{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KHVLRQYM57H6FPMGT5MA2OLO3Z","short_pith_number":"pith:KHVLRQYM","schema_version":"1.0","canonical_sha256":"51eab8c30cefcfe2bd869f580d396ede4d666fdc52738006bf58a0978fa1efe2","source":{"kind":"arxiv","id":"2508.20227","version":1},"attestation_state":"computed","paper":{"title":"A Novel Framework for Automated Explain Vision Model Using Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chris Ngo, Phu-Vinh Nguyen, Tan-Hanh Pham, Truong Son Hy","submitted_at":"2025-08-27T19:16:40Z","abstract_excerpt":"The development of many vision models mainly focuses on improving their performance using metrics such as accuracy, IoU, and mAP, with less attention to explainability due to the complexity of applying xAI methods to provide a meaningful explanation of trained models. Although many existing xAI methods aim to explain vision models sample-by-sample, methods explaining the general behavior of vision models, which can only be captured after running on a large dataset, are still underexplored. Furthermore, understanding the behavior of vision models on general images can be very important to preve"},"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":"2508.20227","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T19:16:40Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"7738699f072f8c5ed21d0975db2c9a82b81e3f254859f38a9967e85d5efed016","abstract_canon_sha256":"1a8531f5ced347143bae6bdce626b2ace2b3ae063d30d123ef346bb57a6df297"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:32.260945Z","signature_b64":"o3A+Am9TT7BWN0UoO5WEZI+X80WvI4juFvT5GHmkykNR0Td9ytM82qpk+vZGQkXoZ6PDycyGs95r1Unv1AArCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51eab8c30cefcfe2bd869f580d396ede4d666fdc52738006bf58a0978fa1efe2","last_reissued_at":"2026-07-05T12:00:32.260452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:32.260452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Novel Framework for Automated Explain Vision Model Using Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chris Ngo, Phu-Vinh Nguyen, Tan-Hanh Pham, Truong Son Hy","submitted_at":"2025-08-27T19:16:40Z","abstract_excerpt":"The development of many vision models mainly focuses on improving their performance using metrics such as accuracy, IoU, and mAP, with less attention to explainability due to the complexity of applying xAI methods to provide a meaningful explanation of trained models. Although many existing xAI methods aim to explain vision models sample-by-sample, methods explaining the general behavior of vision models, which can only be captured after running on a large dataset, are still underexplored. Furthermore, understanding the behavior of vision models on general images can be very important to preve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20227","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/2508.20227/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":"2508.20227","created_at":"2026-07-05T12:00:32.260511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20227v1","created_at":"2026-07-05T12:00:32.260511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20227","created_at":"2026-07-05T12:00:32.260511+00:00"},{"alias_kind":"pith_short_12","alias_value":"KHVLRQYM57H6","created_at":"2026-07-05T12:00:32.260511+00:00"},{"alias_kind":"pith_short_16","alias_value":"KHVLRQYM57H6FPMG","created_at":"2026-07-05T12:00:32.260511+00:00"},{"alias_kind":"pith_short_8","alias_value":"KHVLRQYM","created_at":"2026-07-05T12:00:32.260511+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/KHVLRQYM57H6FPMGT5MA2OLO3Z","json":"https://pith.science/pith/KHVLRQYM57H6FPMGT5MA2OLO3Z.json","graph_json":"https://pith.science/api/pith-number/KHVLRQYM57H6FPMGT5MA2OLO3Z/graph.json","events_json":"https://pith.science/api/pith-number/KHVLRQYM57H6FPMGT5MA2OLO3Z/events.json","paper":"https://pith.science/paper/KHVLRQYM"},"agent_actions":{"view_html":"https://pith.science/pith/KHVLRQYM57H6FPMGT5MA2OLO3Z","download_json":"https://pith.science/pith/KHVLRQYM57H6FPMGT5MA2OLO3Z.json","view_paper":"https://pith.science/paper/KHVLRQYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20227&json=true","fetch_graph":"https://pith.science/api/pith-number/KHVLRQYM57H6FPMGT5MA2OLO3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/KHVLRQYM57H6FPMGT5MA2OLO3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KHVLRQYM57H6FPMGT5MA2OLO3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KHVLRQYM57H6FPMGT5MA2OLO3Z/action/storage_attestation","attest_author":"https://pith.science/pith/KHVLRQYM57H6FPMGT5MA2OLO3Z/action/author_attestation","sign_citation":"https://pith.science/pith/KHVLRQYM57H6FPMGT5MA2OLO3Z/action/citation_signature","submit_replication":"https://pith.science/pith/KHVLRQYM57H6FPMGT5MA2OLO3Z/action/replication_record"}},"created_at":"2026-07-05T12:00:32.260511+00:00","updated_at":"2026-07-05T12:00:32.260511+00:00"}