{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NOGIKQJWSVHYW6FMTT5TMA346U","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":"b5cd7f6cc6ced0282e18c5d18afc272b22c550a2cdd6f2a79df953a364ff722e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T17:41:26Z","title_canon_sha256":"5d11cad1a341b35e0ca6cfd1be3cb01731f1e0b480107824ce52b0ed6a7bae71"},"schema_version":"1.0","source":{"id":"2210.17517","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.17517","created_at":"2026-07-05T05:49:15Z"},{"alias_kind":"arxiv_version","alias_value":"2210.17517v2","created_at":"2026-07-05T05:49:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17517","created_at":"2026-07-05T05:49:15Z"},{"alias_kind":"pith_short_12","alias_value":"NOGIKQJWSVHY","created_at":"2026-07-05T05:49:15Z"},{"alias_kind":"pith_short_16","alias_value":"NOGIKQJWSVHYW6FM","created_at":"2026-07-05T05:49:15Z"},{"alias_kind":"pith_short_8","alias_value":"NOGIKQJW","created_at":"2026-07-05T05:49:15Z"}],"graph_snapshots":[{"event_id":"sha256:e373b6efa2fa0a96b410c69bf7289f99c74b499c7517ed64313ba919ed093642","target":"graph","created_at":"2026-07-05T05:49:15Z","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/2210.17517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mathematical reasoning skills are essential for general-purpose intelligent systems to perform tasks from grocery shopping to climate modeling. Towards evaluating and improving AI systems in this domain, we propose LILA, a unified mathematical reasoning benchmark consisting of 23 diverse tasks along four dimensions: (i) mathematical abilities e.g., arithmetic, calculus (ii) language format e.g., question-answering, fill-in-the-blanks (iii) language diversity e.g., no language, simple language (iv) external knowledge e.g., commonsense, physics. We construct our benchmark by extending 20 dataset","authors_text":"Ashish Sabharwal, Ashwin Kalyan, Chitta Baral, Leonard Tang, Matthew Finlayson, Oyvind Tafjord, Pan Lu, Peter Clark, Sean Welleck, Swaroop Mishra, Tanmay Rajpurohit","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T17:41:26Z","title":"Lila: A Unified Benchmark for Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17517","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:d7861e7afa4184a7b7c41376b2b02c15408c1684e4831cea2c8c16b69e58f30b","target":"record","created_at":"2026-07-05T05:49:15Z","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":"b5cd7f6cc6ced0282e18c5d18afc272b22c550a2cdd6f2a79df953a364ff722e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T17:41:26Z","title_canon_sha256":"5d11cad1a341b35e0ca6cfd1be3cb01731f1e0b480107824ce52b0ed6a7bae71"},"schema_version":"1.0","source":{"id":"2210.17517","kind":"arxiv","version":2}},"canonical_sha256":"6b8c854136954f8b78ac9cfb36037cf50f19a605a3dc61df8ff6e7f33333cf3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b8c854136954f8b78ac9cfb36037cf50f19a605a3dc61df8ff6e7f33333cf3f","first_computed_at":"2026-07-05T05:49:15.355757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:15.355757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mehoRFuuB5jpF2zcAG0MPMrfM8m3cnD4lBAQ0N3drwIJErFLRF7t42yXm7QHs9cZR63jYP8kxcWaE8bbIkSMAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:15.356312Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.17517","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7861e7afa4184a7b7c41376b2b02c15408c1684e4831cea2c8c16b69e58f30b","sha256:e373b6efa2fa0a96b410c69bf7289f99c74b499c7517ed64313ba919ed093642"],"state_sha256":"4e7afaf60ef22915ffc1c8c8539d472a8534be8afafc7bb1a9a81f793388870f"}