{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QD76ISTWUXCHJSFJMSMRIIUR4O","short_pith_number":"pith:QD76ISTW","canonical_record":{"source":{"id":"2411.19930","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T18:42:28Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"7eeccc8c740ae036848fcbf4a902a4d22ffa10c86adb6978badee7afc69c9216","abstract_canon_sha256":"d66524f9ccbaec6c80825335bfca5ddfe494c3577876b3db7ff08f51cd9544fe"},"schema_version":"1.0"},"canonical_sha256":"80ffe44a76a5c474c8a96499142291e3960a97b277dfc59511518b2555243fa3","source":{"kind":"arxiv","id":"2411.19930","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19930","created_at":"2026-07-05T11:59:55Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19930v4","created_at":"2026-07-05T11:59:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19930","created_at":"2026-07-05T11:59:55Z"},{"alias_kind":"pith_short_12","alias_value":"QD76ISTWUXCH","created_at":"2026-07-05T11:59:55Z"},{"alias_kind":"pith_short_16","alias_value":"QD76ISTWUXCHJSFJ","created_at":"2026-07-05T11:59:55Z"},{"alias_kind":"pith_short_8","alias_value":"QD76ISTW","created_at":"2026-07-05T11:59:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QD76ISTWUXCHJSFJMSMRIIUR4O","target":"record","payload":{"canonical_record":{"source":{"id":"2411.19930","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T18:42:28Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"7eeccc8c740ae036848fcbf4a902a4d22ffa10c86adb6978badee7afc69c9216","abstract_canon_sha256":"d66524f9ccbaec6c80825335bfca5ddfe494c3577876b3db7ff08f51cd9544fe"},"schema_version":"1.0"},"canonical_sha256":"80ffe44a76a5c474c8a96499142291e3960a97b277dfc59511518b2555243fa3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:55.492283Z","signature_b64":"OVlZlNnMKnYSgP3AAQw4S0xMVsVmQUmu7qS4HsJJNxf8Z/U/B/uAVlo4p40La06bKd1FlLxxSon0v+MerAW9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80ffe44a76a5c474c8a96499142291e3960a97b277dfc59511518b2555243fa3","last_reissued_at":"2026-07-05T11:59:55.491723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:55.491723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.19930","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:59:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JGKAHTU4d+0vN+giYzYbJxXYOsVKGjqu3pMo/ufaLaqVXen01cqrrR8jAGp8JTeJzuYqhMjINc2bjVdUaizXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T04:01:08.916308Z"},"content_sha256":"20afb528d042acc83eb52f3c02153f1abe023e62c983c2d2c028ef68fdd1a6fc","schema_version":"1.0","event_id":"sha256:20afb528d042acc83eb52f3c02153f1abe023e62c983c2d2c028ef68fdd1a6fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QD76ISTWUXCHJSFJMSMRIIUR4O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Domain-Adaptive Post-Training for Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bo Dai, Daixuan Cheng, Shaohan Huang, Wayne Xin Zhao, Xintong Zhang, Zhenliang Zhang, Zhongzhi Luan, Ziyu Zhu","submitted_at":"2024-11-29T18:42:28Z","abstract_excerpt":"Adapting general multimodal large language models (MLLMs) to specific domains, such as scientific and industrial fields, is highly significant in promoting their practical applications. This paper systematically investigates domain adaptation of MLLMs via post-training, focusing on data synthesis, training pipeline, and task evaluation. (1) Data Synthesis: Using only open-source models, we develop a generate-then-filter pipeline that curates diverse visual instruction tasks based on domain-specific image-caption pairs. The resulting data surpass the data synthesized by manual rules or strong c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19930","kind":"arxiv","version":4},"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/2411.19930/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":"2026-07-05T11:59:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8gd8OcpAn3PAcjTTc9GZ1/okJbGJxxciJmw+7pdnShOgmqjgySmyg5OUSRKQhME9SqjWN/9/MHjMBXevY20BDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T04:01:08.916701Z"},"content_sha256":"4a064fc7715840ed1ef4cddf9b1852fd07c7e97c361ace0ea6bda85917d2ec1e","schema_version":"1.0","event_id":"sha256:4a064fc7715840ed1ef4cddf9b1852fd07c7e97c361ace0ea6bda85917d2ec1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QD76ISTWUXCHJSFJMSMRIIUR4O/bundle.json","state_url":"https://pith.science