{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:P5BISNESQOLX4PHRQJLHZY5N6T","short_pith_number":"pith:P5BISNES","canonical_record":{"source":{"id":"2603.00546","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-28T08:49:22Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"627ed7dad6c2b2d21d3f34097eeba0fffe7e8a3f47ca88c15d7150800ce22874","abstract_canon_sha256":"6676fd32e621c57d14c772ab76e0ab3271620de548f26369db1bb5400b2ceabc"},"schema_version":"1.0"},"canonical_sha256":"7f4289349283977e3cf182567ce3adf4fe9ed88dca0693cafa8a03f82ff509b3","source":{"kind":"arxiv","id":"2603.00546","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.00546","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"arxiv_version","alias_value":"2603.00546v2","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00546","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"pith_short_12","alias_value":"P5BISNESQOLX","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"pith_short_16","alias_value":"P5BISNESQOLX4PHR","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"pith_short_8","alias_value":"P5BISNES","created_at":"2026-07-16T01:22:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:P5BISNESQOLX4PHRQJLHZY5N6T","target":"record","payload":{"canonical_record":{"source":{"id":"2603.00546","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-28T08:49:22Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"627ed7dad6c2b2d21d3f34097eeba0fffe7e8a3f47ca88c15d7150800ce22874","abstract_canon_sha256":"6676fd32e621c57d14c772ab76e0ab3271620de548f26369db1bb5400b2ceabc"},"schema_version":"1.0"},"canonical_sha256":"7f4289349283977e3cf182567ce3adf4fe9ed88dca0693cafa8a03f82ff509b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:22:35.377834Z","signature_b64":"M5PtOpG0e3uCnhEaySRGKqT2UpqA+xscQ8G2pOCtoNLyThOfnxQfJ2Uvu7D+N4FlXooqlwqXFi1VMbtENuYkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f4289349283977e3cf182567ce3adf4fe9ed88dca0693cafa8a03f82ff509b3","last_reissued_at":"2026-07-16T01:22:35.376840Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:22:35.376840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.00546","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":"2026-07-16T01:22:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pJIxOnKdw/257d8SEOpTa5ka6eNstNZZT1DQLly0UsjUh1FkVDZurFqZMx22Ou309ZAzbOF2+y17nFoMTb1HBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:45:44.573710Z"},"content_sha256":"552b0c480c15b78140f237416a8d965e3bb91b0735116dbd1ca15b01e1cddc5c","schema_version":"1.0","event_id":"sha256:552b0c480c15b78140f237416a8d965e3bb91b0735116dbd1ca15b01e1cddc5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:P5BISNESQOLX4PHRQJLHZY5N6T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advancing Multimodal Judge Models through a Capability-Oriented Benchmark and MCTS-Driven Data Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Huanjin Yao, Min Yang, Zeyu Chen, Ziwang Zhao","submitted_at":"2026-02-28T08:49:22Z","abstract_excerpt":"Using Multimodal Large Language Models (MLLMs) as judges to achieve precise and consistent evaluations has gradually become an emerging paradigm across various domains. Evaluating the capability and reliability of MLLM-as-a-judge systems is therefore essential for ensuring trustworthy assessment. Existing judge benchmarks categorize samples by task types but fail to capture the fundamental judgment capabilities required for reliable evaluation. In this work, we introduce M-JudgeBench, a ten-dimensional capability-oriented benchmark designed to comprehensively assess the judgment abilities of M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00546","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/2603.00546/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":"2026-07-16T01:22:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"waT4xg7Ps7JeGl2UyOOa9M3CVKpPJvtLgskGU2ka7KtKbn3mD0kAjss/alJl+bXFJfzVAGoKdwlJEOqQbiygAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:45:44.574681Z"},"content_sha256":"fed3ff62f0ae0e510f66dab76f87943b654fae0f77ef8c5a367e5f33c4286160","schema_version":"1.0","event_id":"sha256:fed3ff62f0ae0e510f66dab76f87943b654fae0f77ef8c5a367e5f33c4286160"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P5BISNESQOLX4PHRQJLHZY5N6T/bundle.json","state_url":"https://pith.