{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VLLCYD3DXHCAXYW4GECZIHQNE6","short_pith_number":"pith:VLLCYD3D","schema_version":"1.0","canonical_sha256":"aad62c0f63b9c40be2dc3105941e0d278369412fb08811fb97572a2463e190ec","source":{"kind":"arxiv","id":"2204.05660","version":1},"attestation_state":"computed","paper":{"title":"NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Arindam Mitra, Ashwin Kalyan, Bhavdeep Sachdeva, Chitta Baral, Neeraj Varshney, Peter Clark, Swaroop Mishra","submitted_at":"2022-04-12T09:36:10Z","abstract_excerpt":"Given the ubiquitous nature of numbers in text, reasoning with numbers to perform simple calculations is an important skill of AI systems. While many datasets and models have been developed to this end, state-of-the-art AI systems are brittle; failing to perform the underlying mathematical reasoning when they appear in a slightly different scenario. Drawing inspiration from GLUE that was proposed in the context of natural language understanding, we propose NumGLUE, a multi-task benchmark that evaluates the performance of AI systems on eight different tasks, that at their core require simple ar"},"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":"2204.05660","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-12T09:36:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5972570a1fdcf17f042a54ccd75604e89e7365c57a133861b615503a1a964d1f","abstract_canon_sha256":"fd06a1ac104d99bee0a9ab064d9532d92eaf92c6813fe235223186d1e7464085"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:00.777048Z","signature_b64":"7vHu3jn+zkW+UlMZTaRhlqdLuBGT0tQI0sX0kTAZ0JbxNlIMBu9iTSWINre1dK8WJO9tlB+xs80+ko9vCfz0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aad62c0f63b9c40be2dc3105941e0d278369412fb08811fb97572a2463e190ec","last_reissued_at":"2026-07-05T04:14:00.776497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:00.776497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Arindam Mitra, Ashwin Kalyan, Bhavdeep Sachdeva, Chitta Baral, Neeraj Varshney, Peter Clark, Swaroop Mishra","submitted_at":"2022-04-12T09:36:10Z","abstract_excerpt":"Given the ubiquitous nature of numbers in text, reasoning with numbers to perform simple calculations is an important skill of AI systems. While many datasets and models have been developed to this end, state-of-the-art AI systems are brittle; failing to perform the underlying mathematical reasoning when they appear in a slightly different scenario. Drawing inspiration from GLUE that was proposed in the context of natural language understanding, we propose NumGLUE, a multi-task benchmark that evaluates the performance of AI systems on eight different tasks, that at their core require simple ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05660","kind":"arxiv","version":1},"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/2204.05660/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":"2204.05660","created_at":"2026-07-05T04:14:00.776556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.05660v1","created_at":"2026-07-05T04:14:00.776556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05660","created_at":"2026-07-05T04:14:00.776556+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLLCYD3DXHCA","created_at":"2026-07-05T04:14:00.776556+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLLCYD3DXHCAXYW4","created_at":"2026-07-05T04:14:00.776556+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLLCYD3D","created_at":"2026-07-05T04:14:00.776556+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLLCYD3DXHCAXYW4GECZIHQNE6","json":"https://pith.science/pith/VLLCYD3DXHCAXYW4GECZIHQNE6.json","graph_json":"https://pith.science/api/pith-number/VLLCYD3DXHCAXYW4GECZIHQNE6/graph.json","events_json":"https://pith.science/api/pith-number/VLLCYD3DXHCAXYW4GECZIHQNE6/events.json","paper":"https://pith.science/paper/VLLCYD3D"},"agent_actions":{"view_html":"https://pith.science/pith/VLLCYD3DXHCAXYW4GECZIHQNE6","download_json":"https://pith.science/pith/VLLCYD3DXHCAXYW4GECZIHQNE6.json","view_paper":"https://pith.science/paper/VLLCYD3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.05660&json=true","fetch_graph":"https://pith.science/api/pith-number/VLLCYD3DXHCAXYW4GECZIHQNE6/graph.json","fetch_events":"https://pith.science/api/pith-number/VLLCYD3DXHCAXYW4GECZIHQNE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLLCYD3DXHCAXYW4GECZIHQNE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLLCYD3DXHCAXYW4GECZIHQNE6/action/storage_attestation","attest_author":"https://pith.science/pith/VLLCYD3DXHCAXYW4GECZIHQNE6/action/author_attestation","sign_citation":"https://pith.science/pith/VLLCYD3DXHCAXYW4GECZIHQNE6/action/citation_signature","submit_replication":"https://pith.science/pith/VLLCYD3DXHCAXYW4GECZIHQNE6/action/replication_record"}},"created_at":"2026-07-05T04:14:00.776556+00:00","updated_at":"2026-07-05T04:14:00.776556+00:00"}