{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NOGIKQJWSVHYW6FMTT5TMA346U","short_pith_number":"pith:NOGIKQJW","schema_version":"1.0","canonical_sha256":"6b8c854136954f8b78ac9cfb36037cf50f19a605a3dc61df8ff6e7f33333cf3f","source":{"kind":"arxiv","id":"2210.17517","version":2},"attestation_state":"computed","paper":{"title":"Lila: A Unified Benchmark for Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashish Sabharwal, Ashwin Kalyan, Chitta Baral, Leonard Tang, Matthew Finlayson, Oyvind Tafjord, Pan Lu, Peter Clark, Sean Welleck, Swaroop Mishra, Tanmay Rajpurohit","submitted_at":"2022-10-31T17:41:26Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.17517","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T17:41:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5d11cad1a341b35e0ca6cfd1be3cb01731f1e0b480107824ce52b0ed6a7bae71","abstract_canon_sha256":"b5cd7f6cc6ced0282e18c5d18afc272b22c550a2cdd6f2a79df953a364ff722e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:15.356312Z","signature_b64":"mehoRFuuB5jpF2zcAG0MPMrfM8m3cnD4lBAQ0N3drwIJErFLRF7t42yXm7QHs9cZR63jYP8kxcWaE8bbIkSMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b8c854136954f8b78ac9cfb36037cf50f19a605a3dc61df8ff6e7f33333cf3f","last_reissued_at":"2026-07-05T05:49:15.355757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:15.355757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lila: A Unified Benchmark for Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashish Sabharwal, Ashwin Kalyan, Chitta Baral, Leonard Tang, Matthew Finlayson, Oyvind Tafjord, Pan Lu, Peter Clark, Sean Welleck, Swaroop Mishra, Tanmay Rajpurohit","submitted_at":"2022-10-31T17:41:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17517","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.17517/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.17517","created_at":"2026-07-05T05:49:15.355837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.17517v2","created_at":"2026-07-05T05:49:15.355837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17517","created_at":"2026-07-05T05:49:15.355837+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOGIKQJWSVHY","created_at":"2026-07-05T05:49:15.355837+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOGIKQJWSVHYW6FM","created_at":"2026-07-05T05:49:15.355837+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOGIKQJW","created_at":"2026-07-05T05:49:15.355837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.16944","citing_title":"Zephyr: Direct Distillation of LM Alignment","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NOGIKQJWSVHYW6FMTT5TMA346U","json":"https://pith.science/pith/NOGIKQJWSVHYW6FMTT5TMA346U.json","graph_json":"https://pith.science/api/pith-number/NOGIKQJWSVHYW6FMTT5TMA346U/graph.json","events_json":"https://pith.science/api/pith-number/NOGIKQJWSVHYW6FMTT5TMA346U/events.json","paper":"https://pith.science/paper/NOGIKQJW"},"agent_actions":{"view_html":"https://pith.science/pith/NOGIKQJWSVHYW6FMTT5TMA346U","download_json":"https://pith.science/pith/NOGIKQJWSVHYW6FMTT5TMA346U.json","view_paper":"https://pith.science/paper/NOGIKQJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.17517&json=true","fetch_graph":"https://pith.science/api/pith-number/NOGIKQJWSVHYW6FMTT5TMA346U/graph.json","fetch_events":"https://pith.science/api/pith-number/NOGIKQJWSVHYW6FMTT5TMA346U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOGIKQJWSVHYW6FMTT5TMA346U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOGIKQJWSVHYW6FMTT5TMA346U/action/storage_attestation","attest_author":"https://pith.science/pith/NOGIKQJWSVHYW6FMTT5TMA346U/action/author_attestation","sign_citation":"https://pith.science/pith/NOGIKQJWSVHYW6FMTT5TMA346U/action/citation_signature","submit_replication":"https://pith.science/pith/NOGIKQJWSVHYW6FMTT5TMA346U/action/replication_record"}},"created_at":"2026-07-05T05:49:15.355837+00:00","updated_at":"2026-07-05T05:49:15.355837+00:00"}