{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RLQZERNWEPBZEW4BKSDO4DGZ75","short_pith_number":"pith:RLQZERNW","canonical_record":{"source":{"id":"2501.18310","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T12:37:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba6e7ceb2e288b222268a6b5facfeebc3efc46748e93a767c3ea8471e6dd160c","abstract_canon_sha256":"6bfe8cc249967cbe24bdb4c2c798645e3a2b8aca38f13c9e11847d7460922862"},"schema_version":"1.0"},"canonical_sha256":"8ae19245b623c3925b815486ee0cd9ff4bee581e73319e8f0e0f02fedb9745aa","source":{"kind":"arxiv","id":"2501.18310","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18310","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18310v2","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18310","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"pith_short_12","alias_value":"RLQZERNWEPBZ","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"pith_short_16","alias_value":"RLQZERNWEPBZEW4B","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"pith_short_8","alias_value":"RLQZERNW","created_at":"2026-07-05T11:17:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RLQZERNWEPBZEW4BKSDO4DGZ75","target":"record","payload":{"canonical_record":{"source":{"id":"2501.18310","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T12:37:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba6e7ceb2e288b222268a6b5facfeebc3efc46748e93a767c3ea8471e6dd160c","abstract_canon_sha256":"6bfe8cc249967cbe24bdb4c2c798645e3a2b8aca38f13c9e11847d7460922862"},"schema_version":"1.0"},"canonical_sha256":"8ae19245b623c3925b815486ee0cd9ff4bee581e73319e8f0e0f02fedb9745aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:23.270750Z","signature_b64":"ivLTQZePHrOH/S/RExuKUdti0ZosXyjx6JSdtxyQHRckxVF0oRg2lM9GeGW18O10FR0pX68+OJL9vs3GausSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ae19245b623c3925b815486ee0cd9ff4bee581e73319e8f0e0f02fedb9745aa","last_reissued_at":"2026-07-05T11:17:23.270251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:23.270251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.18310","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":"2026-07-05T11:17:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Qej/Pp5B0USI4MvZVUnUb3Q+rOlyzKTCtUD2zpjizqety3ITeFqv373v8x6AetE6trPET3EtyGX6jd9e/zEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:38:49.804713Z"},"content_sha256":"fc602fe305556831997737a4399d434edd5cf63c80748b6b3a7227a775e576f9","schema_version":"1.0","event_id":"sha256:fc602fe305556831997737a4399d434edd5cf63c80748b6b3a7227a775e576f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RLQZERNWEPBZEW4BKSDO4DGZ75","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrew C Yao, Haoxiong Liu, Jiacheng Sun, Zhenguo Li","submitted_at":"2025-01-30T12:37:06Z","abstract_excerpt":"The synergy between deep learning models and traditional automation tools, such as built-in tactics of the proof assistant and off-the-shelf automated theorem provers, plays a crucial role in developing robust and efficient neural theorem provers(NTPs). However, for proof synthesis with LLMs, previous work applies automation tools either only when explicitly invoked by the model or at a single granularity level, failing to fully exploit their power. To solve this issue, we propose ProofAug, a procedure that equips LLMs with automation methods at various granularities through fine-grained struc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18310","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/2501.18310/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":"2026-07-05T11:17:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wT3LshB5eMJKv1LpC3CYi1AxqwC+VVU8m2uNgf1R30qm0fBwmA0KjP2/LNrRXYYiQytkAb/3g9ldu48kcrjmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:38:49.805259Z"},"content_sha256":"8a1d9ceb55d7fb2da8b0a69de5b2918b7f21f63bd81187b62c48466ebc17240a","schema_version":"1.0","event_id":"sha256:8a1d9ceb55d7fb2da8b0a69de5b2918b7f21f63bd81187b62c48466ebc17240a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RLQZERNWEPBZEW4BKSDO4DGZ75/bundle.json","state_url":"https://pith.science/pith/RLQZERNWEPBZEW4BKSDO4DGZ75/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RLQZERNWEPBZEW4BKSDO4DGZ75/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":"2026-08-07T03:38:49Z","links":{"resolver":"https://pith.science/pith/RLQZERNWEPBZEW4BKSDO4DGZ75","bundle":"https://pith.science/pith/RLQZERNWEPBZEW4BKSDO4DGZ75/bundle.json","state":"https://pith.science/pith/RLQZERNWEPBZEW4BKSDO4DGZ75/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RLQZERNWEPBZEW4BKSDO4DGZ75/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RLQZERNWEPBZEW4BKSDO4DGZ75","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":"6bfe8cc249967cbe24bdb4c2c798645e3a2b8aca38f13c9e11847d7460922862","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T12:37:06Z","title_canon_sha256":"ba6e7ceb2e288b222268a6b5facfeebc3efc46748e93a767c3ea8471e6dd160c"},"schema_version":"1.0","source":{"id":"2501.18310","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18310","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18310v2","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18310","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"pith_short_12","alias_value":"RLQZERNWEPBZ","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"pith_short_16","alias_value":"RLQZERNWEPBZEW4B","created_at":"2026-07-05T11:17:23Z"},{"alias_kind":"pith_short_8","alias_value":"RLQZERNW","created_at":"2026-07-05T11:17:23Z"}],"graph_snapshots":[{"event_id":"sha256:8a1d9ceb55d7fb2da8b0a69de5b2918b7f21f63bd81187b62c48466ebc17240a","target":"graph","created_at":"2026-07-05T11:17:23Z","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/2501.18310/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The synergy between deep learning models and traditional automation tools, such as built-in tactics of the proof assistant and off-the-shelf automated theorem provers, plays a crucial role in developing robust and efficient neural theorem provers(NTPs). However, for proof synthesis with LLMs, previous work applies automation tools either only when explicitly invoked by the model or at a single granularity level, failing to fully exploit their power. To solve this issue, we propose ProofAug, a procedure that equips LLMs with automation methods at various granularities through fine-grained struc","authors_text":"Andrew C Yao, Haoxiong Liu, Jiacheng Sun, Zhenguo Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T12:37:06Z","title":"ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18310","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:fc602fe305556831997737a4399d434edd5cf63c80748b6b3a7227a775e576f9","target":"record","created_at":"2026-07-05T11:17:23Z","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":"6bfe8cc249967cbe24bdb4c2c798645e3a2b8aca38f13c9e11847d7460922862","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T12:37:06Z","title_canon_sha256":"ba6e7ceb2e288b222268a6b5facfeebc3efc46748e93a767c3ea8471e6dd160c"},"schema_version":"1.0","source":{"id":"2501.18310","kind":"arxiv","version":2}},"canonical_sha256":"8ae19245b623c3925b815486ee0cd9ff4bee581e73319e8f0e0f02fedb9745aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ae19245b623c3925b815486ee0cd9ff4bee581e73319e8f0e0f02fedb9745aa","first_computed_at":"2026-07-05T11:17:23.270251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:23.270251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ivLTQZePHrOH/S/RExuKUdti0ZosXyjx6JSdtxyQHRckxVF0oRg2lM9GeGW18O10FR0pX68+OJL9vs3GausSDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:23.270750Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18310","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc602fe305556831997737a4399d434edd5cf63c80748b6b3a7227a775e576f9","sha256:8a1d9ceb55d7fb2da8b0a69de5b2918b7f21f63bd81187b62c48466ebc17240a"],"state_sha256":"86d4ce2efa8d4b347fadf846de5534e266c80a465f5382c7cef8cf386f51a743"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IuQlEOBgr37YbECIfNwBw/V2r6a0FerGQmmj81znMCP3Bql9DGietS/mtvtXmdqj++hPW+gJWK/MAQqNbtj7AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T03:38:49.810280Z","bundle_sha256":"ba42213546e04ab0c00a773d3f3203032bd9fb654821508c66fb2f20d75b6bfa"}}