{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VSIYJ2YXTOXR2NM5BB3P54MCN4","short_pith_number":"pith:VSIYJ2YX","canonical_record":{"source":{"id":"2607.15299","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-07-07T08:35:38Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"9208e02bb619828a1e3392cddb25929cf225aa7e24988a5add12f75b6e4f1d52","abstract_canon_sha256":"1ee17b326182ff210879c9fbeec63f6185c590dcec1f285ed82d68d4254f7c17"},"schema_version":"1.0"},"canonical_sha256":"ac9184eb179baf1d359d0876fef1826f13ba2e938bc0496b755b6bdfe55d1cc1","source":{"kind":"arxiv","id":"2607.15299","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15299","created_at":"2026-07-20T00:18:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15299v1","created_at":"2026-07-20T00:18:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15299","created_at":"2026-07-20T00:18:25Z"},{"alias_kind":"pith_short_12","alias_value":"VSIYJ2YXTOXR","created_at":"2026-07-20T00:18:25Z"},{"alias_kind":"pith_short_16","alias_value":"VSIYJ2YXTOXR2NM5","created_at":"2026-07-20T00:18:25Z"},{"alias_kind":"pith_short_8","alias_value":"VSIYJ2YX","created_at":"2026-07-20T00:18:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VSIYJ2YXTOXR2NM5BB3P54MCN4","target":"record","payload":{"canonical_record":{"source":{"id":"2607.15299","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-07-07T08:35:38Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"9208e02bb619828a1e3392cddb25929cf225aa7e24988a5add12f75b6e4f1d52","abstract_canon_sha256":"1ee17b326182ff210879c9fbeec63f6185c590dcec1f285ed82d68d4254f7c17"},"schema_version":"1.0"},"canonical_sha256":"ac9184eb179baf1d359d0876fef1826f13ba2e938bc0496b755b6bdfe55d1cc1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T00:18:25.758993Z","signature_b64":"AW0PD4rURwxDqq7Nd6jj3jCk8m627cYSVBE+M1B+LqiXr1uvgm6zSNlcDFtw4cA/65blAIuZhZ9aYmzvVZbMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac9184eb179baf1d359d0876fef1826f13ba2e938bc0496b755b6bdfe55d1cc1","last_reissued_at":"2026-07-20T00:18:25.758195Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T00:18:25.758195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.15299","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":"2026-07-20T00:18:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2UmteOqp78NX3RDgVy4+p4j6zIUDv85nPwjSJQ1Ys2jSUGw3Y99OGkuyAgdCKxmq5mZFE7AV866BHr350yE5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:16:06.135023Z"},"content_sha256":"9332b7b94253e73e69fb473e9265cf44d87bcc9eb9a295dcbcb570012cb279cc","schema_version":"1.0","event_id":"sha256:9332b7b94253e73e69fb473e9265cf44d87bcc9eb9a295dcbcb570012cb279cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VSIYJ2YXTOXR2NM5BB3P54MCN4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.MM","authors_text":"Bin Wang, Conghui He, Jiaqi Wang, Linke Ouyang, Pan Zhang, Xiaoyi Dong, Yiqi Lin, Zhiyuan Zhao","submitted_at":"2026-07-07T08:35:38Z","abstract_excerpt":"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 analyzes the weakness of the model based on the evaluation results, then generates a proper incremental dataset for the next training iteration, and enhances the model capability iteratively. Compared with previous instruction fine-tuning dataset collection methods which are separate from the benchmarking, MLLM-DataEngine shows better targeting and can improve MLLMs's capabilities more effectively. Firstly, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15299","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/2607.15299/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":"2026-07-20T00:18:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1dEX2oo+2sitifGVs6DwokamZEl0Kj4Y8vUnC2vPnSTFb+oP50ol7PMPGYEzEcKnY8h2WejJc+BjvJvrB2f/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:16:06.136348Z"},"content_sha256":"7b43d1222d64dc8bd8aa1db79f37afd3a32435d7ebf00b0458ea60d1170e1a0c","schema_version":"1.0","event_id":"sha256:7b43d1222d64dc8bd8aa1db79f37afd3a32435d7ebf00b0458ea60d1170e1a0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VSIYJ2YXTOXR2NM5BB3P54MCN4/bundle.json","state_url":"https://pith.science/pith/VSIYJ2YXTOXR2NM5BB3P54MCN4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VSIYJ2YXTOXR2NM5BB3P54MCN4/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":"2026-08-05T09:16:06Z","links":{"resolver":"https://pith.science/pith/VSIYJ2YXTOXR2NM5BB3P54MCN4","bundle":"https://pith.science/pith/VSIYJ2YXTOXR2NM5BB3P54MCN4/bundle.json","state":"https://pith.science/pith/VSIYJ2YXTOXR2NM5BB3P54MCN4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VSIYJ2YXTOXR2NM5BB3P54MCN4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VSIYJ2YXTOXR2NM5BB3P54MCN4","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":"1ee17b326182ff210879c9fbeec63f6185c590dcec1f285ed82d68d4254f7c17","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-07-07T08:35:38Z","title_canon_sha256":"9208e02bb619828a1e3392cddb25929cf225aa7e24988a5add12f75b6e4f1d52"},"schema_version":"1.0","source":{"id":"2607.15299","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15299","created_at":"2026-07-20T00:18:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15299v1","created_at":"2026-07-20T00:18:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15299","created_at":"2026-07-20T00:18:25Z"},{"alias_kind":"pith_short_12","alias_value":"VSIYJ2YXTOXR","created_at":"2026-07-20T00:18:25Z"},{"alias_kind":"pith_short_16","alias_value":"VSIYJ2YXTOXR2NM5","created_at":"2026-07-20T00:18:25Z"},{"alias_kind":"pith_short_8","alias_value":"VSIYJ2YX","created_at":"2026-07-20T00:18:25Z"}],"graph_snapshots":[{"event_id":"sha256:7b43d1222d64dc8bd8aa1db79f37afd3a32435d7ebf00b0458ea60d1170e1a0c","target":"graph","created_at":"2026-07-20T00:18:25Z","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/2607.15299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"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 analyzes the weakness of the model based on the evaluation results, then generates a proper incremental dataset for the next training iteration, and enhances the model capability iteratively. Compared with previous instruction fine-tuning dataset collection methods which are separate from the benchmarking, MLLM-DataEngine shows better targeting and can improve MLLMs's capabilities more effectively. Firstly, we ","authors_text":"Bin Wang, Conghui He, Jiaqi Wang, Linke Ouyang, Pan Zhang, Xiaoyi Dong, Yiqi Lin, Zhiyuan Zhao","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-07-07T08:35:38Z","title":"MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15299","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":"sha256:9332b7b94253e73e69fb473e9265cf44d87bcc9eb9a295dcbcb570012cb279cc","target":"record","created_at":"2026-07-20T00:18:25Z","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":"1ee17b326182ff210879c9fbeec63f6185c590dcec1f285ed82d68d4254f7c17","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-07-07T08:35:38Z","title_canon_sha256":"9208e02bb619828a1e3392cddb25929cf225aa7e24988a5add12f75b6e4f1d52"},"schema_version":"1.0","source":{"id":"2607.15299","kind":"arxiv","version":1}},"canonical_sha256":"ac9184eb179baf1d359d0876fef1826f13ba2e938bc0496b755b6bdfe55d1cc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac9184eb179baf1d359d0876fef1826f13ba2e938bc0496b755b6bdfe55d1cc1","first_computed_at":"2026-07-20T00:18:25.758195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T00:18:25.758195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AW0PD4rURwxDqq7Nd6jj3jCk8m627cYSVBE+M1B+LqiXr1uvgm6zSNlcDFtw4cA/65blAIuZhZ9aYmzvVZbMDA==","signature_status":"signed_v1","signed_at":"2026-07-20T00:18:25.758993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15299","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9332b7b94253e73e69fb473e9265cf44d87bcc9eb9a295dcbcb570012cb279cc","sha256:7b43d1222d64dc8bd8aa1db79f37afd3a32435d7ebf00b0458ea60d1170e1a0c"],"state_sha256":"66b844e4d04af5391f8275f1f920f5eed138927ec12fc05c5b7d7f6f604d9976"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LeAz9eP9Qmv0qCMIb9ZmTvP7Q5jxkdY+OOMAy2IBTQUfR0KbdM/qHZvSmUWrRabP4m3n4JpWuZ6f4XLr4xviDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:16:06.144782Z","bundle_sha256":"73fe4b6847865925665fd1717ea6c6fa99a0695d07bf7ee363555e1b066ee6d0"}}