{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NCRPO36CDC7IUYAO7WC44X4PYX","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":"2eabe69f7b676f074b0418853d0ce7f69af3dbaa6e0d6600149049116d8dca86","cross_cats_sorted":["cs.AI","cs.LO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-19T06:08:39Z","title_canon_sha256":"7f6953b0a1ffb0f0949cd6804daae78e0b3eb48fcbdd3981a9c0c381392c7c0c"},"schema_version":"1.0","source":{"id":"2102.09756","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.09756","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2102.09756v2","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09756","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"NCRPO36CDC7I","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"NCRPO36CDC7IUYAO","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"NCRPO36C","created_at":"2026-07-05T02:50:09Z"}],"graph_snapshots":[{"event_id":"sha256:966d7e6f118c235a1f1f6e16d30dea8ed09caed67ef9e9b4d1dcd6d1fe13be1d","target":"graph","created_at":"2026-07-05T02:50:09Z","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/2102.09756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel approach to interactive theorem-proving (ITP) using deep reinforcement learning. The proposed framework is able to learn proof search strategies as well as tactic and arguments prediction in an end-to-end manner. We formulate the process of ITP as a Markov decision process (MDP) in which each state represents a set of potential derivation paths. This structure allows us to introduce a novel backtracking mechanism which enables the agent to efficiently discard (predicted) dead-end derivations and restart from promising alternatives. We implement the framework in the HOL4 theo","authors_text":"Amir Dezfouli, Christian Walder, Michael Norrish, Minchao Wu","cross_cats":["cs.AI","cs.LO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-19T06:08:39Z","title":"TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09756","kind":"arxiv","version":2},"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:d924525223f565a718ad1cc874138b010ff9d892947a5911d600efe22acfd471","target":"record","created_at":"2026-07-05T02:50:09Z","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":"2eabe69f7b676f074b0418853d0ce7f69af3dbaa6e0d6600149049116d8dca86","cross_cats_sorted":["cs.AI","cs.LO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-19T06:08:39Z","title_canon_sha256":"7f6953b0a1ffb0f0949cd6804daae78e0b3eb48fcbdd3981a9c0c381392c7c0c"},"schema_version":"1.0","source":{"id":"2102.09756","kind":"arxiv","version":2}},"canonical_sha256":"68a2f76fc218be8a600efd85ce5f8fc5c97fcd6530427ceafa32fc4763d098ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68a2f76fc218be8a600efd85ce5f8fc5c97fcd6530427ceafa32fc4763d098ee","first_computed_at":"2026-07-05T02:50:09.328355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:09.328355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cf49EhqZyFnkL+pNONqAW6xf/o7NlpS8B0dc6ZQbNLKgAiU015peQQFg3OTED5dLe9QFg9fzL/8fJFs1X2StBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:09.328746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.09756","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d924525223f565a718ad1cc874138b010ff9d892947a5911d600efe22acfd471","sha256:966d7e6f118c235a1f1f6e16d30dea8ed09caed67ef9e9b4d1dcd6d1fe13be1d"],"state_sha256":"05bd8bfe157de8f45e0eb582b9d430f43a9c7fdda4daba52bca60d4b66ed5f37"}