{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4VUDM7MC43KLYHJQJUO2O3TZTS","short_pith_number":"pith:4VUDM7MC","canonical_record":{"source":{"id":"2410.16166","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T16:32:41Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"41e353d58ed266476589896cc54fb41acb1ae4e4c09b3f646e685ea516b83516","abstract_canon_sha256":"d33e773b522d66c0ed0e93101167da5c914515b815a558d948eeedd4c0d7608c"},"schema_version":"1.0"},"canonical_sha256":"e568367d82e6d4bc1d304d1da76e799c8e90373ff6765815e7b425c271dec569","source":{"kind":"arxiv","id":"2410.16166","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16166","created_at":"2026-07-05T09:23:30Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16166v1","created_at":"2026-07-05T09:23:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16166","created_at":"2026-07-05T09:23:30Z"},{"alias_kind":"pith_short_12","alias_value":"4VUDM7MC43KL","created_at":"2026-07-05T09:23:30Z"},{"alias_kind":"pith_short_16","alias_value":"4VUDM7MC43KLYHJQ","created_at":"2026-07-05T09:23:30Z"},{"alias_kind":"pith_short_8","alias_value":"4VUDM7MC","created_at":"2026-07-05T09:23:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4VUDM7MC43KLYHJQJUO2O3TZTS","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16166","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T16:32:41Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"41e353d58ed266476589896cc54fb41acb1ae4e4c09b3f646e685ea516b83516","abstract_canon_sha256":"d33e773b522d66c0ed0e93101167da5c914515b815a558d948eeedd4c0d7608c"},"schema_version":"1.0"},"canonical_sha256":"e568367d82e6d4bc1d304d1da76e799c8e90373ff6765815e7b425c271dec569","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:30.768200Z","signature_b64":"gwJ/P7yPaRc1opyDFz1cHJs/xtBjzco4oK+E4qIzRt6P3Dgw3XVNDxAiUo4YXIdawv3ddX8zR+sikaI5bB8pAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e568367d82e6d4bc1d304d1da76e799c8e90373ff6765815e7b425c271dec569","last_reissued_at":"2026-07-05T09:23:30.767798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:30.767798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16166","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":"2026-07-05T09:23:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rCJU5VxRn8nvipBZ3YN2MFwHJ5UGnZmaP7Y9+24Sz6J5SReaBz32arDguWiRYIOo+oaAhonNMe5/LkKaiXW4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:15:29.362365Z"},"content_sha256":"16baf6f532876771b646264f356508c49644c1aeb19f9c8111b2798696fe5792","schema_version":"1.0","event_id":"sha256:16baf6f532876771b646264f356508c49644c1aeb19f9c8111b2798696fe5792"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4VUDM7MC43KLYHJQJUO2O3TZTS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bingning Wang, Han Huang, Haoyu Lu, Liang Wang, Qiang Liu, Shu Wu, Weipeng Chen, Yuqi Huo, Zijia Zhao","submitted_at":"2024-10-21T16:32:41Z","abstract_excerpt":"Multimodal large language models (MLLMs) have made significant strides by integrating visual and textual modalities. A critical factor in training MLLMs is the quality of image-text pairs within multimodal pretraining datasets. However, $\\textit {de facto}$ filter-based data quality enhancement paradigms often discard a substantial portion of high-quality image data due to inadequate semantic alignment between images and texts, leading to inefficiencies in data utilization and scalability. In this paper, we propose the Adaptive Image-Text Quality Enhancer (AITQE), a model that dynamically asse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16166","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/2410.16166/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":"2026-07-05T09:23:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Plm5C0oSJ4IMHuvtslMDaVUBgx2JCi2tYK4OgyQED/5SLD/CTe0xwffMjq8yOwdG6ahJWg0HseO31lR9mnzrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:15:29.362760Z"},"content_sha256":"4af3fd8274dfd42199a60ea5164be3616de7e634f3c97a9243f787e3dff9f7c9","schema_version":"1.0","event_id":"sha256:4af3fd8274dfd42199a60ea5164be3616de7e634f3c97a9243f787e3dff9f7c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4VUDM7MC43KLYHJQJUO2O3TZTS/bundle.json","state_url":"https://pith.science