{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SRQYVQKH7HOPXVEMEY2WUKUVBP","short_pith_number":"pith:SRQYVQKH","canonical_record":{"source":{"id":"2308.13566","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-25T01:41:04Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"15bfaf87768539a6b6c502f5fef899de39513fc9fc7aec126d713e19113921c2","abstract_canon_sha256":"03c4dc6c2d8299fce97895cd773718fd402aa2e98f875fabf923ba88a7b4de38"},"schema_version":"1.0"},"canonical_sha256":"94618ac147f9dcfbd48c26356a2a950bf2669a5c4c1cc6b6fb7b273a9210a144","source":{"kind":"arxiv","id":"2308.13566","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13566","created_at":"2026-07-05T06:49:25Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13566v2","created_at":"2026-07-05T06:49:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13566","created_at":"2026-07-05T06:49:25Z"},{"alias_kind":"pith_short_12","alias_value":"SRQYVQKH7HOP","created_at":"2026-07-05T06:49:25Z"},{"alias_kind":"pith_short_16","alias_value":"SRQYVQKH7HOPXVEM","created_at":"2026-07-05T06:49:25Z"},{"alias_kind":"pith_short_8","alias_value":"SRQYVQKH","created_at":"2026-07-05T06:49:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SRQYVQKH7HOPXVEMEY2WUKUVBP","target":"record","payload":{"canonical_record":{"source":{"id":"2308.13566","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-25T01:41:04Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"15bfaf87768539a6b6c502f5fef899de39513fc9fc7aec126d713e19113921c2","abstract_canon_sha256":"03c4dc6c2d8299fce97895cd773718fd402aa2e98f875fabf923ba88a7b4de38"},"schema_version":"1.0"},"canonical_sha256":"94618ac147f9dcfbd48c26356a2a950bf2669a5c4c1cc6b6fb7b273a9210a144","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:25.301213Z","signature_b64":"sAJiE/50LQdwjx0ChrjHk+eyXIFkIkgTcVmKNOcCPgmOlMFLcCOs4dNuY/0Wz4/vNEDUfE0iXFQLdXC0qxn0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94618ac147f9dcfbd48c26356a2a950bf2669a5c4c1cc6b6fb7b273a9210a144","last_reissued_at":"2026-07-05T06:49:25.300812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:25.300812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.13566","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":"2026-07-05T06:49:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUz2OjSvLd0uKao8LSlk0f0qzC2hJOpLW9+ljm2/ltGO1BzHEf51p/qpaaUkULBRum8CHjzMjaqgPIby0md9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:37:36.986951Z"},"content_sha256":"fcd655df4d9de2421c584aa0652bef7d42327943aa404c808c818e0aa4040564","schema_version":"1.0","event_id":"sha256:fcd655df4d9de2421c584aa0652bef7d42327943aa404c808c818e0aa4040564"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SRQYVQKH7HOPXVEMEY2WUKUVBP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MLLM-DataEngine: An Iterative Refinement Approach for MLLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bin Wang, Conghui He, Jiaqi Wang, Linke Ouyang, Pan Zhang, Siyuan Huang, Xiaoyi Dong, Zhiyuan Zhao","submitted_at":"2023-08-25T01:41:04Z","abstract_excerpt":"Despite the great advance of Multimodal Large Language Models (MLLMs) in both instruction dataset building and benchmarking, the independence of training and evaluation makes current MLLMs hard to further improve their capability under the guidance of evaluation results with a relatively low human cost. In this paper, we propose MLLM-DataEngine, a novel closed-loop system that bridges data generation, model training, and evaluation. Within each loop iteration, the MLLM-DataEngine first analyze the weakness of the model based on the evaluation results, then generate a proper incremental dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13566","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/2308.13566/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":"2026-07-05T06:49:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tRzoDuw49BlUDpXJEafyriJY1sc7T+8+uCxmSXfAuEkEjzySCyDjiYaL0HybqqaBlOcMJMGTC+uQhYXOM7JeAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:37:36.987832Z"},"content_sha256":"3ccbd9963e7ea70baf27cc4c1d47cbd90e53d2e8b84f7e303900b73515761849","schema_version":"1.0","event_id":"sha256:3ccbd9963e7ea70baf27cc4c1d47cbd90e53d2e8b84f7e303900b73515761849"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SRQYVQKH7HOPXVEMEY2WUKUVBP/bundle.json","state_url":"https://