{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2DDA6AIKJDFJ7HTQS3HBGVP65J","short_pith_number":"pith:2DDA6AIK","schema_version":"1.0","canonical_sha256":"d0c60f010a48ca9f9e7096ce1355feea7eee9c9e8a9d3fb1aad60d8962d9ac26","source":{"kind":"arxiv","id":"2507.09008","version":1},"attestation_state":"computed","paper":{"title":"VISTA: A Visual Analytics Framework to Enhance Foundation Model-Generated Data Labels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jorge Piazentin Ono, Kwan-Liu Ma, Liang Gou, Liu Ren, WenBin He, Xiaoqi Wang, Xiwei Xuan","submitted_at":"2025-07-11T20:17:23Z","abstract_excerpt":"The advances in multi-modal foundation models (FMs) (e.g., CLIP and LLaVA) have facilitated the auto-labeling of large-scale datasets, enhancing model performance in challenging downstream tasks such as open-vocabulary object detection and segmentation. However, the quality of FM-generated labels is less studied as existing approaches focus more on data quantity over quality. This is because validating large volumes of data without ground truth presents a considerable challenge in practice. Existing methods typically rely on limited metrics to identify problematic data, lacking a comprehensive"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.09008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-11T20:17:23Z","cross_cats_sorted":[],"title_canon_sha256":"345f3db11b6a5d3ad578f1ca8b90d5b42f94b56051972cb7d2784d47d52b88ea","abstract_canon_sha256":"0f79f0d1fb26546c4d3f8262299061f7b23c732947eb32838d597594e0924856"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:02.080374Z","signature_b64":"PDYRam5Wmd2DTWl/nJBf9M2EF1RnVeFmFY9XoAIqXEB4ZXIFWrphI8pctkFfjVGzIk5Dpl04nhuI+RcdGplbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0c60f010a48ca9f9e7096ce1355feea7eee9c9e8a9d3fb1aad60d8962d9ac26","last_reissued_at":"2026-07-05T11:36:02.079871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:02.079871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VISTA: A Visual Analytics Framework to Enhance Foundation Model-Generated Data Labels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jorge Piazentin Ono, Kwan-Liu Ma, Liang Gou, Liu Ren, WenBin He, Xiaoqi Wang, Xiwei Xuan","submitted_at":"2025-07-11T20:17:23Z","abstract_excerpt":"The advances in multi-modal foundation models (FMs) (e.g., CLIP and LLaVA) have facilitated the auto-labeling of large-scale datasets, enhancing model performance in challenging downstream tasks such as open-vocabulary object detection and segmentation. However, the quality of FM-generated labels is less studied as existing approaches focus more on data quantity over quality. This is because validating large volumes of data without ground truth presents a considerable challenge in practice. Existing methods typically rely on limited metrics to identify problematic data, lacking a comprehensive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09008","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/2507.09008/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.09008","created_at":"2026-07-05T11:36:02.079929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09008v1","created_at":"2026-07-05T11:36:02.079929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09008","created_at":"2026-07-05T11:36:02.079929+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DDA6AIKJDFJ","created_at":"2026-07-05T11:36:02.079929+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DDA6AIKJDFJ7HTQ","created_at":"2026-07-05T11:36:02.079929+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DDA6AIK","created_at":"2026-07-05T11:36:02.079929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DDA6AIKJDFJ7HTQS3HBGVP65J","json":"https://pith.science/pith/2DDA6AIKJDFJ7HTQS3HBGVP65J.json","graph_json":"https://pith.science/api/pith-number/2DDA6AIKJDFJ7HTQS3HBGVP65J/graph.json","events_json":"https://pith.science/api/pith-number/2DDA6AIKJDFJ7HTQS3HBGVP65J/events.json","paper":"https://pith.science/paper/2DDA6AIK"},"agent_actions":{"view_html":"https://pith.science/pith/2DDA6AIKJDFJ7HTQS3HBGVP65J","download_json":"https://pith.science/pith/2DDA6AIKJDFJ7HTQS3HBGVP65J.json","view_paper":"https://pith.science/paper/2DDA6AIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09008&json=true","fetch_graph":"https://pith.science/api/pith-number/2DDA6AIKJDFJ7HTQS3HBGVP65J/graph.json","fetch_events":"https://pith.science/api/pith-number/2DDA6AIKJDFJ7HTQS3HBGVP65J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DDA6AIKJDFJ7HTQS3HBGVP65J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DDA6AIKJDFJ7HTQS3HBGVP65J/action/storage_attestation","attest_author":"https://pith.science/pith/2DDA6AIKJDFJ7HTQS3HBGVP65J/action/author_attestation","sign_citation":"https://pith.science/pith/2DDA6AIKJDFJ7HTQS3HBGVP65J/action/citation_signature","submit_replication":"https://pith.science/pith/2DDA6AIKJDFJ7HTQS3HBGVP65J/action/replication_record"}},"created_at":"2026-07-05T11:36:02.079929+00:00","updated_at":"2026-07-05T11:36:02.079929+00:00"}