/pith/QD76ISTWUXCHJSFJMSMRIIUR4O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QD76ISTWUXCHJSFJMSMRIIUR4O/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":"2026-07-10T04:01:08Z","links":{"resolver":"https://pith.science/pith/QD76ISTWUXCHJSFJMSMRIIUR4O","bundle":"https://pith.science/pith/QD76ISTWUXCHJSFJMSMRIIUR4O/bundle.json","state":"https://pith.science/pith/QD76ISTWUXCHJSFJMSMRIIUR4O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QD76ISTWUXCHJSFJMSMRIIUR4O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QD76ISTWUXCHJSFJMSMRIIUR4O","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":"d66524f9ccbaec6c80825335bfca5ddfe494c3577876b3db7ff08f51cd9544fe","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T18:42:28Z","title_canon_sha256":"7eeccc8c740ae036848fcbf4a902a4d22ffa10c86adb6978badee7afc69c9216"},"schema_version":"1.0","source":{"id":"2411.19930","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19930","created_at":"2026-07-05T11:59:55Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19930v4","created_at":"2026-07-05T11:59:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19930","created_at":"2026-07-05T11:59:55Z"},{"alias_kind":"pith_short_12","alias_value":"QD76ISTWUXCH","created_at":"2026-07-05T11:59:55Z"},{"alias_kind":"pith_short_16","alias_value":"QD76ISTWUXCHJSFJ","created_at":"2026-07-05T11:59:55Z"},{"alias_kind":"pith_short_8","alias_value":"QD76ISTW","created_at":"2026-07-05T11:59:55Z"}],"graph_snapshots":[{"event_id":"sha256:4a064fc7715840ed1ef4cddf9b1852fd07c7e97c361ace0ea6bda85917d2ec1e","target":"graph","created_at":"2026-07-05T11:59:55Z","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/2411.19930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adapting general multimodal large language models (MLLMs) to specific domains, such as scientific and industrial fields, is highly significant in promoting their practical applications. This paper systematically investigates domain adaptation of MLLMs via post-training, focusing on data synthesis, training pipeline, and task evaluation. (1) Data Synthesis: Using only open-source models, we develop a generate-then-filter pipeline that curates diverse visual instruction tasks based on domain-specific image-caption pairs. The resulting data surpass the data synthesized by manual rules or strong c","authors_text":"Bo Dai, Daixuan Cheng, Shaohan Huang, Wayne Xin Zhao, Xintong Zhang, Zhenliang Zhang, Zhongzhi Luan, Ziyu Zhu","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T18:42:28Z","title":"On Domain-Adaptive Post-Training for Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19930","kind":"arxiv","version":4},"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":"sha256:20afb528d042acc83eb52f3c02153f1abe023e62c983c2d2c028ef68fdd1a6fc","target":"record","created_at":"2026-07-05T11:59:55Z","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":"d66524f9ccbaec6c80825335bfca5ddfe494c3577876b3db7ff08f51cd9544fe","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T18:42:28Z","title_canon_sha256":"7eeccc8c740ae036848fcbf4a902a4d22ffa10c86adb6978badee7afc69c9216"},"schema_version":"1.0","source":{"id":"2411.19930","kind":"arxiv","version":4}},"canonical_sha256":"80ffe44a76a5c474c8a96499142291e3960a97b277dfc59511518b2555243fa3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80ffe44a76a5c474c8a96499142291e3960a97b277dfc59511518b2555243fa3","first_computed_at":"2026-07-05T11:59:55.491723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:55.491723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OVlZlNnMKnYSgP3AAQw4S0xMVsVmQUmu7qS4HsJJNxf8Z/U/B/uAVlo4p40La06bKd1FlLxxSon0v+MerAW9AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:55.492283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19930","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20afb528d042acc83eb52f3c02153f1abe023e62c983c2d2c028ef68fdd1a6fc","sha256:4a064fc7715840ed1ef4cddf9b1852fd07c7e97c361ace0ea6bda85917d2ec1e"],"state_sha256":"448b355fa38a16f957ecf9364d14e9a3410cf8b06d7e6ddaf046ecd9345503ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FueMoZaETT/LTu0rhmAyxb881FgDE2tV25freJfFmdZ2o7DFY4e/RxrKzJ7rnWJEFK/H2+TQW1lH5yNoyzXZDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T04:01:08.918811Z","bundle_sha256":"03a64b15b993d471e9784d3f79f00c279156b10e5235b8701a362b36643190d4"}}