pith.science/pith/SRQYVQKH7HOPXVEMEY2WUKUVBP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SRQYVQKH7HOPXVEMEY2WUKUVBP/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":"2026-08-05T10:37:36Z","links":{"resolver":"https://pith.science/pith/SRQYVQKH7HOPXVEMEY2WUKUVBP","bundle":"https://pith.science/pith/SRQYVQKH7HOPXVEMEY2WUKUVBP/bundle.json","state":"https://pith.science/pith/SRQYVQKH7HOPXVEMEY2WUKUVBP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SRQYVQKH7HOPXVEMEY2WUKUVBP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SRQYVQKH7HOPXVEMEY2WUKUVBP","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":"03c4dc6c2d8299fce97895cd773718fd402aa2e98f875fabf923ba88a7b4de38","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-25T01:41:04Z","title_canon_sha256":"15bfaf87768539a6b6c502f5fef899de39513fc9fc7aec126d713e19113921c2"},"schema_version":"1.0","source":{"id":"2308.13566","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13566","created_at":"2026-07-05T06:49:25Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13566v2","created_at":"2026-07-05T06:49:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13566","created_at":"2026-07-05T06:49:25Z"},{"alias_kind":"pith_short_12","alias_value":"SRQYVQKH7HOP","created_at":"2026-07-05T06:49:25Z"},{"alias_kind":"pith_short_16","alias_value":"SRQYVQKH7HOPXVEM","created_at":"2026-07-05T06:49:25Z"},{"alias_kind":"pith_short_8","alias_value":"SRQYVQKH","created_at":"2026-07-05T06:49:25Z"}],"graph_snapshots":[{"event_id":"sha256:3ccbd9963e7ea70baf27cc4c1d47cbd90e53d2e8b84f7e303900b73515761849","target":"graph","created_at":"2026-07-05T06:49:25Z","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/2308.13566/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the great advance of Multimodal Large Language Models (MLLMs) in both instruction dataset building and benchmarking, the independence of training and evaluation makes current MLLMs hard to further improve their capability under the guidance of evaluation results with a relatively low human cost. In this paper, we propose MLLM-DataEngine, a novel closed-loop system that bridges data generation, model training, and evaluation. Within each loop iteration, the MLLM-DataEngine first analyze the weakness of the model based on the evaluation results, then generate a proper incremental dataset","authors_text":"Bin Wang, Conghui He, Jiaqi Wang, Linke Ouyang, Pan Zhang, Siyuan Huang, Xiaoyi Dong, Zhiyuan Zhao","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-25T01:41:04Z","title":"MLLM-DataEngine: An Iterative Refinement Approach for MLLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13566","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:fcd655df4d9de2421c584aa0652bef7d42327943aa404c808c818e0aa4040564","target":"record","created_at":"2026-07-05T06:49:25Z","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":"03c4dc6c2d8299fce97895cd773718fd402aa2e98f875fabf923ba88a7b4de38","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-25T01:41:04Z","title_canon_sha256":"15bfaf87768539a6b6c502f5fef899de39513fc9fc7aec126d713e19113921c2"},"schema_version":"1.0","source":{"id":"2308.13566","kind":"arxiv","version":2}},"canonical_sha256":"94618ac147f9dcfbd48c26356a2a950bf2669a5c4c1cc6b6fb7b273a9210a144","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94618ac147f9dcfbd48c26356a2a950bf2669a5c4c1cc6b6fb7b273a9210a144","first_computed_at":"2026-07-05T06:49:25.300812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:49:25.300812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sAJiE/50LQdwjx0ChrjHk+eyXIFkIkgTcVmKNOcCPgmOlMFLcCOs4dNuY/0Wz4/vNEDUfE0iXFQLdXC0qxn0Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:49:25.301213Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.13566","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcd655df4d9de2421c584aa0652bef7d42327943aa404c808c818e0aa4040564","sha256:3ccbd9963e7ea70baf27cc4c1d47cbd90e53d2e8b84f7e303900b73515761849"],"state_sha256":"2e11e89e18b20391372c7d31781eaebd04161296d783b150e5930e3fd53841f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"knzzqlR/bvKLfv4Dtidh6CxQpYm7tXIaX2ZuG5q73pZuVO2elSu2qb63mN920z1dWA/X/ILq2VY9ybmwu9//Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:37:36.996221Z","bundle_sha256":"19d6d7cb424190ef3c558a8ed2a659bf0c7c5b63c201585489e63d997ffef8ea"}}