{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ULKWBEBKB7NHJRF73UCG27ZA6D","short_pith_number":"pith:ULKWBEBK","canonical_record":{"source":{"id":"2403.02677","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T06:05:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"518465bb10d8e1cbd64376a9a5e12aef3230cf8201cac16b41d8527501338482","abstract_canon_sha256":"18d3467805500e89853cec74a3cfefd2f1c8e992c9bf9b1b8d9b33b958ac5b52"},"schema_version":"1.0"},"canonical_sha256":"a2d560902a0fda74c4bfdd046d7f20f0fd218d506ea88a96c9b6bd8229ab721d","source":{"kind":"arxiv","id":"2403.02677","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.02677","created_at":"2026-07-05T07:52:20Z"},{"alias_kind":"arxiv_version","alias_value":"2403.02677v1","created_at":"2026-07-05T07:52:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02677","created_at":"2026-07-05T07:52:20Z"},{"alias_kind":"pith_short_12","alias_value":"ULKWBEBKB7NH","created_at":"2026-07-05T07:52:20Z"},{"alias_kind":"pith_short_16","alias_value":"ULKWBEBKB7NHJRF7","created_at":"2026-07-05T07:52:20Z"},{"alias_kind":"pith_short_8","alias_value":"ULKWBEBK","created_at":"2026-07-05T07:52:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ULKWBEBKB7NHJRF73UCG27ZA6D","target":"record","payload":{"canonical_record":{"source":{"id":"2403.02677","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T06:05:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"518465bb10d8e1cbd64376a9a5e12aef3230cf8201cac16b41d8527501338482","abstract_canon_sha256":"18d3467805500e89853cec74a3cfefd2f1c8e992c9bf9b1b8d9b33b958ac5b52"},"schema_version":"1.0"},"canonical_sha256":"a2d560902a0fda74c4bfdd046d7f20f0fd218d506ea88a96c9b6bd8229ab721d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:20.837610Z","signature_b64":"Jq9YFEN47vp0NeNPqOV+RKj0ur6nne4tWv3xRQXADUWKBRQpbl9+AE3qyL2e4+b4VKnIpwm4Ty5J1AQfV0n5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2d560902a0fda74c4bfdd046d7f20f0fd218d506ea88a96c9b6bd8229ab721d","last_reissued_at":"2026-07-05T07:52:20.837233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:20.837233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.02677","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":"2026-07-05T07:52:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w/w0lNlw89LjNGL/tsyy9mygxzGKlJYlYHPeITgIzucaTfvYOY0L5/O8mdRBDdvkPgdcd11xgNVVKW5tdv/EBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:57:36.174118Z"},"content_sha256":"267181d0caea5de51d8d8175d54fdd209bf70a463448d49f28a466af890307dc","schema_version":"1.0","event_id":"sha256:267181d0caea5de51d8d8175d54fdd209bf70a463448d49f28a466af890307dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ULKWBEBKB7NHJRF73UCG27ZA6D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Heng Wang, Khalil Mrini, Linjie Yang, Sateesh Kumar, Weizhi Wang, Xifeng Yan, Yu Tian","submitted_at":"2024-03-05T06:05:15Z","abstract_excerpt":"We propose a novel framework for filtering image-text data by leveraging fine-tuned Multimodal Language Models (MLMs). Our approach outperforms predominant filtering methods (e.g., CLIPScore) via integrating the recent advances in MLMs. We design four distinct yet complementary metrics to holistically measure the quality of image-text data. A new pipeline is established to construct high-quality instruction data for fine-tuning MLMs as data filters. Comparing with CLIPScore, our MLM filters produce more precise and comprehensive scores that directly improve the quality of filtered data and boo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02677","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/2403.02677/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":"2026-07-05T07:52:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c4rTgVmLdcdv0aWdBgULthcbCnqmqtWvWFJmopHyyD1XQ7KExuLUW3Vg0eAhtG8p19O1iSuiHShNKeB1EOKNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:57:36.175022Z"},"content_sha256":"1832c7b6b1518d61a114029889516d3982267b711a5b6444c6ddd4560b32863f","schema_version":"1.0","event_id":"sha256:1832c7b6b1518d61a114029889516d3982267b711a5b6444c6ddd4560b32863f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ULKWBEBKB7NHJRF73UCG27ZA6D/bundle.json","state_url":"https://pith.science/pith/ULKWBEBKB7NHJRF73UCG27ZA6D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ULKWBEBKB7NHJRF73UCG27ZA6D/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":"2026-08-08T13:57:36Z","links":{"resolver":"https://pith.science/pith/ULKWBEBKB7NHJRF73UCG27ZA6D","bundle":"https://pith.science/pith/ULKWBEBKB7NHJRF73UCG27ZA6D/bundle.json","state":"https://pith.science/pith/ULKWBEBKB7NHJRF73UCG27ZA6D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ULKWBEBKB7NHJRF73UCG27ZA6D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ULKWBEBKB7NHJRF73UCG27ZA6D","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":"18d3467805500e89853cec74a3cfefd2f1c8e992c9bf9b1b8d9b33b958ac5b52","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T06:05:15Z","title_canon_sha256":"518465bb10d8e1cbd64376a9a5e12aef3230cf8201cac16b41d8527501338482"},"schema_version":"1.0","source":{"id":"2403.02677","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.02677","created_at":"2026-07-05T07:52:20Z"},{"alias_kind":"arxiv_version","alias_value":"2403.02677v1","created_at":"2026-07-05T07:52:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02677","created_at":"2026-07-05T07:52:20Z"},{"alias_kind":"pith_short_12","alias_value":"ULKWBEBKB7NH","created_at":"2026-07-05T07:52:20Z"},{"alias_kind":"pith_short_16","alias_value":"ULKWBEBKB7NHJRF7","created_at":"2026-07-05T07:52:20Z"},{"alias_kind":"pith_short_8","alias_value":"ULKWBEBK","created_at":"2026-07-05T07:52:20Z"}],"graph_snapshots":[{"event_id":"sha256:1832c7b6b1518d61a114029889516d3982267b711a5b6444c6ddd4560b32863f","target":"graph","created_at":"2026-07-05T07:52:20Z","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/2403.02677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel framework for filtering image-text data by leveraging fine-tuned Multimodal Language Models (MLMs). Our approach outperforms predominant filtering methods (e.g., CLIPScore) via integrating the recent advances in MLMs. We design four distinct yet complementary metrics to holistically measure the quality of image-text data. A new pipeline is established to construct high-quality instruction data for fine-tuning MLMs as data filters. Comparing with CLIPScore, our MLM filters produce more precise and comprehensive scores that directly improve the quality of filtered data and boo","authors_text":"Heng Wang, Khalil Mrini, Linjie Yang, Sateesh Kumar, Weizhi Wang, Xifeng Yan, Yu Tian","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T06:05:15Z","title":"Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02677","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":"sha256:267181d0caea5de51d8d8175d54fdd209bf70a463448d49f28a466af890307dc","target":"record","created_at":"2026-07-05T07:52:20Z","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":"18d3467805500e89853cec74a3cfefd2f1c8e992c9bf9b1b8d9b33b958ac5b52","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T06:05:15Z","title_canon_sha256":"518465bb10d8e1cbd64376a9a5e12aef3230cf8201cac16b41d8527501338482"},"schema_version":"1.0","source":{"id":"2403.02677","kind":"arxiv","version":1}},"canonical_sha256":"a2d560902a0fda74c4bfdd046d7f20f0fd218d506ea88a96c9b6bd8229ab721d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2d560902a0fda74c4bfdd046d7f20f0fd218d506ea88a96c9b6bd8229ab721d","first_computed_at":"2026-07-05T07:52:20.837233Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:20.837233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jq9YFEN47vp0NeNPqOV+RKj0ur6nne4tWv3xRQXADUWKBRQpbl9+AE3qyL2e4+b4VKnIpwm4Ty5J1AQfV0n5Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:20.837610Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.02677","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:267181d0caea5de51d8d8175d54fdd209bf70a463448d49f28a466af890307dc","sha256:1832c7b6b1518d61a114029889516d3982267b711a5b6444c6ddd4560b32863f"],"state_sha256":"fac55cd503e5c3feadd211b9684d10ac9b684256e529113f5c172a71eabd22dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8zdp4CAZ4B9LDxExvZHcLQyz/x15hmjJKSVlCRF93bE7E/XgnUOOLCeRpa98Wbm6TkftGqkALaAu4bisSys9DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:57:36.181575Z","bundle_sha256":"22bfa0e3fbe2ac7ee613a729e80b313ecd47037d9c4fde39de04fc22283775b9"}}