{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LYCF5MGK546WQ2CIQB6TGLP66Y","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":"de1e54f1390507bb2f24182f650b1a5ef9ce9886aa49763c46aa5333e55d5cd5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2025-03-28T18:54:56Z","title_canon_sha256":"ec232819c2547ece245f8448e715cadf4011643c6b1606ec1e23672bece7e948"},"schema_version":"1.0","source":{"id":"2503.22832","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22832","created_at":"2026-07-05T10:47:37Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22832v2","created_at":"2026-07-05T10:47:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22832","created_at":"2026-07-05T10:47:37Z"},{"alias_kind":"pith_short_12","alias_value":"LYCF5MGK546W","created_at":"2026-07-05T10:47:37Z"},{"alias_kind":"pith_short_16","alias_value":"LYCF5MGK546WQ2CI","created_at":"2026-07-05T10:47:37Z"},{"alias_kind":"pith_short_8","alias_value":"LYCF5MGK","created_at":"2026-07-05T10:47:37Z"}],"graph_snapshots":[{"event_id":"sha256:fa36f283bfc9cc624018382ae0bdf3ee559be26a7c88c78a116dc0e305c961c7","target":"graph","created_at":"2026-07-05T10:47:37Z","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/2503.22832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Complex reasoning tasks often rely on the ability to consistently and accurately apply simple rules across incremental steps, a foundational capability which we term \"level-0\" reasoning. To systematically evaluate this capability, we introduce L0-Bench, a language model benchmark for testing procedural correctness -- the ability to generate correct reasoning processes, complementing existing benchmarks that primarily focus on outcome correctness. Given synthetic Python functions with simple operations, L0-Bench grades models on their ability to generate step-by-step, error-free execution trace","authors_text":"Boris Ginsburg, Cheng-Ping Hsieh, Erik Arakelyan, Faisal Ladhak, Santiago Akle Serano, Simeng Sun","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2025-03-28T18:54:56Z","title":"L0-Reasoning Bench: Evaluating Procedural Correctness in Language Models via Simple Program Execution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22832","kind":"arxiv","version":2},"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":"sha256:045ef065713d6032c9f38e287c024438c318f329f6137b63671c6c14fcdbb720","target":"record","created_at":"2026-07-05T10:47:37Z","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":"de1e54f1390507bb2f24182f650b1a5ef9ce9886aa49763c46aa5333e55d5cd5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2025-03-28T18:54:56Z","title_canon_sha256":"ec232819c2547ece245f8448e715cadf4011643c6b1606ec1e23672bece7e948"},"schema_version":"1.0","source":{"id":"2503.22832","kind":"arxiv","version":2}},"canonical_sha256":"5e045eb0caef3d686848807d332dfef605861b9ae5509d6ce9019fc226b1726b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e045eb0caef3d686848807d332dfef605861b9ae5509d6ce9019fc226b1726b","first_computed_at":"2026-07-05T10:47:37.299401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:37.299401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Je/4YFzMxBY02hm06cfDnrS+9FuAGz6cb2iRampHRaRWAWO5E4RYz8Sl2S0k751ALg4+qwpGEaI0RokJ6BSMAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:37.299880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.22832","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:045ef065713d6032c9f38e287c024438c318f329f6137b63671c6c14fcdbb720","sha256:fa36f283bfc9cc624018382ae0bdf3ee559be26a7c88c78a116dc0e305c961c7"],"state_sha256":"fd6b7ac72e090c240184ccda625e150a6edc19ab05c735aaa7e02130a961a4e3"}