{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4FGZWKXG3PTCKGETEKESK5CZWQ","short_pith_number":"pith:4FGZWKXG","schema_version":"1.0","canonical_sha256":"e14d9b2ae6dbe62518932289257459b4275635cc3be250b9f86ad5eba1abdf48","source":{"kind":"arxiv","id":"2406.12546","version":2},"attestation_state":"computed","paper":{"title":"Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Philipp Mondorf","submitted_at":"2024-06-18T12:24:22Z","abstract_excerpt":"Knights and knaves problems represent a classic genre of logical puzzles where characters either tell the truth or lie. The objective is to logically deduce each character's identity based on their statements. The challenge arises from the truth-telling or lying behavior, which influences the logical implications of each statement. Solving these puzzles requires not only direct deductions from individual statements, but the ability to assess the truthfulness of statements by reasoning through various hypothetical scenarios. As such, knights and knaves puzzles serve as compelling examples of su"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.12546","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T12:24:22Z","cross_cats_sorted":[],"title_canon_sha256":"cc7ef3574f826448d385daf71daeb359a0f5a425ceff8b33856944b0fe4a4057","abstract_canon_sha256":"97282c45c97504c43429714192348eaff3ded82d265082b789767d780cbbc2ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:13.936203Z","signature_b64":"gKdUJRyr18+6ENMYNC+ZaPGLdPBCY+mX6mehkito5skSWBFs9JVwCRaIIFVjfnIN3hOOqL5Mxx+7byrO03SnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e14d9b2ae6dbe62518932289257459b4275635cc3be250b9f86ad5eba1abdf48","last_reissued_at":"2026-07-05T09:17:13.935754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:13.935754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Philipp Mondorf","submitted_at":"2024-06-18T12:24:22Z","abstract_excerpt":"Knights and knaves problems represent a classic genre of logical puzzles where characters either tell the truth or lie. The objective is to logically deduce each character's identity based on their statements. The challenge arises from the truth-telling or lying behavior, which influences the logical implications of each statement. Solving these puzzles requires not only direct deductions from individual statements, but the ability to assess the truthfulness of statements by reasoning through various hypothetical scenarios. As such, knights and knaves puzzles serve as compelling examples of su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12546","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/2406.12546/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.12546","created_at":"2026-07-05T09:17:13.935812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12546v2","created_at":"2026-07-05T09:17:13.935812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12546","created_at":"2026-07-05T09:17:13.935812+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FGZWKXG3PTC","created_at":"2026-07-05T09:17:13.935812+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FGZWKXG3PTCKGET","created_at":"2026-07-05T09:17:13.935812+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FGZWKXG","created_at":"2026-07-05T09:17:13.935812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.16745","citing_title":"Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4FGZWKXG3PTCKGETEKESK5CZWQ","json":"https://pith.science/pith/4FGZWKXG3PTCKGETEKESK5CZWQ.json","graph_json":"https://pith.science/api/pith-number/4FGZWKXG3PTCKGETEKESK5CZWQ/graph.json","events_json":"https://pith.science/api/pith-number/4FGZWKXG3PTCKGETEKESK5CZWQ/events.json","paper":"https://pith.science/paper/4FGZWKXG"},"agent_actions":{"view_html":"https://pith.science/pith/4FGZWKXG3PTCKGETEKESK5CZWQ","download_json":"https://pith.science/pith/4FGZWKXG3PTCKGETEKESK5CZWQ.json","view_paper":"https://pith.science/paper/4FGZWKXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12546&json=true","fetch_graph":"https://pith.science/api/pith-number/4FGZWKXG3PTCKGETEKESK5CZWQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4FGZWKXG3PTCKGETEKESK5CZWQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FGZWKXG3PTCKGETEKESK5CZWQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FGZWKXG3PTCKGETEKESK5CZWQ/action/storage_attestation","attest_author":"https://pith.science/pith/4FGZWKXG3PTCKGETEKESK5CZWQ/action/author_attestation","sign_citation":"https://pith.science/pith/4FGZWKXG3PTCKGETEKESK5CZWQ/action/citation_signature","submit_replication":"https://pith.science/pith/4FGZWKXG3PTCKGETEKESK5CZWQ/action/replication_record"}},"created_at":"2026-07-05T09:17:13.935812+00:00","updated_at":"2026-07-05T09:17:13.935812+00:00"}