{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NCRPO36CDC7IUYAO7WC44X4PYX","short_pith_number":"pith:NCRPO36C","canonical_record":{"source":{"id":"2102.09756","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-19T06:08:39Z","cross_cats_sorted":["cs.AI","cs.LO"],"title_canon_sha256":"7f6953b0a1ffb0f0949cd6804daae78e0b3eb48fcbdd3981a9c0c381392c7c0c","abstract_canon_sha256":"2eabe69f7b676f074b0418853d0ce7f69af3dbaa6e0d6600149049116d8dca86"},"schema_version":"1.0"},"canonical_sha256":"68a2f76fc218be8a600efd85ce5f8fc5c97fcd6530427ceafa32fc4763d098ee","source":{"kind":"arxiv","id":"2102.09756","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NCRPO36CDC7IUYAO7WC44X4PYX","target":"record","payload":{"canonical_record":{"source":{"id":"2102.09756","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-19T06:08:39Z","cross_cats_sorted":["cs.AI","cs.LO"],"title_canon_sha256":"7f6953b0a1ffb0f0949cd6804daae78e0b3eb48fcbdd3981a9c0c381392c7c0c","abstract_canon_sha256":"2eabe69f7b676f074b0418853d0ce7f69af3dbaa6e0d6600149049116d8dca86"},"schema_version":"1.0"},"canonical_sha256":"68a2f76fc218be8a600efd85ce5f8fc5c97fcd6530427ceafa32fc4763d098ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:09.328746Z","signature_b64":"cf49EhqZyFnkL+pNONqAW6xf/o7NlpS8B0dc6ZQbNLKgAiU015peQQFg3OTED5dLe9QFg9fzL/8fJFs1X2StBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68a2f76fc218be8a600efd85ce5f8fc5c97fcd6530427ceafa32fc4763d098ee","last_reissued_at":"2026-07-05T02:50:09.328355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:09.328355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.09756","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K9D/baJjc3HzSbn9waW2qLW8BfdjaupxoIgWTwvlYsIjcHKWx1ZGu7jJv9EtqZnT0CzaR84eyS5gYQmW8U+iCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:47:53.824604Z"},"content_sha256":"d924525223f565a718ad1cc874138b010ff9d892947a5911d600efe22acfd471","schema_version":"1.0","event_id":"sha256:d924525223f565a718ad1cc874138b010ff9d892947a5911d600efe22acfd471"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NCRPO36CDC7IUYAO7WC44X4PYX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LO"],"primary_cat":"cs.LG","authors_text":"Amir Dezfouli, Christian Walder, Michael Norrish, Minchao Wu","submitted_at":"2021-02-19T06:08:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09756","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/2102.09756/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hzmLs06wckoach7dHei9lwuOfVJnGALYqP9qbzeKWPlSbqDC4dzTVj32m025bxSzVSzlm+LRTVr0Ma+YXZcvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:47:53.825136Z"},"content_sha256":"966d7e6f118c235a1f1f6e16d30dea8ed09caed67ef9e9b4d1dcd6d1fe13be1d","schema_version":"1.0","event_id":"sha256:966d7e6f118c235a1f1f6e16d30dea8ed09caed67ef9e9b4d1dcd6d1fe13be1d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NCRPO36CDC7IUYAO7WC44X4PYX/bundle.json","state_url":"https://pith.science/pith/NCRPO36CDC7IUYAO7WC44X4PYX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NCRPO36CDC7IUYAO7WC44X4PYX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T17:47:53Z","links":{"resolver":"https://pith.science/pith/NCRPO36CDC7IUYAO7WC44X4PYX","bundle":"https://pith.science/pith/NCRPO36CDC7IUYAO7WC44X4PYX/bundle.json","state":"https://pith.science/pith/NCRPO36CDC7IUYAO7WC44X4PYX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NCRPO36CDC7IUYAO7WC44X4PYX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zKqA+Md3uYcYu60xAJzD2ki7kyMl+xdqHn66AdBZCmHvJFMX36BrtuIYk7Ej/GvhsW1B+YVUh5O4ULsNMXKWCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T17:47:53.829261Z","bundle_sha256":"904f7aadfabb7663b8595b5e69598d002005e360057e4d315444e6990fd9d480"}}