{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L32JXNVSYBGLBZSB5MXRWHPOB5","short_pith_number":"pith:L32JXNVS","schema_version":"1.0","canonical_sha256":"5ef49bb6b2c04cb0e641eb2f1b1dee0f49995c69bb2c550885910e1690de9d2d","source":{"kind":"arxiv","id":"2606.04310","version":1},"attestation_state":"computed","paper":{"title":"Latent Anchor-Driven Test Generation for Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Bin Duan, Guowei Yang, Matthew B. Dwyer","submitted_at":"2026-06-03T00:33:21Z","abstract_excerpt":"Deep Neural Networks (DNNs) are increasingly being deployed in security-critical and safety-sensitive applications, which makes rigorous testing essential to identify and mitigate model weaknesses. Existing DNN testing approaches explore either the input space or a learned latent space. While latent-space generation can better maintain plausibility than direct input-space mutation, current methods still face a trade-off among exploration controllability, failure diversity, and seed-relative semantic drift. To overcome these limitations, we propose Latte, a black-box testing framework that gene"},"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":"2606.04310","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T00:33:21Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"7c5f805b922e4f85b882b89ca0bc5f4900ff98c0bbc4b5a51cf9fa1d585110b3","abstract_canon_sha256":"e91f8cb6805e23d71b5c9c0d78d7489da1a9dee0bdf8c73d82c4fc30012a8914"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:03.147996Z","signature_b64":"UDucLj7+mfpuwtyQCIOd2jbjvQhPi0FqCuKP+KZP/3zraDkZvKOmX64p5TfBKFqtinXUFavIqoUflAvGjxe7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ef49bb6b2c04cb0e641eb2f1b1dee0f49995c69bb2c550885910e1690de9d2d","last_reissued_at":"2026-06-04T01:09:03.147562Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:03.147562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Anchor-Driven Test Generation for Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Bin Duan, Guowei Yang, Matthew B. Dwyer","submitted_at":"2026-06-03T00:33:21Z","abstract_excerpt":"Deep Neural Networks (DNNs) are increasingly being deployed in security-critical and safety-sensitive applications, which makes rigorous testing essential to identify and mitigate model weaknesses. Existing DNN testing approaches explore either the input space or a learned latent space. While latent-space generation can better maintain plausibility than direct input-space mutation, current methods still face a trade-off among exploration controllability, failure diversity, and seed-relative semantic drift. To overcome these limitations, we propose Latte, a black-box testing framework that gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04310","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/2606.04310/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":"2606.04310","created_at":"2026-06-04T01:09:03.147630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04310v1","created_at":"2026-06-04T01:09:03.147630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04310","created_at":"2026-06-04T01:09:03.147630+00:00"},{"alias_kind":"pith_short_12","alias_value":"L32JXNVSYBGL","created_at":"2026-06-04T01:09:03.147630+00:00"},{"alias_kind":"pith_short_16","alias_value":"L32JXNVSYBGLBZSB","created_at":"2026-06-04T01:09:03.147630+00:00"},{"alias_kind":"pith_short_8","alias_value":"L32JXNVS","created_at":"2026-06-04T01:09:03.147630+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/L32JXNVSYBGLBZSB5MXRWHPOB5","json":"https://pith.science/pith/L32JXNVSYBGLBZSB5MXRWHPOB5.json","graph_json":"https://pith.science/api/pith-number/L32JXNVSYBGLBZSB5MXRWHPOB5/graph.json","events_json":"https://pith.science/api/pith-number/L32JXNVSYBGLBZSB5MXRWHPOB5/events.json","paper":"https://pith.science/paper/L32JXNVS"},"agent_actions":{"view_html":"https://pith.science/pith/L32JXNVSYBGLBZSB5MXRWHPOB5","download_json":"https://pith.science/pith/L32JXNVSYBGLBZSB5MXRWHPOB5.json","view_paper":"https://pith.science/paper/L32JXNVS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04310&json=true","fetch_graph":"https://pith.science/api/pith-number/L32JXNVSYBGLBZSB5MXRWHPOB5/graph.json","fetch_events":"https://pith.science/api/pith-number/L32JXNVSYBGLBZSB5MXRWHPOB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L32JXNVSYBGLBZSB5MXRWHPOB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L32JXNVSYBGLBZSB5MXRWHPOB5/action/storage_attestation","attest_author":"https://pith.science/pith/L32JXNVSYBGLBZSB5MXRWHPOB5/action/author_attestation","sign_citation":"https://pith.science/pith/L32JXNVSYBGLBZSB5MXRWHPOB5/action/citation_signature","submit_replication":"https://pith.science/pith/L32JXNVSYBGLBZSB5MXRWHPOB5/action/replication_record"}},"created_at":"2026-06-04T01:09:03.147630+00:00","updated_at":"2026-06-04T01:09:03.147630+00:00"}