{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AZ6SPJIVM22XRXF2HITZU5ZMB5","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":"147de6d2154f90c31af0cdcd949ed111dabfa3753b25263b4ab39175c73e490e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T17:51:24Z","title_canon_sha256":"95f9f7943e1f4eb8ebd61dd99ee2ea85282aaa17f7f639cba98c9ad08a73c26e"},"schema_version":"1.0","source":{"id":"2406.12830","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12830","created_at":"2026-07-05T09:13:36Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12830v3","created_at":"2026-07-05T09:13:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12830","created_at":"2026-07-05T09:13:36Z"},{"alias_kind":"pith_short_12","alias_value":"AZ6SPJIVM22X","created_at":"2026-07-05T09:13:36Z"},{"alias_kind":"pith_short_16","alias_value":"AZ6SPJIVM22XRXF2","created_at":"2026-07-05T09:13:36Z"},{"alias_kind":"pith_short_8","alias_value":"AZ6SPJIV","created_at":"2026-07-05T09:13:36Z"}],"graph_snapshots":[{"event_id":"sha256:479657a43ce8e433b2669514558ecc8617129e805f53a2dba1b0ddf00a45d498","target":"graph","created_at":"2026-07-05T09:13:36Z","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/2406.12830/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LM) are capable of remarkably complex linguistic tasks; however, numerical reasoning is an area in which they frequently struggle. An important but rarely evaluated form of reasoning is understanding probability distributions. In this paper, we focus on evaluating the probabilistic reasoning capabilities of LMs using idealized and real-world statistical distributions. We perform a systematic evaluation of state-of-the-art LMs on three tasks: estimating percentiles, drawing samples, and calculating probabilities. We evaluate three ways to provide context to LMs 1) anchoring exa","authors_text":"Akshay Paruchuri, Daniel McDuff, Jacob Sunshine, Jake Garrison, John Hernandez, Shun Liao, Tim Althoff, Xin Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T17:51:24Z","title":"What Are the Odds? Language Models Are Capable of Probabilistic Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12830","kind":"arxiv","version":3},"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":"sha256:12952d6cdd6316be6aab8d4e9a8935845026dd255bcc759515cd786370153976","target":"record","created_at":"2026-07-05T09:13:36Z","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":"147de6d2154f90c31af0cdcd949ed111dabfa3753b25263b4ab39175c73e490e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T17:51:24Z","title_canon_sha256":"95f9f7943e1f4eb8ebd61dd99ee2ea85282aaa17f7f639cba98c9ad08a73c26e"},"schema_version":"1.0","source":{"id":"2406.12830","kind":"arxiv","version":3}},"canonical_sha256":"067d27a51566b578dcba3a279a772c0f6d02fd395552d125aa2f149f07fe88f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"067d27a51566b578dcba3a279a772c0f6d02fd395552d125aa2f149f07fe88f0","first_computed_at":"2026-07-05T09:13:36.907205Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:36.907205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"budQxzcPw3QqzBmXZGYaT7TVbVROuUkDITOzi5bzaVyBvkYWl7pXSyq0abjH6IZdfEEUSzK0b1MoHhAXOnBsCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:36.907712Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12830","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12952d6cdd6316be6aab8d4e9a8935845026dd255bcc759515cd786370153976","sha256:479657a43ce8e433b2669514558ecc8617129e805f53a2dba1b0ddf00a45d498"],"state_sha256":"2134aa7997c85f8689d23aff4c77794d03b9e7592d2925a6087d48f96047bd14"}