{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:YAC3XAZ4NSZEMC5I6JP5HSMCZC","short_pith_number":"pith:YAC3XAZ4","schema_version":"1.0","canonical_sha256":"c005bb833c6cb2460ba8f25fd3c982c889b19ccc8bb02147990bfd05e4d7fb60","source":{"kind":"arxiv","id":"1606.04442","version":2},"attestation_state":"computed","paper":{"title":"DeepMath - Deep Sequence Models for Premise Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Alex A. Alemi, Christian Szegedy, Francois Chollet, Geoffrey Irving, Josef Urban, Niklas Een","submitted_at":"2016-06-14T16:27:41Z","abstract_excerpt":"We study the effectiveness of neural sequence models for premise selection in automated theorem proving, one of the main bottlenecks in the formalization of mathematics. We propose a two stage approach for this task that yields good results for the premise selection task on the Mizar corpus while avoiding the hand-engineered features of existing state-of-the-art models. To our knowledge, this is the first time deep learning has been applied to theorem proving on a large scale."},"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":"1606.04442","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-14T16:27:41Z","cross_cats_sorted":["cs.LG","cs.LO"],"title_canon_sha256":"20b886344fe7314b236ba9f2260959be0cdece2d9cbe3c77d37b6a8868089dd7","abstract_canon_sha256":"22660d1b887dd3dbc8a88cf18258f12d910f6aaac89e1c65cbad66f8665d6799"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:02.029126Z","signature_b64":"6dtmIWeSeSR2fnlXAp/0FVGZ3whUxz9R85Ez/wAA1C3KVU5nOhjJTkVMgjZ3LOV8ke74LE1Tc9pWeJLoupx9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c005bb833c6cb2460ba8f25fd3c982c889b19ccc8bb02147990bfd05e4d7fb60","last_reissued_at":"2026-05-18T00:52:02.028626Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:02.028626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepMath - Deep Sequence Models for Premise Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Alex A. Alemi, Christian Szegedy, Francois Chollet, Geoffrey Irving, Josef Urban, Niklas Een","submitted_at":"2016-06-14T16:27:41Z","abstract_excerpt":"We study the effectiveness of neural sequence models for premise selection in automated theorem proving, one of the main bottlenecks in the formalization of mathematics. We propose a two stage approach for this task that yields good results for the premise selection task on the Mizar corpus while avoiding the hand-engineered features of existing state-of-the-art models. To our knowledge, this is the first time deep learning has been applied to theorem proving on a large scale."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.04442","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":""},"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":"1606.04442","created_at":"2026-05-18T00:52:02.028695+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.04442v2","created_at":"2026-05-18T00:52:02.028695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.04442","created_at":"2026-05-18T00:52:02.028695+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAC3XAZ4NSZE","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAC3XAZ4NSZEMC5I","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAC3XAZ4","created_at":"2026-05-18T12:30:53.716459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09012","citing_title":"Re$^2$Math: Benchmarking Theorem Retrieval in Research-Level Mathematics","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YAC3XAZ4NSZEMC5I6JP5HSMCZC","json":"https://pith.science/pith/YAC3XAZ4NSZEMC5I6JP5HSMCZC.json","graph_json":"https://pith.science/api/pith-number/YAC3XAZ4NSZEMC5I6JP5HSMCZC/graph.json","events_json":"https://pith.science/api/pith-number/YAC3XAZ4NSZEMC5I6JP5HSMCZC/events.json","paper":"https://pith.science/paper/YAC3XAZ4"},"agent_actions":{"view_html":"https://pith.science/pith/YAC3XAZ4NSZEMC5I6JP5HSMCZC","download_json":"https://pith.science/pith/YAC3XAZ4NSZEMC5I6JP5HSMCZC.json","view_paper":"https://pith.science/paper/YAC3XAZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.04442&json=true","fetch_graph":"https://pith.science/api/pith-number/YAC3XAZ4NSZEMC5I6JP5HSMCZC/graph.json","fetch_events":"https://pith.science/api/pith-number/YAC3XAZ4NSZEMC5I6JP5HSMCZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAC3XAZ4NSZEMC5I6JP5HSMCZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAC3XAZ4NSZEMC5I6JP5HSMCZC/action/storage_attestation","attest_author":"https://pith.science/pith/YAC3XAZ4NSZEMC5I6JP5HSMCZC/action/author_attestation","sign_citation":"https://pith.science/pith/YAC3XAZ4NSZEMC5I6JP5HSMCZC/action/citation_signature","submit_replication":"https://pith.science/pith/YAC3XAZ4NSZEMC5I6JP5HSMCZC/action/replication_record"}},"created_at":"2026-05-18T00:52:02.028695+00:00","updated_at":"2026-05-18T00:52:02.028695+00:00"}