{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5EH67PQPNGULHV6V7MHNWP2BP4","short_pith_number":"pith:5EH67PQP","schema_version":"1.0","canonical_sha256":"e90fefbe0f69a8b3d7d5fb0edb3f417f2e690cc1381c3eaf38f712e96d91e788","source":{"kind":"arxiv","id":"2002.10766","version":2},"attestation_state":"computed","paper":{"title":"Teaching the Old Dog New Tricks: Supervised Learning with Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabrizio Detassis, Michela Milano, Michele Lombardi","submitted_at":"2020-02-25T09:47:39Z","abstract_excerpt":"Adding constraint support in Machine Learning has the potential to address outstanding issues in data-driven AI systems, such as safety and fairness. Existing approaches typically apply constrained optimization techniques to ML training, enforce constraint satisfaction by adjusting the model design, or use constraints to correct the output. Here, we investigate a different, complementary, strategy based on \"teaching\" constraint satisfaction to a supervised ML method via the direct use of a state-of-the-art constraint solver: this enables taking advantage of decades of research on constrained o"},"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":"2002.10766","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-25T09:47:39Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"046bc29cfdb8383a57843cc8ba9bc357e03c4cc3412018f9ca220676bba56afa","abstract_canon_sha256":"53fe020ae778d24ad80dcf2f0af0174c3863411095691b1934d5ed1e0c489081"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:43.627637Z","signature_b64":"hisxYB6vFqnxpfR6ff+2Uv5Mi1T+J8lK/ErvDUMWqYOubYxaTrK1PASIOtcsjbucP2WPg0nzEjBA+ZqpQgf2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e90fefbe0f69a8b3d7d5fb0edb3f417f2e690cc1381c3eaf38f712e96d91e788","last_reissued_at":"2026-07-05T02:18:43.627128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:43.627128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teaching the Old Dog New Tricks: Supervised Learning with Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabrizio Detassis, Michela Milano, Michele Lombardi","submitted_at":"2020-02-25T09:47:39Z","abstract_excerpt":"Adding constraint support in Machine Learning has the potential to address outstanding issues in data-driven AI systems, such as safety and fairness. Existing approaches typically apply constrained optimization techniques to ML training, enforce constraint satisfaction by adjusting the model design, or use constraints to correct the output. Here, we investigate a different, complementary, strategy based on \"teaching\" constraint satisfaction to a supervised ML method via the direct use of a state-of-the-art constraint solver: this enables taking advantage of decades of research on constrained o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.10766","kind":"arxiv","version":2},"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/2002.10766/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":"2002.10766","created_at":"2026-07-05T02:18:43.627181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.10766v2","created_at":"2026-07-05T02:18:43.627181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.10766","created_at":"2026-07-05T02:18:43.627181+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EH67PQPNGUL","created_at":"2026-07-05T02:18:43.627181+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EH67PQPNGULHV6V","created_at":"2026-07-05T02:18:43.627181+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EH67PQP","created_at":"2026-07-05T02:18:43.627181+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/5EH67PQPNGULHV6V7MHNWP2BP4","json":"https://pith.science/pith/5EH67PQPNGULHV6V7MHNWP2BP4.json","graph_json":"https://pith.science/api/pith-number/5EH67PQPNGULHV6V7MHNWP2BP4/graph.json","events_json":"https://pith.science/api/pith-number/5EH67PQPNGULHV6V7MHNWP2BP4/events.json","paper":"https://pith.science/paper/5EH67PQP"},"agent_actions":{"view_html":"https://pith.science/pith/5EH67PQPNGULHV6V7MHNWP2BP4","download_json":"https://pith.science/pith/5EH67PQPNGULHV6V7MHNWP2BP4.json","view_paper":"https://pith.science/paper/5EH67PQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.10766&json=true","fetch_graph":"https://pith.science/api/pith-number/5EH67PQPNGULHV6V7MHNWP2BP4/graph.json","fetch_events":"https://pith.science/api/pith-number/5EH67PQPNGULHV6V7MHNWP2BP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EH67PQPNGULHV6V7MHNWP2BP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EH67PQPNGULHV6V7MHNWP2BP4/action/storage_attestation","attest_author":"https://pith.science/pith/5EH67PQPNGULHV6V7MHNWP2BP4/action/author_attestation","sign_citation":"https://pith.science/pith/5EH67PQPNGULHV6V7MHNWP2BP4/action/citation_signature","submit_replication":"https://pith.science/pith/5EH67PQPNGULHV6V7MHNWP2BP4/action/replication_record"}},"created_at":"2026-07-05T02:18:43.627181+00:00","updated_at":"2026-07-05T02:18:43.627181+00:00"}