{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SR6W2XOHJFIQABWLV3EXSLG5FY","short_pith_number":"pith:SR6W2XOH","canonical_record":{"source":{"id":"2507.20156","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T07:20:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"67a61f4eb89286b8045a326c62b139c75595f220022add436bf3bd053463d249","abstract_canon_sha256":"e5909426f342740a60c6b862f73c77036a1d2db0d058ddf1ac164938af2a0e20"},"schema_version":"1.0"},"canonical_sha256":"947d6d5dc749510006cbaec9792cdd2e01b09fe1f493612f09544692be515f3e","source":{"kind":"arxiv","id":"2507.20156","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20156","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20156v1","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20156","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"pith_short_12","alias_value":"SR6W2XOHJFIQ","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"pith_short_16","alias_value":"SR6W2XOHJFIQABWL","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"pith_short_8","alias_value":"SR6W2XOH","created_at":"2026-07-05T11:44:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SR6W2XOHJFIQABWLV3EXSLG5FY","target":"record","payload":{"canonical_record":{"source":{"id":"2507.20156","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T07:20:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"67a61f4eb89286b8045a326c62b139c75595f220022add436bf3bd053463d249","abstract_canon_sha256":"e5909426f342740a60c6b862f73c77036a1d2db0d058ddf1ac164938af2a0e20"},"schema_version":"1.0"},"canonical_sha256":"947d6d5dc749510006cbaec9792cdd2e01b09fe1f493612f09544692be515f3e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:14.301085Z","signature_b64":"UmRKXITRSYUZU6n6sqp+WOA3Y4bPtxaCjjSNTBjhOEQrgCIHAHuDXg9EYbIbZC6q0wUKI8PaceKwAMW9TBz9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"947d6d5dc749510006cbaec9792cdd2e01b09fe1f493612f09544692be515f3e","last_reissued_at":"2026-07-05T11:44:14.300559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:14.300559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.20156","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":"2026-07-05T11:44:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k+138g4LWvkyLXLAZ763jcNE+ZhdosTVggLINtWYaBGz1k3HA+eGsU3ocUOPeTf8YoypPnj3bF9DEdFEIo/JAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T09:43:54.621895Z"},"content_sha256":"5f7d1b1f645bba2ed4d7203e0742982836cd76ee824008043880a94a02602f3c","schema_version":"1.0","event_id":"sha256:5f7d1b1f645bba2ed4d7203e0742982836cd76ee824008043880a94a02602f3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SR6W2XOHJFIQABWLV3EXSLG5FY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Trust the Model: Compact VLMs as In-Context Judges for Image-Text Data Quality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abdulaziz Al-Badawi, Abdulrahman Alfulayt, Daulet Toibazar, Kesen Wang, Pedro J. Moreno, Sherif Mohamed","submitted_at":"2025-07-27T07:20:25Z","abstract_excerpt":"Vision-language models (VLMs) extend the conventional large language models by integrating visual data, enabling richer multimodal reasoning and significantly broadens the practical applications of AI. However, including visual inputs also brings new challenges in maintaining data quality. Empirical evidence consistently shows that carefully curated and representative training examples often yield superior results compared to simply increasing the quantity of data. Inspired by this observation, we introduce a streamlined data filtration framework that employs a compact VLM, fine-tuned on a hig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20156","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/2507.20156/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":"2026-07-05T11:44:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AsulvVNeKYZ8K/x0IJP9/YoIPOUCrbZix/GGKpgpYWrLrz43NaBEjcaOcayNgmjZkpFninmrc6WY5eE7TSIbCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T09:43:54.622460Z"},"content_sha256":"b16da48d0b63a270154405f93908202b56802c233271ba6dc928e2b08ec00b9e","schema_version":"1.0","event_id":"sha256:b16da48d0b63a270154405f93908202b56802c233271ba6dc928e2b08ec00b9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SR6W2XOHJFIQABWLV3EXSLG5FY/bundle.json","state_url