{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XQK2CAFLS2D7L5PXWPWJKU7OHA","short_pith_number":"pith:XQK2CAFL","canonical_record":{"source":{"id":"2502.16906","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T07:02:31Z","cross_cats_sorted":[],"title_canon_sha256":"3c3b3b6eff72e6b14c85cc80823ce14b198b631fb2434947ad36cd0a492fb976","abstract_canon_sha256":"420d234b33b312106d45f043bd2c5a73a06f9d62b7f17def358311959edffbc1"},"schema_version":"1.0"},"canonical_sha256":"bc15a100ab9687f5f5f7b3ec9553ee380496c8f74b69bebec7e9bd5b36da0768","source":{"kind":"arxiv","id":"2502.16906","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.16906","created_at":"2026-07-05T10:19:02Z"},{"alias_kind":"arxiv_version","alias_value":"2502.16906v1","created_at":"2026-07-05T10:19:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16906","created_at":"2026-07-05T10:19:02Z"},{"alias_kind":"pith_short_12","alias_value":"XQK2CAFLS2D7","created_at":"2026-07-05T10:19:02Z"},{"alias_kind":"pith_short_16","alias_value":"XQK2CAFLS2D7L5PX","created_at":"2026-07-05T10:19:02Z"},{"alias_kind":"pith_short_8","alias_value":"XQK2CAFL","created_at":"2026-07-05T10:19:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XQK2CAFLS2D7L5PXWPWJKU7OHA","target":"record","payload":{"canonical_record":{"source":{"id":"2502.16906","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T07:02:31Z","cross_cats_sorted":[],"title_canon_sha256":"3c3b3b6eff72e6b14c85cc80823ce14b198b631fb2434947ad36cd0a492fb976","abstract_canon_sha256":"420d234b33b312106d45f043bd2c5a73a06f9d62b7f17def358311959edffbc1"},"schema_version":"1.0"},"canonical_sha256":"bc15a100ab9687f5f5f7b3ec9553ee380496c8f74b69bebec7e9bd5b36da0768","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:02.014006Z","signature_b64":"JWEneG4AQepEXRd+aazyfcM07mjEaxFVrhJY5oDE0Zrnn1U8xQQk0/kIOwSWXhyvlda4kv+lHjBDl/UXwD21Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc15a100ab9687f5f5f7b3ec9553ee380496c8f74b69bebec7e9bd5b36da0768","last_reissued_at":"2026-07-05T10:19:02.013412Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:02.013412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.16906","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":"2026-07-05T10:19:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fry4x3zsGtF2PaYKNr303199dk3GVk8gSriWcc0waLlTap0RENlBoAWg1q+ZigCi2tnn2+gNMdPE5QrVHM81DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:17:36.912506Z"},"content_sha256":"0eb1d8997685ae002018bea42ab377915822b6cce7fe99e079f713e26c55cd14","schema_version":"1.0","event_id":"sha256:0eb1d8997685ae002018bea42ab377915822b6cce7fe99e079f713e26c55cd14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XQK2CAFLS2D7L5PXWPWJKU7OHA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Yu, Fei Huang, Junyang Lin, Keming Lu, Qinyuan Cheng, Qin Zhu, Runyu Peng, Xipeng Qiu, Xuanjing Huang","submitted_at":"2025-02-24T07:02:31Z","abstract_excerpt":"While logical reasoning evaluation of Large Language Models (LLMs) has attracted significant attention, existing benchmarks predominantly rely on multiple-choice formats that are vulnerable to random guessing, leading to overestimated performance and substantial performance fluctuations. To obtain more accurate assessments of models' reasoning capabilities, we propose an automated method for synthesizing open-ended logic puzzles, and use it to develop a bilingual benchmark, AutoLogi. Our approach features program-based verification and controllable difficulty levels, enabling more reliable eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16906","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/2502.16906/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":"2026-07-05T10:19:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vXws2AGLxjWjJI7Y3a19axwtHVpDZQYkfXyAlJJt+V3P3g8DrdzXg68J2yUmKstRdNSDoLJeKqMtqB+D3PP1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:17:36.914146Z"},"content_sha256":"84bb91e78e2fcf578a54bfc3f3e4df4bb9dd9e2808a137ca43ff61b00e65b395","schema_version":"1.0","event_id":"sha256:84bb91e78e2fcf578a54bfc3f3e4df4bb9dd9e2808a137ca43ff61b00e65b395"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XQK2CAFLS2D7L5PXWPWJKU7OHA/bundle.json","state_url":"https://pith.science/pith/XQK2CAFLS2D7L5