{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UNHKNSOGCZ2SGVFLLU7QVXI2WE","short_pith_number":"pith:UNHKNSOG","schema_version":"1.0","canonical_sha256":"a34ea6c9c616752354ab5d3f0add1ab1091db53930361f9444459caf934e1cf7","source":{"kind":"arxiv","id":"2402.11291","version":3},"attestation_state":"computed","paper":{"title":"Puzzle Solving using Reasoning of Large Language Models: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Giorgos Filandrianos, Giorgos Stamou, Maria Lymperaiou, Panagiotis Giadikiaroglou","submitted_at":"2024-02-17T14:19:38Z","abstract_excerpt":"Exploring the capabilities of Large Language Models (LLMs) in puzzle solving unveils critical insights into their potential and challenges in AI, marking a significant step towards understanding their applicability in complex reasoning tasks. This survey leverages a unique taxonomy -- dividing puzzles into rule-based and rule-less categories -- to critically assess LLMs through various methodologies, including prompting techniques, neuro-symbolic approaches, and fine-tuning. Through a critical review of relevant datasets and benchmarks, we assess LLMs' performance, identifying significant chal"},"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":"2402.11291","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-17T14:19:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db7884a0a732b04996abf5b8ade456d3f6558d48809af43952fb63a78abd5b6d","abstract_canon_sha256":"295fe7ec98742d59c2b20105e56ecd6d47ff66be7a1bcef8ef6a46f3c4b2e71e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:34.135266Z","signature_b64":"Tp77Yp08nkkhv2DwYsdvfkSBPhyhrAJSmFZefARLqga6c6CDO6BIbZ0XmBJn5ba0ea0Ct9JU+BJ6toWZ54MZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a34ea6c9c616752354ab5d3f0add1ab1091db53930361f9444459caf934e1cf7","last_reissued_at":"2026-07-05T11:46:34.134518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:34.134518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Puzzle Solving using Reasoning of Large Language Models: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Giorgos Filandrianos, Giorgos Stamou, Maria Lymperaiou, Panagiotis Giadikiaroglou","submitted_at":"2024-02-17T14:19:38Z","abstract_excerpt":"Exploring the capabilities of Large Language Models (LLMs) in puzzle solving unveils critical insights into their potential and challenges in AI, marking a significant step towards understanding their applicability in complex reasoning tasks. This survey leverages a unique taxonomy -- dividing puzzles into rule-based and rule-less categories -- to critically assess LLMs through various methodologies, including prompting techniques, neuro-symbolic approaches, and fine-tuning. Through a critical review of relevant datasets and benchmarks, we assess LLMs' performance, identifying significant chal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11291","kind":"arxiv","version":3},"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/2402.11291/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":"2402.11291","created_at":"2026-07-05T11:46:34.134659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11291v3","created_at":"2026-07-05T11:46:34.134659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11291","created_at":"2026-07-05T11:46:34.134659+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNHKNSOGCZ2S","created_at":"2026-07-05T11:46:34.134659+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNHKNSOGCZ2SGVFL","created_at":"2026-07-05T11:46:34.134659+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNHKNSOG","created_at":"2026-07-05T11:46:34.134659+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05185","citing_title":"ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2508.08636","citing_title":"InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11223","citing_title":"Do Vision-Language-Models show human-like logical problem-solving capability in point and click puzzle games?","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNHKNSOGCZ2SGVFLLU7QVXI2WE","json":"https://pith.science/pith/UNHKNSOGCZ2SGVFLLU7QVXI2WE.json","graph_json":"https://pith.science/api/pith-number/UNHKNSOGCZ2SGVFLLU7QVXI2WE/graph.json","events_json":"https://pith.science/api/pith-number/UNHKNSOGCZ2SGVFLLU7QVXI2WE/events.json","paper":"https://pith.science/paper/UNHKNSOG"},"agent_actions":{"view_html":"https://pith.science/pith/UNHKNSOGCZ2SGVFLLU7QVXI2WE","download_json":"https://pith.science/pith/UNHKNSOGCZ2SGVFLLU7QVXI2WE.json","view_paper":"https://pith.science/paper/UNHKNSOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11291&json=true","fetch_graph":"https://pith.science/api/pith-number/UNHKNSOGCZ2SGVFLLU7QVXI2WE/graph.json","fetch_events":"https://pith.science/api/pith-number/UNHKNSOGCZ2SGVFLLU7QVXI2WE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNHKNSOGCZ2SGVFLLU7QVXI2WE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNHKNSOGCZ2SGVFLLU7QVXI2WE/action/storage_attestation","attest_author":"https://pith.science/pith/UNHKNSOGCZ2SGVFLLU7QVXI2WE/action/author_attestation","sign_citation":"https://pith.science/pith/UNHKNSOGCZ2SGVFLLU7QVXI2WE/action/citation_signature","submit_replication":"https://pith.science/pith/UNHKNSOGCZ2SGVFLLU7QVXI2WE/action/replication_record"}},"created_at":"2026-07-05T11:46:34.134659+00:00","updated_at":"2026-07-05T11:46:34.134659+00:00"}