{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EFBFVPDILPDKE6JR4UC7B5XNKW","short_pith_number":"pith:EFBFVPDI","canonical_record":{"source":{"id":"2502.00855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-02T17:00:22Z","cross_cats_sorted":[],"title_canon_sha256":"024b24b5afc45303c55c72cd8fe8f5b7d8e9444a5b97427294bcd9142c749af9","abstract_canon_sha256":"139cf4197f938094035a2807f238e3ca0eeca498cef5e97d2de4e0e7fee0b15e"},"schema_version":"1.0"},"canonical_sha256":"21425abc685bc6a27931e505f0f6ed55a18274df20d6958b07a7701d93c6e750","source":{"kind":"arxiv","id":"2502.00855","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00855","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00855v1","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00855","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"pith_short_12","alias_value":"EFBFVPDILPDK","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"pith_short_16","alias_value":"EFBFVPDILPDKE6JR","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"pith_short_8","alias_value":"EFBFVPDI","created_at":"2026-07-05T10:08:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EFBFVPDILPDKE6JR4UC7B5XNKW","target":"record","payload":{"canonical_record":{"source":{"id":"2502.00855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-02T17:00:22Z","cross_cats_sorted":[],"title_canon_sha256":"024b24b5afc45303c55c72cd8fe8f5b7d8e9444a5b97427294bcd9142c749af9","abstract_canon_sha256":"139cf4197f938094035a2807f238e3ca0eeca498cef5e97d2de4e0e7fee0b15e"},"schema_version":"1.0"},"canonical_sha256":"21425abc685bc6a27931e505f0f6ed55a18274df20d6958b07a7701d93c6e750","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:39.312768Z","signature_b64":"wJWyFMlqTW/L4xqXBBH+wbDhP26c784hilDCDOY8mDzbqyyo6fk/NlCgsn2GUVB6vJiNDw5zCzBqn2jTLRk1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21425abc685bc6a27931e505f0f6ed55a18274df20d6958b07a7701d93c6e750","last_reissued_at":"2026-07-05T10:08:39.312390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:39.312390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.00855","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:08:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"duYx4mtoIsZZbTe2OJdlNd78VbNV9TbEOJrJII9VX5HyS2oczQbr4mGN/Bpamq5tHVoAov6K27EdYHLaegqQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:57:58.182037Z"},"content_sha256":"97f2d7154c4aed2cb1c9073dfb58ab90f0eb9d288fe10026344ffe2de55c43de","schema_version":"1.0","event_id":"sha256:97f2d7154c4aed2cb1c9073dfb58ab90f0eb9d288fe10026344ffe2de55c43de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EFBFVPDILPDKE6JR4UC7B5XNKW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Psychometric-Based Evaluation for Theorem Proving with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Feng Yang, Jianyu Zhang, Jilin Hu, Long Zhang, Xiaokun Luan, Yongwang Zhao, Zhiwei Xu","submitted_at":"2025-02-02T17:00:22Z","abstract_excerpt":"Large language models (LLMs) for formal theorem proving have become a prominent research focus. At present, the proving ability of these LLMs is mainly evaluated through proof pass rates on datasets such as miniF2F. However, this evaluation method overlooks the varying importance of theorems. As a result, it fails to highlight the real performance disparities between LLMs and leads to high evaluation costs. This study proposes a psychometric-based evaluation method for theorem proving with LLMs, comprising two main components: Dataset Annotation and Adaptive Evaluation. First, we propose a met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00855","kind":"arxiv","version":1},"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/2502.00855/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":"2026-07-05T10:08:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n4SaDGzKqxeyv8cveRQ/8n5qQnywmlmbMl8ujmgr/DbX2VOMoBH6zCH1hs0SBc3DXy9cVm5L3lnrhy7BK+eCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:57:58.182428Z"},"content_sha256":"905805669369bc3c6a8473dbf871fce93afb4ebdcc3324841f2264d887936fc0","schema_version":"1.0","event_id":"sha256:905805669369bc3c6a8473dbf871fce93afb4ebdcc3324841f2264d887936fc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EFBFVPDILPDKE6JR4UC7B5XNKW/bundle.json","state_url":"https://