{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PF3MTVX5LKP6L4JYR6FYR35LVG","short_pith_number":"pith:PF3MTVX5","schema_version":"1.0","canonical_sha256":"7976c9d6fd5a9fe5f1388f8b88efaba9ac5a894a193e43dfe8c94a1a7e53ee78","source":{"kind":"arxiv","id":"2105.14706","version":2},"attestation_state":"computed","paper":{"title":"The Role of Entropy in Guiding a Connection Prover","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Josef Urban, Miroslav Ol\\v{s}\\'ak, Zsolt Zombori","submitted_at":"2021-05-31T04:57:44Z","abstract_excerpt":"In this work we study how to learn good algorithms for selecting reasoning steps in theorem proving. We explore this in the connection tableau calculus implemented by leanCoP where the partial tableau provides a clean and compact notion of a state to which a limited number of inferences can be applied. We start by incorporating a state-of-the-art learning algorithm -- a graph neural network (GNN) -- into the plCoP theorem prover. Then we use it to observe the system's behaviour in a reinforcement learning setting, i.e., when learning inference guidance from successful Monte-Carlo tree searches"},"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":"2105.14706","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-05-31T04:57:44Z","cross_cats_sorted":["cs.LG","cs.LO"],"title_canon_sha256":"afb7321015c51032b68493c412ff262877194cc237aeb8b1d7ffc92ec481b951","abstract_canon_sha256":"0561cb26c20826d2e28306e7458080ef4ceee4cef67dd0bf7db0510694c6cf2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:26.469132Z","signature_b64":"4cm7EmtF+hjWCoTVYNHIePoUZPEeDyniE9zAQPKX0nH04IhpTSzSf1qj+D9y5rjkyClNqU1EHjwcsUBIJ5EfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7976c9d6fd5a9fe5f1388f8b88efaba9ac5a894a193e43dfe8c94a1a7e53ee78","last_reissued_at":"2026-07-05T02:58:26.468735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:26.468735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Role of Entropy in Guiding a Connection Prover","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Josef Urban, Miroslav Ol\\v{s}\\'ak, Zsolt Zombori","submitted_at":"2021-05-31T04:57:44Z","abstract_excerpt":"In this work we study how to learn good algorithms for selecting reasoning steps in theorem proving. We explore this in the connection tableau calculus implemented by leanCoP where the partial tableau provides a clean and compact notion of a state to which a limited number of inferences can be applied. We start by incorporating a state-of-the-art learning algorithm -- a graph neural network (GNN) -- into the plCoP theorem prover. Then we use it to observe the system's behaviour in a reinforcement learning setting, i.e., when learning inference guidance from successful Monte-Carlo tree searches"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14706","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/2105.14706/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":"2105.14706","created_at":"2026-07-05T02:58:26.468784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.14706v2","created_at":"2026-07-05T02:58:26.468784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14706","created_at":"2026-07-05T02:58:26.468784+00:00"},{"alias_kind":"pith_short_12","alias_value":"PF3MTVX5LKP6","created_at":"2026-07-05T02:58:26.468784+00:00"},{"alias_kind":"pith_short_16","alias_value":"PF3MTVX5LKP6L4JY","created_at":"2026-07-05T02:58:26.468784+00:00"},{"alias_kind":"pith_short_8","alias_value":"PF3MTVX5","created_at":"2026-07-05T02:58:26.468784+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/PF3MTVX5LKP6L4JYR6FYR35LVG","json":"https://pith.science/pith/PF3MTVX5LKP6L4JYR6FYR35LVG.json","graph_json":"https://pith.science/api/pith-number/PF3MTVX5LKP6L4JYR6FYR35LVG/graph.json","events_json":"https://pith.science/api/pith-number/PF3MTVX5LKP6L4JYR6FYR35LVG/events.json","paper":"https://pith.science/paper/PF3MTVX5"},"agent_actions":{"view_html":"https://pith.science/pith/PF3MTVX5LKP6L4JYR6FYR35LVG","download_json":"https://pith.science/pith/PF3MTVX5LKP6L4JYR6FYR35LVG.json","view_paper":"https://pith.science/paper/PF3MTVX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.14706&json=true","fetch_graph":"https://pith.science/api/pith-number/PF3MTVX5LKP6L4JYR6FYR35LVG/graph.json","fetch_events":"https://pith.science/api/pith-number/PF3MTVX5LKP6L4JYR6FYR35LVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PF3MTVX5LKP6L4JYR6FYR35LVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PF3MTVX5LKP6L4JYR6FYR35LVG/action/storage_attestation","attest_author":"https://pith.science/pith/PF3MTVX5LKP6L4JYR6FYR35LVG/action/author_attestation","sign_citation":"https://pith.science/pith/PF3MTVX5LKP6L4JYR6FYR35LVG/action/citation_signature","submit_replication":"https://pith.science/pith/PF3MTVX5LKP6L4JYR6FYR35LVG/action/replication_record"}},"created_at":"2026-07-05T02:58:26.468784+00:00","updated_at":"2026-07-05T02:58:26.468784+00:00"}