{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ORVL3UB4IPLTLEWT4MHFOMFBB3","short_pith_number":"pith:ORVL3UB4","canonical_record":{"source":{"id":"2506.04688","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T07:11:36Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"6101e68afa10390d197505c59fb9c4bf0e9e9b1e2bf78b395bacee341dc0bfa6","abstract_canon_sha256":"a7779b8a87b6b72615bf7c7c4e7e1eff689c48f281a3bfef117263c511ea018a"},"schema_version":"1.0"},"canonical_sha256":"746abdd03c43d73592d3e30e5730a10efbb5223095bb54e27451ea8c22eb2fd5","source":{"kind":"arxiv","id":"2506.04688","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04688","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04688v1","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04688","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"ORVL3UB4IPLT","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_16","alias_value":"ORVL3UB4IPLTLEWT","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_8","alias_value":"ORVL3UB4","created_at":"2026-07-05T11:16:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ORVL3UB4IPLTLEWT4MHFOMFBB3","target":"record","payload":{"canonical_record":{"source":{"id":"2506.04688","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T07:11:36Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"6101e68afa10390d197505c59fb9c4bf0e9e9b1e2bf78b395bacee341dc0bfa6","abstract_canon_sha256":"a7779b8a87b6b72615bf7c7c4e7e1eff689c48f281a3bfef117263c511ea018a"},"schema_version":"1.0"},"canonical_sha256":"746abdd03c43d73592d3e30e5730a10efbb5223095bb54e27451ea8c22eb2fd5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:18.886309Z","signature_b64":"pWjqq8vJeZbfkoY8pf44W2bIdNzfMXLQ17pSYKQ79Ph6J/Mp0xh0PIRsNeCaUGuZ7EHbyGnbUFQXHZUU7/j4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"746abdd03c43d73592d3e30e5730a10efbb5223095bb54e27451ea8c22eb2fd5","last_reissued_at":"2026-07-05T11:16:18.885824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:18.885824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.04688","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":"2026-07-05T11:16:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZO6+ZaXuDPD2YBu21nwY8TnW9Q8E/9Ms8cOtRYeZqYQQ4Ny8zjZPa9Z+vVR4fx+nsgiYRPJ9VExwWQU853YqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:49:14.345490Z"},"content_sha256":"f513e162627b148c8afcc2a1349e488b12dd668b63b05693d280ce4dbe0c6bbc","schema_version":"1.0","event_id":"sha256:f513e162627b148c8afcc2a1349e488b12dd668b63b05693d280ce4dbe0c6bbc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ORVL3UB4IPLTLEWT4MHFOMFBB3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMRefine: Unveiling the Obstacles to Robust Refinement in 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":"Geewook Kim, Gio Paik, Jinbae Im","submitted_at":"2025-06-05T07:11:36Z","abstract_excerpt":"This paper introduces MMRefine, a MultiModal Refinement benchmark designed to evaluate the error refinement capabilities of Multimodal Large Language Models (MLLMs). As the emphasis shifts toward enhancing reasoning during inference, MMRefine provides a framework that evaluates MLLMs' abilities to detect and correct errors across six distinct scenarios beyond just comparing final accuracy before and after refinement. Furthermore, the benchmark analyzes the refinement performance by categorizing errors into six error types. Experiments with various open and closed MLLMs reveal bottlenecks and f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04688","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/2506.04688/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":"2026-07-05T11:16:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6KspSPpMDj23izH/N+YKlje1ckbYNvwPDPvmuTPJ8kmlmLCBzgCPDIv/hsPsKNBwW1r/UGru/lIXSAo6LQ9VAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:49:14.346018Z"},"content_sha256":"970820153ae9b7f6a6d43653b4e0614621d290733106114db89c381a432912c1","schema_version":"1.0","event_id":"sha256:970820153ae9b7f6a6d43653b4e0614621d290733106114db89c381a432912c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ORVL3UB4IPLTLEWT4MHFOMFBB3/bundle.json","state_url