{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AR6UHUZYQGJVTCEDYJKF4E4GZE","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":"01e0c24cfc6c9e3e52479773a211f8a65c85cb492c7cce71868e3ce1c8e21fc8","cross_cats_sorted":["cs.AI","cs.HC","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T17:59:42Z","title_canon_sha256":"37863ae2f143b3e4c150bd2ec951a041a91545e6dab0bf83f04fc1dc663f3710"},"schema_version":"1.0","source":{"id":"2606.07515","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07515","created_at":"2026-06-08T01:05:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07515v1","created_at":"2026-06-08T01:05:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07515","created_at":"2026-06-08T01:05:32Z"},{"alias_kind":"pith_short_12","alias_value":"AR6UHUZYQGJV","created_at":"2026-06-08T01:05:32Z"},{"alias_kind":"pith_short_16","alias_value":"AR6UHUZYQGJVTCED","created_at":"2026-06-08T01:05:32Z"},{"alias_kind":"pith_short_8","alias_value":"AR6UHUZY","created_at":"2026-06-08T01:05:32Z"}],"graph_snapshots":[{"event_id":"sha256:52ff365f0d38a406e4245df6b59499f35ad47946957fbd4aa69fc7f2c76152d5","target":"graph","created_at":"2026-06-08T01:05:32Z","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/2606.07515/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the probabilistic reasoning capabilities of large language models through a controlled benchmarking study on discrete probability problems. We constructed two datasets, respectively a set of standard exercises and a set of counterintuitive exercises, designed to trigger heuristic reasoning, and evaluated 8 state-of-the-art models, each tested with and without Chain-of-Thought prompting. Models achieve an average accuracy of 0.96 on standard problems but only 0.59 on counterintuitive ones. We further provide empirical evidence of token bias: performance drops by over 20% when can","authors_text":"Bernardo Busoni, Gianmarco Bet, Luca Avena","cross_cats":["cs.AI","cs.HC","math.PR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T17:59:42Z","title":"How reliable are LLMs when it comes to playing dice?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07515","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:fdbef1043109694fb774decfe06ee5c4f2542e3dd7c4b8a8bb710434c14c485a","target":"record","created_at":"2026-06-08T01:05:32Z","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":"01e0c24cfc6c9e3e52479773a211f8a65c85cb492c7cce71868e3ce1c8e21fc8","cross_cats_sorted":["cs.AI","cs.HC","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T17:59:42Z","title_canon_sha256":"37863ae2f143b3e4c150bd2ec951a041a91545e6dab0bf83f04fc1dc663f3710"},"schema_version":"1.0","source":{"id":"2606.07515","kind":"arxiv","version":1}},"canonical_sha256":"047d43d3388193598883c2545e1386c902d69fc986c273254a45320e33a70e66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"047d43d3388193598883c2545e1386c902d69fc986c273254a45320e33a70e66","first_computed_at":"2026-06-08T01:05:32.296552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:05:32.296552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i9CCKAPfqnk/JiHsUPHgqj+EvTjmM2GwNROKKymMVzYDFglwdqgtrxHQltWiKEKcq6Ea1UBN1ZSdqA9ZOAGPAA==","signature_status":"signed_v1","signed_at":"2026-06-08T01:05:32.297477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07515","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdbef1043109694fb774decfe06ee5c4f2542e3dd7c4b8a8bb710434c14c485a","sha256:52ff365f0d38a406e4245df6b59499f35ad47946957fbd4aa69fc7f2c76152d5"],"state_sha256":"15c95d7d101663542411163fd48bf79ed75223886ba9522e2529b716d8866d61"}