{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:VO3XCJY56VSTLK43SKW2C5F5CT","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":"68ed103e56a2a6f934b4f625f68de2233dbbd0e34941918fb2f5392ad85d20a4","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-03T21:29:53Z","title_canon_sha256":"226b7ab8d45b2fdef7bf57fa38eb1c39482dfe7b16a71e34deb4a066969cc27e"},"schema_version":"1.0","source":{"id":"2008.01204","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.01204","created_at":"2026-07-05T01:24:18Z"},{"alias_kind":"arxiv_version","alias_value":"2008.01204v1","created_at":"2026-07-05T01:24:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.01204","created_at":"2026-07-05T01:24:18Z"},{"alias_kind":"pith_short_12","alias_value":"VO3XCJY56VST","created_at":"2026-07-05T01:24:18Z"},{"alias_kind":"pith_short_16","alias_value":"VO3XCJY56VSTLK43","created_at":"2026-07-05T01:24:18Z"},{"alias_kind":"pith_short_8","alias_value":"VO3XCJY5","created_at":"2026-07-05T01:24:18Z"}],"graph_snapshots":[{"event_id":"sha256:f941925eddd67fafc9bf0aacc53cd75741430216ab2713420e75d7f1ba8ba6da","target":"graph","created_at":"2026-07-05T01:24:18Z","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/2008.01204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is great interest in using formal methods to guarantee the reliability of deep neural networks. However, these techniques may also be used to implant carefully selected input-output pairs. We present initial results on a novel technique for using SMT solvers to fine tune the weights of a ReLU neural network to guarantee outcomes on a finite set of particular examples. This procedure can be used to ensure performance on key examples, but it could also be used to insert difficult-to-find incorrect examples that trigger unexpected performance. We demonstrate this approach by fine tuning an ","authors_text":"Aurora Schmidt, Daniel Genin, Ivan Papusha, Joshua Brul\\'e, Rosa Wu, Yanni Kouskoulas","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-03T21:29:53Z","title":"Incorrect by Construction: Fine Tuning Neural Networks for Guaranteed Performance on Finite Sets of Examples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.01204","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:d31e4140f7664eebbcd51cf834d1cc310c1dfdc9762aef20d6e8524b5a11a1c8","target":"record","created_at":"2026-07-05T01:24:18Z","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":"68ed103e56a2a6f934b4f625f68de2233dbbd0e34941918fb2f5392ad85d20a4","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-03T21:29:53Z","title_canon_sha256":"226b7ab8d45b2fdef7bf57fa38eb1c39482dfe7b16a71e34deb4a066969cc27e"},"schema_version":"1.0","source":{"id":"2008.01204","kind":"arxiv","version":1}},"canonical_sha256":"abb771271df56535ab9b92ada174bd14db8256a09b88a3fc8e58b0566065db3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abb771271df56535ab9b92ada174bd14db8256a09b88a3fc8e58b0566065db3d","first_computed_at":"2026-07-05T01:24:18.609851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:24:18.609851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S26tuo1sVnHQCFRDVztzzxYyt1b9ll0pbcXpZPfuAHAIJtDS66FXJQexv4qxogrRdMFSsVB6Wfp8C87gnZZSBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:24:18.610290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.01204","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d31e4140f7664eebbcd51cf834d1cc310c1dfdc9762aef20d6e8524b5a11a1c8","sha256:f941925eddd67fafc9bf0aacc53cd75741430216ab2713420e75d7f1ba8ba6da"],"state_sha256":"804d1ac197f24a9c087eb14ded0399557f8b534e0314a169c51d3d8cbe26df98"}