pith.science/pith/EFBFVPDILPDKE6JR4UC7B5XNKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EFBFVPDILPDKE6JR4UC7B5XNKW/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":"2026-07-07T11:57:58Z","links":{"resolver":"https://pith.science/pith/EFBFVPDILPDKE6JR4UC7B5XNKW","bundle":"https://pith.science/pith/EFBFVPDILPDKE6JR4UC7B5XNKW/bundle.json","state":"https://pith.science/pith/EFBFVPDILPDKE6JR4UC7B5XNKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EFBFVPDILPDKE6JR4UC7B5XNKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EFBFVPDILPDKE6JR4UC7B5XNKW","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":"139cf4197f938094035a2807f238e3ca0eeca498cef5e97d2de4e0e7fee0b15e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-02T17:00:22Z","title_canon_sha256":"024b24b5afc45303c55c72cd8fe8f5b7d8e9444a5b97427294bcd9142c749af9"},"schema_version":"1.0","source":{"id":"2502.00855","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00855","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00855v1","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00855","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"pith_short_12","alias_value":"EFBFVPDILPDK","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"pith_short_16","alias_value":"EFBFVPDILPDKE6JR","created_at":"2026-07-05T10:08:39Z"},{"alias_kind":"pith_short_8","alias_value":"EFBFVPDI","created_at":"2026-07-05T10:08:39Z"}],"graph_snapshots":[{"event_id":"sha256:905805669369bc3c6a8473dbf871fce93afb4ebdcc3324841f2264d887936fc0","target":"graph","created_at":"2026-07-05T10:08:39Z","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/2502.00855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) for formal theorem proving have become a prominent research focus. At present, the proving ability of these LLMs is mainly evaluated through proof pass rates on datasets such as miniF2F. However, this evaluation method overlooks the varying importance of theorems. As a result, it fails to highlight the real performance disparities between LLMs and leads to high evaluation costs. This study proposes a psychometric-based evaluation method for theorem proving with LLMs, comprising two main components: Dataset Annotation and Adaptive Evaluation. First, we propose a met","authors_text":"Feng Yang, Jianyu Zhang, Jilin Hu, Long Zhang, Xiaokun Luan, Yongwang Zhao, Zhiwei Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-02T17:00:22Z","title":"Psychometric-Based Evaluation for Theorem Proving with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00855","kind":"arxiv","version":1},"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":"sha256:97f2d7154c4aed2cb1c9073dfb58ab90f0eb9d288fe10026344ffe2de55c43de","target":"record","created_at":"2026-07-05T10:08:39Z","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":"139cf4197f938094035a2807f238e3ca0eeca498cef5e97d2de4e0e7fee0b15e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-02T17:00:22Z","title_canon_sha256":"024b24b5afc45303c55c72cd8fe8f5b7d8e9444a5b97427294bcd9142c749af9"},"schema_version":"1.0","source":{"id":"2502.00855","kind":"arxiv","version":1}},"canonical_sha256":"21425abc685bc6a27931e505f0f6ed55a18274df20d6958b07a7701d93c6e750","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21425abc685bc6a27931e505f0f6ed55a18274df20d6958b07a7701d93c6e750","first_computed_at":"2026-07-05T10:08:39.312390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:39.312390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wJWyFMlqTW/L4xqXBBH+wbDhP26c784hilDCDOY8mDzbqyyo6fk/NlCgsn2GUVB6vJiNDw5zCzBqn2jTLRk1Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:39.312768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00855","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97f2d7154c4aed2cb1c9073dfb58ab90f0eb9d288fe10026344ffe2de55c43de","sha256:905805669369bc3c6a8473dbf871fce93afb4ebdcc3324841f2264d887936fc0"],"state_sha256":"8ab36ed6ab2445e75c1916b6f6c4336bd6609c06d077727bf020ec1561f2b966"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b9aqjMZ68yWQ2yiqN85krHC1Eal1x+OSy0XpmYppfiWMKPY2nQFEuRR48u2ayR8oSvND31TSSokTS/GTUsM3Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:57:58.184342Z","bundle_sha256":"bf6d1f4c65765948d97f6c0fb65811c317474d6307d0bbbe9b995bfd7a6d7cfb"}}