{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:X6QRV6O4AZY52NVWECFA4OGML3","short_pith_number":"pith:X6QRV6O4","schema_version":"1.0","canonical_sha256":"bfa11af9dc0671dd36b6208a0e38cc5ef1c1394b9a065752728b214390922fe4","source":{"kind":"arxiv","id":"2006.08852","version":1},"attestation_state":"computed","paper":{"title":"Counterexample-Guided Learning of Monotonic Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aishwarya Sivaraman, Golnoosh Farnadi, Guy Van den Broeck, Todd Millstein","submitted_at":"2020-06-16T01:04:26Z","abstract_excerpt":"The widespread adoption of deep learning is often attributed to its automatic feature construction with minimal inductive bias. However, in many real-world tasks, the learned function is intended to satisfy domain-specific constraints. We focus on monotonicity constraints, which are common and require that the function's output increases with increasing values of specific input features. We develop a counterexample-guided technique to provably enforce monotonicity constraints at prediction time. Additionally, we propose a technique to use monotonicity as an inductive bias for deep learning. It"},"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":"2006.08852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T01:04:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a689ad838462b57c1e6faf9cd10d674cf49d9fc359847f022f107efc10504560","abstract_canon_sha256":"1732449ba8f92a6a54df396e5cb34b9d2004364ff953972f7549c7ffc86adee9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:43.644722Z","signature_b64":"XBX7xy7Gp87YnrlViHP11isq+xK9BDm7juLktA/x9G7NH9SHEvkc7NMMMfZhXRbSgXpMO3gnaJ4R+9AwmEzVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfa11af9dc0671dd36b6208a0e38cc5ef1c1394b9a065752728b214390922fe4","last_reissued_at":"2026-07-05T01:10:43.644296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:43.644296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counterexample-Guided Learning of Monotonic Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aishwarya Sivaraman, Golnoosh Farnadi, Guy Van den Broeck, Todd Millstein","submitted_at":"2020-06-16T01:04:26Z","abstract_excerpt":"The widespread adoption of deep learning is often attributed to its automatic feature construction with minimal inductive bias. However, in many real-world tasks, the learned function is intended to satisfy domain-specific constraints. We focus on monotonicity constraints, which are common and require that the function's output increases with increasing values of specific input features. We develop a counterexample-guided technique to provably enforce monotonicity constraints at prediction time. Additionally, we propose a technique to use monotonicity as an inductive bias for deep learning. It"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08852","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/2006.08852/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":"2006.08852","created_at":"2026-07-05T01:10:43.644364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.08852v1","created_at":"2026-07-05T01:10:43.644364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08852","created_at":"2026-07-05T01:10:43.644364+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6QRV6O4AZY5","created_at":"2026-07-05T01:10:43.644364+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6QRV6O4AZY52NVW","created_at":"2026-07-05T01:10:43.644364+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6QRV6O4","created_at":"2026-07-05T01:10:43.644364+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/X6QRV6O4AZY52NVWECFA4OGML3","json":"https://pith.science/pith/X6QRV6O4AZY52NVWECFA4OGML3.json","graph_json":"https://pith.science/api/pith-number/X6QRV6O4AZY52NVWECFA4OGML3/graph.json","events_json":"https://pith.science/api/pith-number/X6QRV6O4AZY52NVWECFA4OGML3/events.json","paper":"https://pith.science/paper/X6QRV6O4"},"agent_actions":{"view_html":"https://pith.science/pith/X6QRV6O4AZY52NVWECFA4OGML3","download_json":"https://pith.science/pith/X6QRV6O4AZY52NVWECFA4OGML3.json","view_paper":"https://pith.science/paper/X6QRV6O4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.08852&json=true","fetch_graph":"https://pith.science/api/pith-number/X6QRV6O4AZY52NVWECFA4OGML3/graph.json","fetch_events":"https://pith.science/api/pith-number/X6QRV6O4AZY52NVWECFA4OGML3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6QRV6O4AZY52NVWECFA4OGML3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6QRV6O4AZY52NVWECFA4OGML3/action/storage_attestation","attest_author":"https://pith.science/pith/X6QRV6O4AZY52NVWECFA4OGML3/action/author_attestation","sign_citation":"https://pith.science/pith/X6QRV6O4AZY52NVWECFA4OGML3/action/citation_signature","submit_replication":"https://pith.science/pith/X6QRV6O4AZY52NVWECFA4OGML3/action/replication_record"}},"created_at":"2026-07-05T01:10:43.644364+00:00","updated_at":"2026-07-05T01:10:43.644364+00:00"}