{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6KHS4CL4MSCZGIY3GYRXTLZEHC","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":"056fcb335094a2f257eaa1fb10b698d1ba8784df725d44a1b826fde36c212496","cross_cats_sorted":["cs.AI","cs.CL","cs.DS","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T16:29:25Z","title_canon_sha256":"6383462608e7006aa82b5ff70b3238421faa9ea2bc169fb4f371a81f138e5d53"},"schema_version":"1.0","source":{"id":"2406.04229","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04229","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04229v1","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04229","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"6KHS4CL4MSCZ","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"6KHS4CL4MSCZGIY3","created_at":"2026-07-05T08:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"6KHS4CL4","created_at":"2026-07-05T08:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:35d42b102e3868a33204af696d337a6f6c62b5b3ea4bad49fef40075ea2578eb","target":"graph","created_at":"2026-07-05T08:28:28Z","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/2406.04229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Eliciting reasoning capabilities from language models (LMs) is a critical direction on the path towards building intelligent systems. Most recent studies dedicated to reasoning focus on out-of-distribution performance on procedurally-generated synthetic benchmarks, bespoke-built to evaluate specific skills only. This trend makes results hard to transfer across publications, slowing down progress. Three years ago, a similar issue was identified and rectified in the field of neural algorithmic reasoning, with the advent of the CLRS benchmark. CLRS is a dataset generator comprising graph executio","authors_text":"Alex Vitvitskyi, Avi Schwarzschild, Borja Ibarz, Charles Blundell, Larisa Markeeva, Olga Kozlova, Petar Veli\\v{c}kovi\\'c, Sean McLeish, Tom Goldstein, Wilfried Bounsi","cross_cats":["cs.AI","cs.CL","cs.DS","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T16:29:25Z","title":"The CLRS-Text Algorithmic Reasoning Language Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04229","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:a3cb88c93d87471ab9c96f80e40fe4fef54370bb19d28a81d339cab941794141","target":"record","created_at":"2026-07-05T08:28:28Z","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":"056fcb335094a2f257eaa1fb10b698d1ba8784df725d44a1b826fde36c212496","cross_cats_sorted":["cs.AI","cs.CL","cs.DS","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T16:29:25Z","title_canon_sha256":"6383462608e7006aa82b5ff70b3238421faa9ea2bc169fb4f371a81f138e5d53"},"schema_version":"1.0","source":{"id":"2406.04229","kind":"arxiv","version":1}},"canonical_sha256":"f28f2e097c648593231b362379af2438a79a71026c4aa5a160e501611e6fded2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f28f2e097c648593231b362379af2438a79a71026c4aa5a160e501611e6fded2","first_computed_at":"2026-07-05T08:28:28.257231Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:28.257231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VtHIvu+0RiQpU8ots72eOW5DmsF6jsgXJ2OjBvW73IR0efH2SA4bJER2lgjHcFdVrYcUxPghP/1rVHTHAqn6CA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:28.257713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04229","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3cb88c93d87471ab9c96f80e40fe4fef54370bb19d28a81d339cab941794141","sha256:35d42b102e3868a33204af696d337a6f6c62b5b3ea4bad49fef40075ea2578eb"],"state_sha256":"dfeb5e9afa5e11c034f65849231b5454eb7087986afa9a6ffb5f50006f0a47b0"}