{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OS4GYRGL64IQZXYDW2V6XRB3VA","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":"5109192265951e3d8dc3824834a0c4560da9c6be8ed7e4d741d6e6d6a8089db2","cross_cats_sorted":["cs.SC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-06T15:02:23Z","title_canon_sha256":"2586219da22a9c06e783adeb5cc630c9b36328b9dee043777d71a12b7680b2c3"},"schema_version":"1.0","source":{"id":"2607.05185","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05185","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05185v1","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05185","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"pith_short_12","alias_value":"OS4GYRGL64IQ","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"pith_short_16","alias_value":"OS4GYRGL64IQZXYD","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"pith_short_8","alias_value":"OS4GYRGL","created_at":"2026-07-07T03:19:19Z"}],"graph_snapshots":[{"event_id":"sha256:d268915c20afd31260190b8d7392cc781f07fea78f3f2582064b8db8053c42ae","target":"graph","created_at":"2026-07-07T03:19:19Z","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/2607.05185/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hannes Rothe, Mahnoor Shahid","cross_cats":["cs.SC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-06T15:02:23Z","title":"ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05185","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":"sha256:023b87088f0d086244fe9ade2860f6b0693ccbd7b4364f283b7d46594a937c12","target":"record","created_at":"2026-07-07T03:19:19Z","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":"5109192265951e3d8dc3824834a0c4560da9c6be8ed7e4d741d6e6d6a8089db2","cross_cats_sorted":["cs.SC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-06T15:02:23Z","title_canon_sha256":"2586219da22a9c06e783adeb5cc630c9b36328b9dee043777d71a12b7680b2c3"},"schema_version":"1.0","source":{"id":"2607.05185","kind":"arxiv","version":1}},"canonical_sha256":"74b86c44cbf7110cdf03b6abebc43ba820c42b5516421ebeefc155e0e9e00927","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74b86c44cbf7110cdf03b6abebc43ba820c42b5516421ebeefc155e0e9e00927","first_computed_at":"2026-07-07T03:19:19.024885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T03:19:19.024885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jk16oXmgqR2vyP0vO7xN5k0PUMDdUTx30jGm8hV3XQxE462xFdAF8+cJ4fpBYczhhr+RgSQKuL4VnwNLwG8KCw==","signature_status":"signed_v1","signed_at":"2026-07-07T03:19:19.025285Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.05185","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:023b87088f0d086244fe9ade2860f6b0693ccbd7b4364f283b7d46594a937c12","sha256:d268915c20afd31260190b8d7392cc781f07fea78f3f2582064b8db8053c42ae"],"state_sha256":"d2baa6018c3bec52667893c60e2e2993e167b0325c0e165ac04fdfe7b0f0c350"}