science/pith/P5BISNESQOLX4PHRQJLHZY5N6T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P5BISNESQOLX4PHRQJLHZY5N6T/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":"2026-08-03T17:45:44Z","links":{"resolver":"https://pith.science/pith/P5BISNESQOLX4PHRQJLHZY5N6T","bundle":"https://pith.science/pith/P5BISNESQOLX4PHRQJLHZY5N6T/bundle.json","state":"https://pith.science/pith/P5BISNESQOLX4PHRQJLHZY5N6T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P5BISNESQOLX4PHRQJLHZY5N6T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P5BISNESQOLX4PHRQJLHZY5N6T","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":"6676fd32e621c57d14c772ab76e0ab3271620de548f26369db1bb5400b2ceabc","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-28T08:49:22Z","title_canon_sha256":"627ed7dad6c2b2d21d3f34097eeba0fffe7e8a3f47ca88c15d7150800ce22874"},"schema_version":"1.0","source":{"id":"2603.00546","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.00546","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"arxiv_version","alias_value":"2603.00546v2","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00546","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"pith_short_12","alias_value":"P5BISNESQOLX","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"pith_short_16","alias_value":"P5BISNESQOLX4PHR","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"pith_short_8","alias_value":"P5BISNES","created_at":"2026-07-16T01:22:35Z"}],"graph_snapshots":[{"event_id":"sha256:fed3ff62f0ae0e510f66dab76f87943b654fae0f77ef8c5a367e5f33c4286160","target":"graph","created_at":"2026-07-16T01:22:35Z","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/2603.00546/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using Multimodal Large Language Models (MLLMs) as judges to achieve precise and consistent evaluations has gradually become an emerging paradigm across various domains. Evaluating the capability and reliability of MLLM-as-a-judge systems is therefore essential for ensuring trustworthy assessment. Existing judge benchmarks categorize samples by task types but fail to capture the fundamental judgment capabilities required for reliable evaluation. In this work, we introduce M-JudgeBench, a ten-dimensional capability-oriented benchmark designed to comprehensively assess the judgment abilities of M","authors_text":"Huanjin Yao, Min Yang, Zeyu Chen, Ziwang Zhao","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-28T08:49:22Z","title":"Advancing Multimodal Judge Models through a Capability-Oriented Benchmark and MCTS-Driven Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00546","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":"sha256:552b0c480c15b78140f237416a8d965e3bb91b0735116dbd1ca15b01e1cddc5c","target":"record","created_at":"2026-07-16T01:22:35Z","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":"6676fd32e621c57d14c772ab76e0ab3271620de548f26369db1bb5400b2ceabc","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-28T08:49:22Z","title_canon_sha256":"627ed7dad6c2b2d21d3f34097eeba0fffe7e8a3f47ca88c15d7150800ce22874"},"schema_version":"1.0","source":{"id":"2603.00546","kind":"arxiv","version":2}},"canonical_sha256":"7f4289349283977e3cf182567ce3adf4fe9ed88dca0693cafa8a03f82ff509b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f4289349283977e3cf182567ce3adf4fe9ed88dca0693cafa8a03f82ff509b3","first_computed_at":"2026-07-16T01:22:35.376840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T01:22:35.376840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M5PtOpG0e3uCnhEaySRGKqT2UpqA+xscQ8G2pOCtoNLyThOfnxQfJ2Uvu7D+N4FlXooqlwqXFi1VMbtENuYkCA==","signature_status":"signed_v1","signed_at":"2026-07-16T01:22:35.377834Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.00546","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:552b0c480c15b78140f237416a8d965e3bb91b0735116dbd1ca15b01e1cddc5c","sha256:fed3ff62f0ae0e510f66dab76f87943b654fae0f77ef8c5a367e5f33c4286160"],"state_sha256":"af7bb298128204b127f4297737124628bc46dd3d7218fd8fb5a114825fe7e2cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Qtu3Ppaaz7hwKqI6+FwFuNEs7ZF7cvhM07p1rHQ9ybI+7XgnsO63CYNojZlmFs7YyC9MBykQ1dqA/5yu2W+Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:45:44.580419Z","bundle_sha256":"9257882a0d4f24d507dcec1bb186d1837e422370b5fe1cf2ec0c15abfb6e6f83"}}