{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:75K2LPHQORUZOZR473KDNN3IRV","short_pith_number":"pith:75K2LPHQ","canonical_record":{"source":{"id":"2502.14191","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T01:48:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5cb54b92895b3a033dd568edbeff64fe13959adff57f28f4013b951e2ba2df80","abstract_canon_sha256":"d3597e6849a81489f1ebc9aae164abc142e07dae1d4a94927d51a8ee1f721f3c"},"schema_version":"1.0"},"canonical_sha256":"ff55a5bcf0746997663cfed436b7688d4c524c88df7bb9ecabd2a852ad4595bf","source":{"kind":"arxiv","id":"2502.14191","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14191","created_at":"2026-07-05T10:17:22Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14191v1","created_at":"2026-07-05T10:17:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14191","created_at":"2026-07-05T10:17:22Z"},{"alias_kind":"pith_short_12","alias_value":"75K2LPHQORUZ","created_at":"2026-07-05T10:17:22Z"},{"alias_kind":"pith_short_16","alias_value":"75K2LPHQORUZOZR4","created_at":"2026-07-05T10:17:22Z"},{"alias_kind":"pith_short_8","alias_value":"75K2LPHQ","created_at":"2026-07-05T10:17:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:75K2LPHQORUZOZR473KDNN3IRV","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14191","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T01:48:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5cb54b92895b3a033dd568edbeff64fe13959adff57f28f4013b951e2ba2df80","abstract_canon_sha256":"d3597e6849a81489f1ebc9aae164abc142e07dae1d4a94927d51a8ee1f721f3c"},"schema_version":"1.0"},"canonical_sha256":"ff55a5bcf0746997663cfed436b7688d4c524c88df7bb9ecabd2a852ad4595bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:22.464800Z","signature_b64":"bUV/3MRt6XDbKXZgb+BTjIqmM+C53+0N3Zc9q/rGdIBct2W2OKIulItSivtkl4AR3OGPPMDuaHl5C54zUzPGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff55a5bcf0746997663cfed436b7688d4c524c88df7bb9ecabd2a852ad4595bf","last_reissued_at":"2026-07-05T10:17:22.464177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:22.464177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14191","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":"2026-07-05T10:17:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ge24L5qtfE08B1DJbXCttcRD4JOTKLK/WuwEUcd1ViO0N/jSmW4rUuqh8wHujVwd7SoMRju7Z6U4FQFmWM96AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:41:13.708337Z"},"content_sha256":"45133ab405556937d0f4171d0aef7424a94b3af035397d8a99b36c39f161f791","schema_version":"1.0","event_id":"sha256:45133ab405556937d0f4171d0aef7424a94b3af035397d8a99b36c39f161f791"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:75K2LPHQORUZOZR473KDNN3IRV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Luke Zettlemoyer, Marjan Ghazvininejad, Michihiro Yasunaga","submitted_at":"2025-02-20T01:48:13Z","abstract_excerpt":"Reward models play an essential role in training vision-language models (VLMs) by assessing output quality to enable aligning with human preferences. Despite their importance, the research community lacks comprehensive open benchmarks for evaluating multimodal reward models in VLMs. To address this gap, we introduce Multimodal RewardBench, an expert-annotated benchmark covering six domains: general correctness, preference, knowledge, reasoning, safety, and visual question-answering. Our dataset comprises 5,211 annotated (prompt, chosen response, rejected response) triplets collected from vario"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14191","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/2502.14191/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":"2026-07-05T10:17:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BtzB5J4oHQ5KtAzFzbuyqZpBsyDPg1/4/1ML97EFfOC12aDCU5mIurxPREyXY4LnuJFU9BjzUkzdO7CjkrUSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:41:13.708930Z"},"content_sha256":"93ef2d41b47a8d361636e1a5fb560ad2109dbecf8402f9d33c931f383de36070","schema_version":"1.0","event_id":"sha256:93ef2d41b47a8d361636e1a5fb560ad2109dbecf8402f9d33c931f383de36070"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/75K2LPHQORUZOZR473KDNN3IRV/bundle.json","state_url":"https://pith.science/pith/75K2LPHQORUZOZR473