b3866eb3e3880aa1e9df1ea1df6314b6fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s8IOye2+EvKMZxNlpymHNWFx+BmI3/j/rlx1akzn7qOyLCqOpQ4EDtty8qzv7PS3MeYdeyq+ftEGH7ivsBXQAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:03:56.609745Z","bundle_sha256":"f90fd3192fc3fef7f44d199ee4aed75a346bfce084d39bb2b9ebe0194f3db3b4"}}