{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NTN34IMBZDB7SB4X4LYAIFJQXY","short_pith_number":"pith:NTN34IMB","canonical_record":{"source":{"id":"2506.23465","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T02:13:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"054cf48a3d0b54e7a1f35df5147009f39d93ff4874ea1f3e419814eee6647485","abstract_canon_sha256":"82989cc91dd25f49f52d79c614d77a362b9584a381da42804d75feda84db8511"},"schema_version":"1.0"},"canonical_sha256":"6cdbbe2181c8c3f90797e2f0041530be1765761ae1994b7f8ab8ed68289cd6a7","source":{"kind":"arxiv","id":"2506.23465","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23465","created_at":"2026-07-05T11:29:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23465v1","created_at":"2026-07-05T11:29:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23465","created_at":"2026-07-05T11:29:22Z"},{"alias_kind":"pith_short_12","alias_value":"NTN34IMBZDB7","created_at":"2026-07-05T11:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"NTN34IMBZDB7SB4X","created_at":"2026-07-05T11:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"NTN34IMB","created_at":"2026-07-05T11:29:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NTN34IMBZDB7SB4X4LYAIFJQXY","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23465","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T02:13:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"054cf48a3d0b54e7a1f35df5147009f39d93ff4874ea1f3e419814eee6647485","abstract_canon_sha256":"82989cc91dd25f49f52d79c614d77a362b9584a381da42804d75feda84db8511"},"schema_version":"1.0"},"canonical_sha256":"6cdbbe2181c8c3f90797e2f0041530be1765761ae1994b7f8ab8ed68289cd6a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:22.092676Z","signature_b64":"xXvvnFdkAlCqN5Vf5l5zF055sK9bBLQmilQJJDkoKNoSXMcG0uR9TIpW2KXrghxFAXWSpYf5tBwDjp7iTHNsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cdbbe2181c8c3f90797e2f0041530be1765761ae1994b7f8ab8ed68289cd6a7","last_reissued_at":"2026-07-05T11:29:22.092111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:22.092111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23465","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":"2026-07-05T11:29:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"633jU3cG0pR/7cUKmGb3UN2QalfrYe8IcD8VaB4LJ9v7zhP4cLo3eqv3e2HcH3IKpG7mfTIRSROdqgyoQN1wCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:58:43.424859Z"},"content_sha256":"fb735db244a1bd045d95b401f536517d25f2e3f5b5d5090867b90cca8bf775d4","schema_version":"1.0","event_id":"sha256:fb735db244a1bd045d95b401f536517d25f2e3f5b5d5090867b90cca8bf775d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NTN34IMBZDB7SB4X4LYAIFJQXY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sanitizing Manufacturing Dataset Labels Using Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Nazanin Mahjourian, Vinh Nguyen","submitted_at":"2025-06-30T02:13:09Z","abstract_excerpt":"The success of machine learning models in industrial applications is heavily dependent on the quality of the datasets used to train the models. However, large-scale datasets, specially those constructed from crowd-sourcing and web-scraping, often suffer from label noise, inconsistencies, and errors. This problem is particularly pronounced in manufacturing domains, where obtaining high-quality labels is costly and time-consuming. This paper introduces Vision-Language Sanitization and Refinement (VLSR), which is a vision-language-based framework for label sanitization and refinement in multi-lab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23465","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/2506.23465/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":"2026-07-05T11:29:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9u2TkI7+yVbbqz8pvMe1tc6de9kx2YjQxCknAq93PIC80ozAEeS4yZQkwp712sI18IEi/vhDnyKorlSkofUGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:58:43.425979Z"},"content_sha256":"94dc4d05be028ba33cc099f393cc44a1777b1473965138be4a07c68e31fbd182","schema_version":"1.0","event_id":"sha256:94dc4d05be028ba33cc099f393cc44a1777b1473965138be4a07c68e31fbd182"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NTN34IMBZDB7SB4X4LYAIFJQXY/bundle.json","state_url":"https://pith.science/pith/NTN34IMBZDB7SB4X4LYAIFJQXY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NTN34IMBZDB7SB4X4LYAIFJQXY/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":"2026-08-17T16:58:43Z","links":{"resolver":"https://pith.science/pith/NTN34IMBZDB7SB4X4LYAIFJQXY","bundle":"https://pith.science/pith/NTN34IMBZDB7SB4X4LYAIFJQXY/bundle.json","state":"https://pith.science/pith/NTN34IMBZDB7SB4X4LYAIFJQXY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NTN34IMBZDB7SB4X4LYAIFJQXY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NTN34IMBZDB7SB4X4LYAIFJQXY","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":"82989cc91dd25f49f52d79c614d77a362b9584a381da42804d75feda84db8511","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T02:13:09Z","title_canon_sha256":"054cf48a3d0b54e7a1f35df5147009f39d93ff4874ea1f3e419814eee6647485"},"schema_version":"1.0","source":{"id":"2506.23465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23465","created_at":"2026-07-05T11:29:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23465v1","created_at":"2026-07-05T11:29:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23465","created_at":"2026-07-05T11:29:22Z"},{"alias_kind":"pith_short_12","alias_value":"NTN34IMBZDB7","created_at":"2026-07-05T11:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"NTN34IMBZDB7SB4X","created_at":"2026-07-05T11:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"NTN34IMB","created_at":"2026-07-05T11:29:22Z"}],"graph_snapshots":[{"event_id":"sha256:94dc4d05be028ba33cc099f393cc44a1777b1473965138be4a07c68e31fbd182","target":"graph","created_at":"2026-07-05T11:29:22Z","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/2506.23465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of machine learning models in industrial applications is heavily dependent on the quality of the datasets used to train the models. However, large-scale datasets, specially those constructed from crowd-sourcing and web-scraping, often suffer from label noise, inconsistencies, and errors. This problem is particularly pronounced in manufacturing domains, where obtaining high-quality labels is costly and time-consuming. This paper introduces Vision-Language Sanitization and Refinement (VLSR), which is a vision-language-based framework for label sanitization and refinement in multi-lab","authors_text":"Nazanin Mahjourian, Vinh Nguyen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T02:13:09Z","title":"Sanitizing Manufacturing Dataset Labels Using Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23465","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:fb735db244a1bd045d95b401f536517d25f2e3f5b5d5090867b90cca8bf775d4","target":"record","created_at":"2026-07-05T11:29:22Z","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":"82989cc91dd25f49f52d79c614d77a362b9584a381da42804d75feda84db8511","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T02:13:09Z","title_canon_sha256":"054cf48a3d0b54e7a1f35df5147009f39d93ff4874ea1f3e419814eee6647485"},"schema_version":"1.0","source":{"id":"2506.23465","kind":"arxiv","version":1}},"canonical_sha256":"6cdbbe2181c8c3f90797e2f0041530be1765761ae1994b7f8ab8ed68289cd6a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cdbbe2181c8c3f90797e2f0041530be1765761ae1994b7f8ab8ed68289cd6a7","first_computed_at":"2026-07-05T11:29:22.092111Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:22.092111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xXvvnFdkAlCqN5Vf5l5zF055sK9bBLQmilQJJDkoKNoSXMcG0uR9TIpW2KXrghxFAXWSpYf5tBwDjp7iTHNsBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:22.092676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb735db244a1bd045d95b401f536517d25f2e3f5b5d5090867b90cca8bf775d4","sha256:94dc4d05be028ba33cc099f393cc44a1777b1473965138be4a07c68e31fbd182"],"state_sha256":"50eb1df9ec1f9c7a063cdbb8b683d5935763a2ee5e48f058020abcf0698b2013"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9A1cCZgZXJoJVNwP3870vyrQ3lpyn2oOTtLrsNwAcE3tvz/4ZArcDZTneZ0nI0JBzGE0tq6QRBvbtOyVK/GNAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T16:58:43.438540Z","bundle_sha256":"307f0c24fd2ca1a8b96d9c06507ae6f0510a583fde8c2f4422471c5fac7cc1f1"}}