KDNN3IRV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/75K2LPHQORUZOZR473KDNN3IRV/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":"2026-08-04T12:41:13Z","links":{"resolver":"https://pith.science/pith/75K2LPHQORUZOZR473KDNN3IRV","bundle":"https://pith.science/pith/75K2LPHQORUZOZR473KDNN3IRV/bundle.json","state":"https://pith.science/pith/75K2LPHQORUZOZR473KDNN3IRV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/75K2LPHQORUZOZR473KDNN3IRV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:75K2LPHQORUZOZR473KDNN3IRV","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":"d3597e6849a81489f1ebc9aae164abc142e07dae1d4a94927d51a8ee1f721f3c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T01:48:13Z","title_canon_sha256":"5cb54b92895b3a033dd568edbeff64fe13959adff57f28f4013b951e2ba2df80"},"schema_version":"1.0","source":{"id":"2502.14191","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14191","created_at":"2026-07-05T10:17:22Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14191v1","created_at":"2026-07-05T10:17:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14191","created_at":"2026-07-05T10:17:22Z"},{"alias_kind":"pith_short_12","alias_value":"75K2LPHQORUZ","created_at":"2026-07-05T10:17:22Z"},{"alias_kind":"pith_short_16","alias_value":"75K2LPHQORUZOZR4","created_at":"2026-07-05T10:17:22Z"},{"alias_kind":"pith_short_8","alias_value":"75K2LPHQ","created_at":"2026-07-05T10:17:22Z"}],"graph_snapshots":[{"event_id":"sha256:93ef2d41b47a8d361636e1a5fb560ad2109dbecf8402f9d33c931f383de36070","target":"graph","created_at":"2026-07-05T10:17:22Z","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/2502.14191/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward models play an essential role in training vision-language models (VLMs) by assessing output quality to enable aligning with human preferences. Despite their importance, the research community lacks comprehensive open benchmarks for evaluating multimodal reward models in VLMs. To address this gap, we introduce Multimodal RewardBench, an expert-annotated benchmark covering six domains: general correctness, preference, knowledge, reasoning, safety, and visual question-answering. Our dataset comprises 5,211 annotated (prompt, chosen response, rejected response) triplets collected from vario","authors_text":"Luke Zettlemoyer, Marjan Ghazvininejad, Michihiro Yasunaga","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T01:48:13Z","title":"Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14191","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":"sha256:45133ab405556937d0f4171d0aef7424a94b3af035397d8a99b36c39f161f791","target":"record","created_at":"2026-07-05T10:17:22Z","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":"d3597e6849a81489f1ebc9aae164abc142e07dae1d4a94927d51a8ee1f721f3c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T01:48:13Z","title_canon_sha256":"5cb54b92895b3a033dd568edbeff64fe13959adff57f28f4013b951e2ba2df80"},"schema_version":"1.0","source":{"id":"2502.14191","kind":"arxiv","version":1}},"canonical_sha256":"ff55a5bcf0746997663cfed436b7688d4c524c88df7bb9ecabd2a852ad4595bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff55a5bcf0746997663cfed436b7688d4c524c88df7bb9ecabd2a852ad4595bf","first_computed_at":"2026-07-05T10:17:22.464177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:22.464177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bUV/3MRt6XDbKXZgb+BTjIqmM+C53+0N3Zc9q/rGdIBct2W2OKIulItSivtkl4AR3OGPPMDuaHl5C54zUzPGDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:22.464800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14191","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45133ab405556937d0f4171d0aef7424a94b3af035397d8a99b36c39f161f791","sha256:93ef2d41b47a8d361636e1a5fb560ad2109dbecf8402f9d33c931f383de36070"],"state_sha256":"28a7389f17cb59b279f08acf92b1a4c7d7d80986c17d0a3f7cc4306d2ecb3c95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KP9d6LpFIBIwWtXvUQ7mABze/rksRx/GSViiarzQWB+paq5LDihaxi6QJBwV1xu0yg8NRAXNhrNU3VtvppHRDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:41:13.717864Z","bundle_sha256":"446131651c8ad2afc94ea42443db94403e01ebaae41f7509c0cba758ded9f5c5"}}