{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OS4GYRGL64IQZXYDW2V6XRB3VA","short_pith_number":"pith:OS4GYRGL","schema_version":"1.0","canonical_sha256":"74b86c44cbf7110cdf03b6abebc43ba820c42b5516421ebeefc155e0e9e00927","source":{"kind":"arxiv","id":"2607.05185","version":1},"attestation_state":"computed","paper":{"title":"ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SC"],"primary_cat":"cs.AI","authors_text":"Hannes Rothe, Mahnoor Shahid","submitted_at":"2026-07-06T15:02:23Z","abstract_excerpt":"Compositional generalization, the ability to understand and produce novel combinations of known components, remains a fundamental challenge for modern artificial intelligence. While few benchmarks exist, many focus on linguistic tasks and lack complex, explicit compositional structures. We introduce ClassicLogic, a new benchmark suite designed to evaluate an agent's ability to learn and compose problem-solving strategies. The benchmark consists of four classic logic puzzles: Sudoku, KenKen, Kakuro, and Futoshiki. Its core innovation is a hierarchical, explicit knowledge base for each game, whe"},"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":"2607.05185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-06T15:02:23Z","cross_cats_sorted":["cs.SC"],"title_canon_sha256":"2586219da22a9c06e783adeb5cc630c9b36328b9dee043777d71a12b7680b2c3","abstract_canon_sha256":"5109192265951e3d8dc3824834a0c4560da9c6be8ed7e4d741d6e6d6a8089db2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T03:19:19.025285Z","signature_b64":"Jk16oXmgqR2vyP0vO7xN5k0PUMDdUTx30jGm8hV3XQxE462xFdAF8+cJ4fpBYczhhr+RgSQKuL4VnwNLwG8KCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74b86c44cbf7110cdf03b6abebc43ba820c42b5516421ebeefc155e0e9e00927","last_reissued_at":"2026-07-07T03:19:19.024885Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T03:19:19.024885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SC"],"primary_cat":"cs.AI","authors_text":"Hannes Rothe, Mahnoor Shahid","submitted_at":"2026-07-06T15:02:23Z","abstract_excerpt":"Compositional generalization, the ability to understand and produce novel combinations of known components, remains a fundamental challenge for modern artificial intelligence. While few benchmarks exist, many focus on linguistic tasks and lack complex, explicit compositional structures. We introduce ClassicLogic, a new benchmark suite designed to evaluate an agent's ability to learn and compose problem-solving strategies. The benchmark consists of four classic logic puzzles: Sudoku, KenKen, Kakuro, and Futoshiki. Its core innovation is a hierarchical, explicit knowledge base for each game, whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05185","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/2607.05185/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":"2607.05185","created_at":"2026-07-07T03:19:19.024939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.05185v1","created_at":"2026-07-07T03:19:19.024939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05185","created_at":"2026-07-07T03:19:19.024939+00:00"},{"alias_kind":"pith_short_12","alias_value":"OS4GYRGL64IQ","created_at":"2026-07-07T03:19:19.024939+00:00"},{"alias_kind":"pith_short_16","alias_value":"OS4GYRGL64IQZXYD","created_at":"2026-07-07T03:19:19.024939+00:00"},{"alias_kind":"pith_short_8","alias_value":"OS4GYRGL","created_at":"2026-07-07T03:19:19.024939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OS4GYRGL64IQZXYDW2V6XRB3VA","json":"https://pith.science/pith/OS4GYRGL64IQZXYDW2V6XRB3VA.json","graph_json":"https://pith.science/api/pith-number/OS4GYRGL64IQZXYDW2V6XRB3VA/graph.json","events_json":"https://pith.science/api/pith-number/OS4GYRGL64IQZXYDW2V6XRB3VA/events.json","paper":"https://pith.science/paper/OS4GYRGL"},"agent_actions":{"view_html":"https://pith.science/pith/OS4GYRGL64IQZXYDW2V6XRB3VA","download_json":"https://pith.science/pith/OS4GYRGL64IQZXYDW2V6XRB3VA.json","view_paper":"https://pith.science/paper/OS4GYRGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.05185&json=true","fetch_graph":"https://pith.science/api/pith-number/OS4GYRGL64IQZXYDW2V6XRB3VA/graph.json","fetch_events":"https://pith.science/api/pith-number/OS4GYRGL64IQZXYDW2V6XRB3VA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OS4GYRGL64IQZXYDW2V6XRB3VA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OS4GYRGL64IQZXYDW2V6XRB3VA/action/storage_attestation","attest_author":"https://pith.science/pith/OS4GYRGL64IQZXYDW2V6XRB3VA/action/author_attestation","sign_citation":"https://pith.science/pith/OS4GYRGL64IQZXYDW2V6XRB3VA/action/citation_signature","submit_replication":"https://pith.science/pith/OS4GYRGL64IQZXYDW2V6XRB3VA/action/replication_record"}},"created_at":"2026-07-07T03:19:19.024939+00:00","updated_at":"2026-07-07T03:19:19.024939+00:00"}