{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FUAAFOMRIX42JIWRWWTCJKDCV4","short_pith_number":"pith:FUAAFOMR","canonical_record":{"source":{"id":"2508.21430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T08:58:39Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"1b73d014435a84971cc8172b1941376f0a1a0fbc4197a68ec94d4f3c88a6233e","abstract_canon_sha256":"583d4a07cf888e360b9d7f199720267cc16b154e9e0f117963c37d3db0cc8516"},"schema_version":"1.0"},"canonical_sha256":"2d0002b99145f9a4a2d1b5a624a862af1bede2a3e7cc107e9eb13dcb5ecdaf1f","source":{"kind":"arxiv","id":"2508.21430","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21430","created_at":"2026-07-05T12:01:34Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21430v1","created_at":"2026-07-05T12:01:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21430","created_at":"2026-07-05T12:01:34Z"},{"alias_kind":"pith_short_12","alias_value":"FUAAFOMRIX42","created_at":"2026-07-05T12:01:34Z"},{"alias_kind":"pith_short_16","alias_value":"FUAAFOMRIX42JIWR","created_at":"2026-07-05T12:01:34Z"},{"alias_kind":"pith_short_8","alias_value":"FUAAFOMR","created_at":"2026-07-05T12:01:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FUAAFOMRIX42JIWRWWTCJKDCV4","target":"record","payload":{"canonical_record":{"source":{"id":"2508.21430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T08:58:39Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"1b73d014435a84971cc8172b1941376f0a1a0fbc4197a68ec94d4f3c88a6233e","abstract_canon_sha256":"583d4a07cf888e360b9d7f199720267cc16b154e9e0f117963c37d3db0cc8516"},"schema_version":"1.0"},"canonical_sha256":"2d0002b99145f9a4a2d1b5a624a862af1bede2a3e7cc107e9eb13dcb5ecdaf1f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:34.732622Z","signature_b64":"h4qSP2uLJaeplKHKIiHFIM/y/BQAYgWR0/xiFtqFO2i+XBBW8SdbSRC03LTGlyLIFh1ZFH8FMZK1Wzypqr5KCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d0002b99145f9a4a2d1b5a624a862af1bede2a3e7cc107e9eb13dcb5ecdaf1f","last_reissued_at":"2026-07-05T12:01:34.731402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:34.731402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.21430","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":"2026-07-05T12:01:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OGgj+RErT4hWwmMnOGZTdooiOnUU0bgM6D3B2wGk8ecNq+mzLhuRd9iyvtScqmE3ztqZhvB0J2UXZdROGNCcBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:54:39.217795Z"},"content_sha256":"6470d81ba9c864789d16ea8408ac7857138e7251d9b3f1850f89dab3c09e5d00","schema_version":"1.0","event_id":"sha256:6470d81ba9c864789d16ea8408ac7857138e7251d9b3f1850f89dab3c09e5d00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FUAAFOMRIX42JIWRWWTCJKDCV4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Med-RewardBench: Benchmarking Reward Models and Judges for Medical Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Cheng-Yi Li, Haiqin Zhong, Hsin-Yu Wu, Jipeng Zhang, Linlin Shen, Meidan Ding, Wei-Chieh Fang, Wenting Chen, Wenxuan Wang","submitted_at":"2025-08-29T08:58:39Z","abstract_excerpt":"Multimodal large language models (MLLMs) hold significant potential in medical applications, including disease diagnosis and clinical decision-making. However, these tasks require highly accurate, context-sensitive, and professionally aligned responses, making reliable reward models and judges critical. Despite their importance, medical reward models (MRMs) and judges remain underexplored, with no dedicated benchmarks addressing clinical requirements. Existing benchmarks focus on general MLLM capabilities or evaluate models as solvers, neglecting essential evaluation dimensions like diagnostic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21430","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/2508.21430/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":"2026-07-05T12:01:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sSq/s45J6qeRNHpNllUo/tYa04zbBNgb7bpGmkIKdfEt9LB874lAsSIJSJ7aI7Qbv1ZmQXNqrfrZ5zPfGdflCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:54:39.218463Z"},"content_sha256":"af5541d108647749c2f1477fed175e2e5a388ae87c63522fbfdd2722eaada9dd","schema_version":"1.0","event_id":"sha256:af5541d108647749c2f1477fed175e2e5a388ae87c63522fbfdd2722eaada9dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FUAAFOMRIX42JIWRWWTCJKDCV4/bundle.json","state_url":"https://pith.science/pith/FUAAFOMRIX42JIWRWWTCJKDCV4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FUAAFOMRIX42JIWRWWTCJKDCV4/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":"2026-07-07T04:54:39Z","links":{"resolver":"https://pith.science/pith/FUAAFOMRIX42JIWRWWTCJKDCV4","bundle":"https://pith.science/pith/FUAAFOMRIX42JIWRWWTCJKDCV4/bundle.json","state":"https://pith.science/pith/FUAAFOMRIX42JIWRWWTCJKDCV4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FUAAFOMRIX42JIWRWWTCJKDCV4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FUAAFOMRIX42JIWRWWTCJKDCV4","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":"583d4a07cf888e360b9d7f199720267cc16b154e9e0f117963c37d3db0cc8516","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T08:58:39Z","title_canon_sha256":"1b73d014435a84971cc8172b1941376f0a1a0fbc4197a68ec94d4f3c88a6233e"},"schema_version":"1.0","source":{"id":"2508.21430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21430","created_at":"2026-07-05T12:01:34Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21430v1","created_at":"2026-07-05T12:01:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21430","created_at":"2026-07-05T12:01:34Z"},{"alias_kind":"pith_short_12","alias_value":"FUAAFOMRIX42","created_at":"2026-07-05T12:01:34Z"},{"alias_kind":"pith_short_16","alias_value":"FUAAFOMRIX42JIWR","created_at":"2026-07-05T12:01:34Z"},{"alias_kind":"pith_short_8","alias_value":"FUAAFOMR","created_at":"2026-07-05T12:01:34Z"}],"graph_snapshots":[{"event_id":"sha256:af5541d108647749c2f1477fed175e2e5a388ae87c63522fbfdd2722eaada9dd","target":"graph","created_at":"2026-07-05T12:01:34Z","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/2508.21430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) hold significant potential in medical applications, including disease diagnosis and clinical decision-making. However, these tasks require highly accurate, context-sensitive, and professionally aligned responses, making reliable reward models and judges critical. Despite their importance, medical reward models (MRMs) and judges remain underexplored, with no dedicated benchmarks addressing clinical requirements. Existing benchmarks focus on general MLLM capabilities or evaluate models as solvers, neglecting essential evaluation dimensions like diagnostic","authors_text":"Cheng-Yi Li, Haiqin Zhong, Hsin-Yu Wu, Jipeng Zhang, Linlin Shen, Meidan Ding, Wei-Chieh Fang, Wenting Chen, Wenxuan Wang","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T08:58:39Z","title":"Med-RewardBench: Benchmarking Reward Models and Judges for Medical Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21430","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":"sha256:6470d81ba9c864789d16ea8408ac7857138e7251d9b3f1850f89dab3c09e5d00","target":"record","created_at":"2026-07-05T12:01:34Z","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":"583d4a07cf888e360b9d7f199720267cc16b154e9e0f117963c37d3db0cc8516","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T08:58:39Z","title_canon_sha256":"1b73d014435a84971cc8172b1941376f0a1a0fbc4197a68ec94d4f3c88a6233e"},"schema_version":"1.0","source":{"id":"2508.21430","kind":"arxiv","version":1}},"canonical_sha256":"2d0002b99145f9a4a2d1b5a624a862af1bede2a3e7cc107e9eb13dcb5ecdaf1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d0002b99145f9a4a2d1b5a624a862af1bede2a3e7cc107e9eb13dcb5ecdaf1f","first_computed_at":"2026-07-05T12:01:34.731402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:34.731402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h4qSP2uLJaeplKHKIiHFIM/y/BQAYgWR0/xiFtqFO2i+XBBW8SdbSRC03LTGlyLIFh1ZFH8FMZK1Wzypqr5KCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:34.732622Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6470d81ba9c864789d16ea8408ac7857138e7251d9b3f1850f89dab3c09e5d00","sha256:af5541d108647749c2f1477fed175e2e5a388ae87c63522fbfdd2722eaada9dd"],"state_sha256":"46e821c92d1128166e21dd94b61c0a6b75543386c38dee7c36cc68cf1523dffa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PEdnhUB0+U/XjeS4uYD6OkTwzNGdErzerSPqVaJJCazLTWZkZDXTaa2353h2ZyJGiDzn4TCti6nm1Ih9vVilAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:54:39.222346Z","bundle_sha256":"cabda17a484ca6e37cd3b619814f697afa054c09a364d9dfabe7d2f6aa765b87"}}