{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:K4EXCOGNRWF7L7ZD43KXSA5W6X","short_pith_number":"pith:K4EXCOGN","canonical_record":{"source":{"id":"2312.06726","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T05:57:09Z","cross_cats_sorted":[],"title_canon_sha256":"980618c5d7d3a0b959fd196832d46f0049043abc938a540a80d82dc3176ec21a","abstract_canon_sha256":"ba58f30364a36d9e570e1377c7c4ddfc83ac53d46fac6d28e8650d59b86781e8"},"schema_version":"1.0"},"canonical_sha256":"57097138cd8d8bf5ff23e6d57903b6f5dd9ee07f01dd9e6af8f31440686f43ae","source":{"kind":"arxiv","id":"2312.06726","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06726","created_at":"2026-07-05T09:02:55Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06726v4","created_at":"2026-07-05T09:02:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06726","created_at":"2026-07-05T09:02:55Z"},{"alias_kind":"pith_short_12","alias_value":"K4EXCOGNRWF7","created_at":"2026-07-05T09:02:55Z"},{"alias_kind":"pith_short_16","alias_value":"K4EXCOGNRWF7L7ZD","created_at":"2026-07-05T09:02:55Z"},{"alias_kind":"pith_short_8","alias_value":"K4EXCOGN","created_at":"2026-07-05T09:02:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:K4EXCOGNRWF7L7ZD43KXSA5W6X","target":"record","payload":{"canonical_record":{"source":{"id":"2312.06726","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T05:57:09Z","cross_cats_sorted":[],"title_canon_sha256":"980618c5d7d3a0b959fd196832d46f0049043abc938a540a80d82dc3176ec21a","abstract_canon_sha256":"ba58f30364a36d9e570e1377c7c4ddfc83ac53d46fac6d28e8650d59b86781e8"},"schema_version":"1.0"},"canonical_sha256":"57097138cd8d8bf5ff23e6d57903b6f5dd9ee07f01dd9e6af8f31440686f43ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:55.577765Z","signature_b64":"/asTwbEieEwJ7AqzRcXaYty5EZ0j8v7hfSiC1cROxr93Cy7QOq1EvOHa717Q1Roo6eSgxhPxHwijqMAjHyr4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57097138cd8d8bf5ff23e6d57903b6f5dd9ee07f01dd9e6af8f31440686f43ae","last_reissued_at":"2026-07-05T09:02:55.577302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:55.577302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.06726","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":"2026-07-05T09:02:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XKo+Pasvq3pPziaiwLgA9MMWUY9kdF1nbJYk9OGFAPf7zpfBUCIV/eTLdUs2P8eNavsPdB7oyegKnQviSwqUAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:05:10.799420Z"},"content_sha256":"36f39a8ec3a6e183407a6cc88f3aaa691cad21f8fc5214dc45d454ab256d93d1","schema_version":"1.0","event_id":"sha256:36f39a8ec3a6e183407a6cc88f3aaa691cad21f8fc5214dc45d454ab256d93d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:K4EXCOGNRWF7L7ZD43KXSA5W6X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Filter & Align: Leveraging Human Knowledge to Curate Image-Text Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cihang Xie, Fangxun Shu, Hao Jiang, Lei Zhang, Sucheng Ren, Tianyang Liu","submitted_at":"2023-12-11T05:57:09Z","abstract_excerpt":"The increasing availability of image-text pairs has largely fueled the rapid advancement in vision-language foundation models. However, the vast scale of these datasets inevitably introduces significant variability in data quality, which can adversely affect the model performance. This highlights the critical role of data filtering, not only to enhance training efficiency but also to improve overall data quality. Existing methods typically rely on metrics such as CLIP Score and BLIP Score, which are derived from pre-trained models. However, these models are often trained on uncurated, noisy da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06726","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/2312.06726/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":"2026-07-05T09:02:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hTuF2UwLnZC3NhYs5X5PXRSl13raHXHPWwidRV7qgzbirZYrihKEnWNCWw3DYmzxzFI3MnjSiUP/4OW126AdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:05:10.799911Z"},"content_sha256":"da043b46aaa82dbce3b1be3d284ba8d83dc7dacbc98ca9359110c0ce6400a43f","schema_version":"1.0","event_id":"sha256:da043b46aaa82dbce3b1be3d284ba8d83dc7dacbc98ca9359110c0ce6400a43f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K4EXCOGNRWF7L7ZD43KXSA5W6X/bundle.json","state_url":"https://