":"https://pith.science/pith/SR6W2XOHJFIQABWLV3EXSLG5FY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SR6W2XOHJFIQABWLV3EXSLG5FY/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":"2026-08-17T09:43:54Z","links":{"resolver":"https://pith.science/pith/SR6W2XOHJFIQABWLV3EXSLG5FY","bundle":"https://pith.science/pith/SR6W2XOHJFIQABWLV3EXSLG5FY/bundle.json","state":"https://pith.science/pith/SR6W2XOHJFIQABWLV3EXSLG5FY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SR6W2XOHJFIQABWLV3EXSLG5FY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SR6W2XOHJFIQABWLV3EXSLG5FY","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":"e5909426f342740a60c6b862f73c77036a1d2db0d058ddf1ac164938af2a0e20","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T07:20:25Z","title_canon_sha256":"67a61f4eb89286b8045a326c62b139c75595f220022add436bf3bd053463d249"},"schema_version":"1.0","source":{"id":"2507.20156","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20156","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20156v1","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20156","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"pith_short_12","alias_value":"SR6W2XOHJFIQ","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"pith_short_16","alias_value":"SR6W2XOHJFIQABWL","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"pith_short_8","alias_value":"SR6W2XOH","created_at":"2026-07-05T11:44:14Z"}],"graph_snapshots":[{"event_id":"sha256:b16da48d0b63a270154405f93908202b56802c233271ba6dc928e2b08ec00b9e","target":"graph","created_at":"2026-07-05T11:44:14Z","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/2507.20156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) extend the conventional large language models by integrating visual data, enabling richer multimodal reasoning and significantly broadens the practical applications of AI. However, including visual inputs also brings new challenges in maintaining data quality. Empirical evidence consistently shows that carefully curated and representative training examples often yield superior results compared to simply increasing the quantity of data. Inspired by this observation, we introduce a streamlined data filtration framework that employs a compact VLM, fine-tuned on a hig","authors_text":"Abdulaziz Al-Badawi, Abdulrahman Alfulayt, Daulet Toibazar, Kesen Wang, Pedro J. Moreno, Sherif Mohamed","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T07:20:25Z","title":"Trust the Model: Compact VLMs as In-Context Judges for Image-Text Data Quality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20156","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":"sha256:5f7d1b1f645bba2ed4d7203e0742982836cd76ee824008043880a94a02602f3c","target":"record","created_at":"2026-07-05T11:44:14Z","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":"e5909426f342740a60c6b862f73c77036a1d2db0d058ddf1ac164938af2a0e20","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T07:20:25Z","title_canon_sha256":"67a61f4eb89286b8045a326c62b139c75595f220022add436bf3bd053463d249"},"schema_version":"1.0","source":{"id":"2507.20156","kind":"arxiv","version":1}},"canonical_sha256":"947d6d5dc749510006cbaec9792cdd2e01b09fe1f493612f09544692be515f3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"947d6d5dc749510006cbaec9792cdd2e01b09fe1f493612f09544692be515f3e","first_computed_at":"2026-07-05T11:44:14.300559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:14.300559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UmRKXITRSYUZU6n6sqp+WOA3Y4bPtxaCjjSNTBjhOEQrgCIHAHuDXg9EYbIbZC6q0wUKI8PaceKwAMW9TBz9BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:14.301085Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.20156","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f7d1b1f645bba2ed4d7203e0742982836cd76ee824008043880a94a02602f3c","sha256:b16da48d0b63a270154405f93908202b56802c233271ba6dc928e2b08ec00b9e"],"state_sha256":"f6156fcc101cc5ea5df60828cff9b3f6c9245d1f6d1da1bbe7fdaecb041a3ec3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WBdow1i0pbbkwLtQRUbwoVSRq31lJjphUfEuMI+Do3d6kqhP4/Ja6tL5js9YQ+5VQQEhD+8XiEjjZYvla+buBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T09:43:54.627726Z","bundle_sha256":"74451856106b59141e727ac699f16b39e6667ad5d68ec815afab10db763813de"}}