/pith/4VUDM7MC43KLYHJQJUO2O3TZTS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4VUDM7MC43KLYHJQJUO2O3TZTS/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":"2026-07-09T02:15:29Z","links":{"resolver":"https://pith.science/pith/4VUDM7MC43KLYHJQJUO2O3TZTS","bundle":"https://pith.science/pith/4VUDM7MC43KLYHJQJUO2O3TZTS/bundle.json","state":"https://pith.science/pith/4VUDM7MC43KLYHJQJUO2O3TZTS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4VUDM7MC43KLYHJQJUO2O3TZTS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4VUDM7MC43KLYHJQJUO2O3TZTS","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":"d33e773b522d66c0ed0e93101167da5c914515b815a558d948eeedd4c0d7608c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T16:32:41Z","title_canon_sha256":"41e353d58ed266476589896cc54fb41acb1ae4e4c09b3f646e685ea516b83516"},"schema_version":"1.0","source":{"id":"2410.16166","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16166","created_at":"2026-07-05T09:23:30Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16166v1","created_at":"2026-07-05T09:23:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16166","created_at":"2026-07-05T09:23:30Z"},{"alias_kind":"pith_short_12","alias_value":"4VUDM7MC43KL","created_at":"2026-07-05T09:23:30Z"},{"alias_kind":"pith_short_16","alias_value":"4VUDM7MC43KLYHJQ","created_at":"2026-07-05T09:23:30Z"},{"alias_kind":"pith_short_8","alias_value":"4VUDM7MC","created_at":"2026-07-05T09:23:30Z"}],"graph_snapshots":[{"event_id":"sha256:4af3fd8274dfd42199a60ea5164be3616de7e634f3c97a9243f787e3dff9f7c9","target":"graph","created_at":"2026-07-05T09:23:30Z","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/2410.16166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have made significant strides by integrating visual and textual modalities. A critical factor in training MLLMs is the quality of image-text pairs within multimodal pretraining datasets. However, $\\textit {de facto}$ filter-based data quality enhancement paradigms often discard a substantial portion of high-quality image data due to inadequate semantic alignment between images and texts, leading to inefficiencies in data utilization and scalability. In this paper, we propose the Adaptive Image-Text Quality Enhancer (AITQE), a model that dynamically asse","authors_text":"Bingning Wang, Han Huang, Haoyu Lu, Liang Wang, Qiang Liu, Shu Wu, Weipeng Chen, Yuqi Huo, Zijia Zhao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T16:32:41Z","title":"Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16166","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":"sha256:16baf6f532876771b646264f356508c49644c1aeb19f9c8111b2798696fe5792","target":"record","created_at":"2026-07-05T09:23:30Z","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":"d33e773b522d66c0ed0e93101167da5c914515b815a558d948eeedd4c0d7608c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T16:32:41Z","title_canon_sha256":"41e353d58ed266476589896cc54fb41acb1ae4e4c09b3f646e685ea516b83516"},"schema_version":"1.0","source":{"id":"2410.16166","kind":"arxiv","version":1}},"canonical_sha256":"e568367d82e6d4bc1d304d1da76e799c8e90373ff6765815e7b425c271dec569","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e568367d82e6d4bc1d304d1da76e799c8e90373ff6765815e7b425c271dec569","first_computed_at":"2026-07-05T09:23:30.767798Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:30.767798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gwJ/P7yPaRc1opyDFz1cHJs/xtBjzco4oK+E4qIzRt6P3Dgw3XVNDxAiUo4YXIdawv3ddX8zR+sikaI5bB8pAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:30.768200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16166","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16baf6f532876771b646264f356508c49644c1aeb19f9c8111b2798696fe5792","sha256:4af3fd8274dfd42199a60ea5164be3616de7e634f3c97a9243f787e3dff9f7c9"],"state_sha256":"737cef49b4ea813db29c59fc69ab2639b00ca15f524bd17c4e675d45f0c63fbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uH/sul8zz3Eu0SExYUzDxLFhlYIskC/jgZVQxH13z+xL9BEDgDhylisevzwWcrY0HMsq9gz8tnVerhEc2m9ICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:15:29.364823Z","bundle_sha256":"b5d4479141dd505e26a9967c588584e7aa9a5cb0e27d3a7f2c8a6686b9f92c01"}}