pith.science/pith/K4EXCOGNRWF7L7ZD43KXSA5W6X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K4EXCOGNRWF7L7ZD43KXSA5W6X/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":"2026-08-06T15:05:10Z","links":{"resolver":"https://pith.science/pith/K4EXCOGNRWF7L7ZD43KXSA5W6X","bundle":"https://pith.science/pith/K4EXCOGNRWF7L7ZD43KXSA5W6X/bundle.json","state":"https://pith.science/pith/K4EXCOGNRWF7L7ZD43KXSA5W6X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K4EXCOGNRWF7L7ZD43KXSA5W6X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K4EXCOGNRWF7L7ZD43KXSA5W6X","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":"ba58f30364a36d9e570e1377c7c4ddfc83ac53d46fac6d28e8650d59b86781e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T05:57:09Z","title_canon_sha256":"980618c5d7d3a0b959fd196832d46f0049043abc938a540a80d82dc3176ec21a"},"schema_version":"1.0","source":{"id":"2312.06726","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06726","created_at":"2026-07-05T09:02:55Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06726v4","created_at":"2026-07-05T09:02:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06726","created_at":"2026-07-05T09:02:55Z"},{"alias_kind":"pith_short_12","alias_value":"K4EXCOGNRWF7","created_at":"2026-07-05T09:02:55Z"},{"alias_kind":"pith_short_16","alias_value":"K4EXCOGNRWF7L7ZD","created_at":"2026-07-05T09:02:55Z"},{"alias_kind":"pith_short_8","alias_value":"K4EXCOGN","created_at":"2026-07-05T09:02:55Z"}],"graph_snapshots":[{"event_id":"sha256:da043b46aaa82dbce3b1be3d284ba8d83dc7dacbc98ca9359110c0ce6400a43f","target":"graph","created_at":"2026-07-05T09:02:55Z","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/2312.06726/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing availability of image-text pairs has largely fueled the rapid advancement in vision-language foundation models. However, the vast scale of these datasets inevitably introduces significant variability in data quality, which can adversely affect the model performance. This highlights the critical role of data filtering, not only to enhance training efficiency but also to improve overall data quality. Existing methods typically rely on metrics such as CLIP Score and BLIP Score, which are derived from pre-trained models. However, these models are often trained on uncurated, noisy da","authors_text":"Cihang Xie, Fangxun Shu, Hao Jiang, Lei Zhang, Sucheng Ren, Tianyang Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T05:57:09Z","title":"Filter & Align: Leveraging Human Knowledge to Curate Image-Text Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06726","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":"sha256:36f39a8ec3a6e183407a6cc88f3aaa691cad21f8fc5214dc45d454ab256d93d1","target":"record","created_at":"2026-07-05T09:02:55Z","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":"ba58f30364a36d9e570e1377c7c4ddfc83ac53d46fac6d28e8650d59b86781e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T05:57:09Z","title_canon_sha256":"980618c5d7d3a0b959fd196832d46f0049043abc938a540a80d82dc3176ec21a"},"schema_version":"1.0","source":{"id":"2312.06726","kind":"arxiv","version":4}},"canonical_sha256":"57097138cd8d8bf5ff23e6d57903b6f5dd9ee07f01dd9e6af8f31440686f43ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57097138cd8d8bf5ff23e6d57903b6f5dd9ee07f01dd9e6af8f31440686f43ae","first_computed_at":"2026-07-05T09:02:55.577302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:02:55.577302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/asTwbEieEwJ7AqzRcXaYty5EZ0j8v7hfSiC1cROxr93Cy7QOq1EvOHa717Q1Roo6eSgxhPxHwijqMAjHyr4Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:02:55.577765Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06726","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36f39a8ec3a6e183407a6cc88f3aaa691cad21f8fc5214dc45d454ab256d93d1","sha256:da043b46aaa82dbce3b1be3d284ba8d83dc7dacbc98ca9359110c0ce6400a43f"],"state_sha256":"bb700ca7514366c82c0ef0750f4886afd9d04146792688f3a124973c931e7555"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J7Y+B33jVfTZ3fsxJ1FavrKGMKs+iRQghg6GHf61YYVAL6j4ap3K2h1xv5N5nGDf5o1i9/zaEcmA/kyZWWG/DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:05:10.803884Z","bundle_sha256":"03bba628acfc1b41b3629a36fc51e2a23ac4084a748e9febfa0492a6de751ca5"}}