PXWPWJKU7OHA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XQK2CAFLS2D7L5PXWPWJKU7OHA/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":"2026-08-10T18:17:36Z","links":{"resolver":"https://pith.science/pith/XQK2CAFLS2D7L5PXWPWJKU7OHA","bundle":"https://pith.science/pith/XQK2CAFLS2D7L5PXWPWJKU7OHA/bundle.json","state":"https://pith.science/pith/XQK2CAFLS2D7L5PXWPWJKU7OHA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XQK2CAFLS2D7L5PXWPWJKU7OHA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XQK2CAFLS2D7L5PXWPWJKU7OHA","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":"420d234b33b312106d45f043bd2c5a73a06f9d62b7f17def358311959edffbc1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T07:02:31Z","title_canon_sha256":"3c3b3b6eff72e6b14c85cc80823ce14b198b631fb2434947ad36cd0a492fb976"},"schema_version":"1.0","source":{"id":"2502.16906","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.16906","created_at":"2026-07-05T10:19:02Z"},{"alias_kind":"arxiv_version","alias_value":"2502.16906v1","created_at":"2026-07-05T10:19:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16906","created_at":"2026-07-05T10:19:02Z"},{"alias_kind":"pith_short_12","alias_value":"XQK2CAFLS2D7","created_at":"2026-07-05T10:19:02Z"},{"alias_kind":"pith_short_16","alias_value":"XQK2CAFLS2D7L5PX","created_at":"2026-07-05T10:19:02Z"},{"alias_kind":"pith_short_8","alias_value":"XQK2CAFL","created_at":"2026-07-05T10:19:02Z"}],"graph_snapshots":[{"event_id":"sha256:84bb91e78e2fcf578a54bfc3f3e4df4bb9dd9e2808a137ca43ff61b00e65b395","target":"graph","created_at":"2026-07-05T10:19:02Z","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/2502.16906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While logical reasoning evaluation of Large Language Models (LLMs) has attracted significant attention, existing benchmarks predominantly rely on multiple-choice formats that are vulnerable to random guessing, leading to overestimated performance and substantial performance fluctuations. To obtain more accurate assessments of models' reasoning capabilities, we propose an automated method for synthesizing open-ended logic puzzles, and use it to develop a bilingual benchmark, AutoLogi. Our approach features program-based verification and controllable difficulty levels, enabling more reliable eva","authors_text":"Bowen Yu, Fei Huang, Junyang Lin, Keming Lu, Qinyuan Cheng, Qin Zhu, Runyu Peng, Xipeng Qiu, Xuanjing Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T07:02:31Z","title":"AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16906","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":"sha256:0eb1d8997685ae002018bea42ab377915822b6cce7fe99e079f713e26c55cd14","target":"record","created_at":"2026-07-05T10:19:02Z","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":"420d234b33b312106d45f043bd2c5a73a06f9d62b7f17def358311959edffbc1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T07:02:31Z","title_canon_sha256":"3c3b3b6eff72e6b14c85cc80823ce14b198b631fb2434947ad36cd0a492fb976"},"schema_version":"1.0","source":{"id":"2502.16906","kind":"arxiv","version":1}},"canonical_sha256":"bc15a100ab9687f5f5f7b3ec9553ee380496c8f74b69bebec7e9bd5b36da0768","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc15a100ab9687f5f5f7b3ec9553ee380496c8f74b69bebec7e9bd5b36da0768","first_computed_at":"2026-07-05T10:19:02.013412Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:02.013412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JWEneG4AQepEXRd+aazyfcM07mjEaxFVrhJY5oDE0Zrnn1U8xQQk0/kIOwSWXhyvlda4kv+lHjBDl/UXwD21Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:02.014006Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.16906","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0eb1d8997685ae002018bea42ab377915822b6cce7fe99e079f713e26c55cd14","sha256:84bb91e78e2fcf578a54bfc3f3e4df4bb9dd9e2808a137ca43ff61b00e65b395"],"state_sha256":"20f3d08131f2b627c607370fe8bb3241cb2a6d3730b60f3596bdb1c631430d54"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dvYtxlKFQ4GLmBopN9DXEwlbaUeOJV/7vfVm+T4GIIfhO/+sc5NAAIAtakb3z6G37uFApH90LCM+Q6S7acTBAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:17:36.924848Z","bundle_sha256":"774014830473f81292e6d9c3a76e0f013bf71ca46792d34e0779fb96ae00d542"}}