{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4CR6XHEBYWSZSWLDESVWZUIELR","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":"cb2794955bf7efcd0063e3876f0f91933383d6543c08ea42bbc8f6c047fd1bba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T18:26:19Z","title_canon_sha256":"2451fe321684e96e0eb45213b976bb01c3c159e78f5b1698aa80e5805017fe5c"},"schema_version":"1.0","source":{"id":"2406.13764","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13764","created_at":"2026-07-05T08:34:34Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13764v1","created_at":"2026-07-05T08:34:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13764","created_at":"2026-07-05T08:34:34Z"},{"alias_kind":"pith_short_12","alias_value":"4CR6XHEBYWSZ","created_at":"2026-07-05T08:34:34Z"},{"alias_kind":"pith_short_16","alias_value":"4CR6XHEBYWSZSWLD","created_at":"2026-07-05T08:34:34Z"},{"alias_kind":"pith_short_8","alias_value":"4CR6XHEB","created_at":"2026-07-05T08:34:34Z"}],"graph_snapshots":[{"event_id":"sha256:fdd54e7c745eb846b8423c15d0f069bbf7c793b1b293b8e987ab477724baa8d5","target":"graph","created_at":"2026-07-05T08:34:34Z","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/2406.13764/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown superior capability to solve reasoning problems with programs. While being a promising direction, most of such frameworks are trained and evaluated in settings with a prior knowledge of task requirements. However, as LLMs become more capable, it is necessary to assess their reasoning abilities in more realistic scenarios where many real-world problems are open-ended with ambiguous scope, and often require multiple formalisms to solve. To investigate this, we introduce the task of reasoning in the wild, where an LLM is tasked to solve a reasoning problem ","authors_text":"Ali Payani, Ehsan Shareghi, Faramarz Fekri, Siheng Xiong, Yuan Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T18:26:19Z","title":"Can LLMs Reason in the Wild with Programs?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13764","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":"sha256:619d4def56fdcc2ef9fc04f0a7bed3bf6332f4e1a231905ff45969a3361c166f","target":"record","created_at":"2026-07-05T08:34:34Z","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":"cb2794955bf7efcd0063e3876f0f91933383d6543c08ea42bbc8f6c047fd1bba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T18:26:19Z","title_canon_sha256":"2451fe321684e96e0eb45213b976bb01c3c159e78f5b1698aa80e5805017fe5c"},"schema_version":"1.0","source":{"id":"2406.13764","kind":"arxiv","version":1}},"canonical_sha256":"e0a3eb9c81c5a599596324ab6cd1045c47c2da8aa525ad04665cb9fed1a50f5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0a3eb9c81c5a599596324ab6cd1045c47c2da8aa525ad04665cb9fed1a50f5f","first_computed_at":"2026-07-05T08:34:34.197386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:34.197386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bbTHm0LqGGEjgbIklrUVsy6RtuJsjsZ0I9uN1RDe263TCIUzoopQZ6MyhwpibggyFltf5PXrbI2RHA2Rt2pxBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:34.197839Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.13764","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:619d4def56fdcc2ef9fc04f0a7bed3bf6332f4e1a231905ff45969a3361c166f","sha256:fdd54e7c745eb846b8423c15d0f069bbf7c793b1b293b8e987ab477724baa8d5"],"state_sha256":"565813ede883058e9779b6401d8ce6b9ba10cb900592e4b7d3be3d690f45b979"}