":"https://pith.science/pith/ORVL3UB4IPLTLEWT4MHFOMFBB3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ORVL3UB4IPLTLEWT4MHFOMFBB3/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":"2026-08-08T08:49:14Z","links":{"resolver":"https://pith.science/pith/ORVL3UB4IPLTLEWT4MHFOMFBB3","bundle":"https://pith.science/pith/ORVL3UB4IPLTLEWT4MHFOMFBB3/bundle.json","state":"https://pith.science/pith/ORVL3UB4IPLTLEWT4MHFOMFBB3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ORVL3UB4IPLTLEWT4MHFOMFBB3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ORVL3UB4IPLTLEWT4MHFOMFBB3","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":"a7779b8a87b6b72615bf7c7c4e7e1eff689c48f281a3bfef117263c511ea018a","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T07:11:36Z","title_canon_sha256":"6101e68afa10390d197505c59fb9c4bf0e9e9b1e2bf78b395bacee341dc0bfa6"},"schema_version":"1.0","source":{"id":"2506.04688","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04688","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04688v1","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04688","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"ORVL3UB4IPLT","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_16","alias_value":"ORVL3UB4IPLTLEWT","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_8","alias_value":"ORVL3UB4","created_at":"2026-07-05T11:16:18Z"}],"graph_snapshots":[{"event_id":"sha256:970820153ae9b7f6a6d43653b4e0614621d290733106114db89c381a432912c1","target":"graph","created_at":"2026-07-05T11:16:18Z","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/2506.04688/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces MMRefine, a MultiModal Refinement benchmark designed to evaluate the error refinement capabilities of Multimodal Large Language Models (MLLMs). As the emphasis shifts toward enhancing reasoning during inference, MMRefine provides a framework that evaluates MLLMs' abilities to detect and correct errors across six distinct scenarios beyond just comparing final accuracy before and after refinement. Furthermore, the benchmark analyzes the refinement performance by categorizing errors into six error types. Experiments with various open and closed MLLMs reveal bottlenecks and f","authors_text":"Geewook Kim, Gio Paik, Jinbae Im","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T07:11:36Z","title":"MMRefine: Unveiling the Obstacles to Robust Refinement in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04688","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:f513e162627b148c8afcc2a1349e488b12dd668b63b05693d280ce4dbe0c6bbc","target":"record","created_at":"2026-07-05T11:16:18Z","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":"a7779b8a87b6b72615bf7c7c4e7e1eff689c48f281a3bfef117263c511ea018a","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T07:11:36Z","title_canon_sha256":"6101e68afa10390d197505c59fb9c4bf0e9e9b1e2bf78b395bacee341dc0bfa6"},"schema_version":"1.0","source":{"id":"2506.04688","kind":"arxiv","version":1}},"canonical_sha256":"746abdd03c43d73592d3e30e5730a10efbb5223095bb54e27451ea8c22eb2fd5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"746abdd03c43d73592d3e30e5730a10efbb5223095bb54e27451ea8c22eb2fd5","first_computed_at":"2026-07-05T11:16:18.885824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:18.885824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pWjqq8vJeZbfkoY8pf44W2bIdNzfMXLQ17pSYKQ79Ph6J/Mp0xh0PIRsNeCaUGuZ7EHbyGnbUFQXHZUU7/j4Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:18.886309Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04688","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f513e162627b148c8afcc2a1349e488b12dd668b63b05693d280ce4dbe0c6bbc","sha256:970820153ae9b7f6a6d43653b4e0614621d290733106114db89c381a432912c1"],"state_sha256":"b5ab854e61841ff07b1671dafece1280cb242c4f53fe441fe8006c205a92eb38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gDpuUwfOkhdhN0qCZg3VAcDxrR28yERDejan6p6YKOp5+uNJ3QwrYA/pIaNfE935viXtOB1GTM78wIJeqAWNBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:49:14.351034Z","bundle_sha256":"5782bab2fdc5f57c319c6fb90f1393a6b6d427c15329bff5569f5f6abc531433"}}