{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CYVBAMHHOE47KFYWCFDC4HQZDS","short_pith_number":"pith:CYVBAMHH","schema_version":"1.0","canonical_sha256":"162a1030e77139f5171611462e1e191ca41090049eafc6aaa0a4023bf0fc7e64","source":{"kind":"arxiv","id":"2005.08516","version":1},"attestation_state":"computed","paper":{"title":"Towards Question Format Independent Numerical Reasoning: A Set of Prerequisite 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, Bhavdeep Sachdeva, Chitta Baral, Neeraj Varshney, Swaroop Mishra","submitted_at":"2020-05-18T08:14:04Z","abstract_excerpt":"Numerical reasoning is often important to accurately understand the world. Recently, several format-specific datasets have been proposed, such as numerical reasoning in the settings of Natural Language Inference (NLI), Reading Comprehension (RC), and Question Answering (QA). Several format-specific models and architectures in response to those datasets have also been proposed. However, there exists a strong need for a benchmark which can evaluate the abilities of models, in performing question format independent numerical reasoning, as (i) the numerical reasoning capabilities we want to teach "},"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":"2005.08516","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-18T08:14:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5a249cf91d79481948341f4b13c159a7b3add28b97e4261fb528ef0f5ca2a6e1","abstract_canon_sha256":"5354f8a16cdac05b4300e9cfba3d70207b01a6818567eb44c87236d48d166130"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:32.493497Z","signature_b64":"IWwYe6VXhTP9sBqVfCps/g5H1q8sYHDfSBU51exb1Bz9oo2A3RlU8FRHMPUHHRSz+WvmlmVIdQMgrE7SU5hOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"162a1030e77139f5171611462e1e191ca41090049eafc6aaa0a4023bf0fc7e64","last_reissued_at":"2026-07-05T01:03:32.493100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:32.493100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Question Format Independent Numerical Reasoning: A Set of Prerequisite 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, Bhavdeep Sachdeva, Chitta Baral, Neeraj Varshney, Swaroop Mishra","submitted_at":"2020-05-18T08:14:04Z","abstract_excerpt":"Numerical reasoning is often important to accurately understand the world. Recently, several format-specific datasets have been proposed, such as numerical reasoning in the settings of Natural Language Inference (NLI), Reading Comprehension (RC), and Question Answering (QA). Several format-specific models and architectures in response to those datasets have also been proposed. However, there exists a strong need for a benchmark which can evaluate the abilities of models, in performing question format independent numerical reasoning, as (i) the numerical reasoning capabilities we want to teach "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08516","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/2005.08516/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":"2005.08516","created_at":"2026-07-05T01:03:32.493156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.08516v1","created_at":"2026-07-05T01:03:32.493156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08516","created_at":"2026-07-05T01:03:32.493156+00:00"},{"alias_kind":"pith_short_12","alias_value":"CYVBAMHHOE47","created_at":"2026-07-05T01:03:32.493156+00:00"},{"alias_kind":"pith_short_16","alias_value":"CYVBAMHHOE47KFYW","created_at":"2026-07-05T01:03:32.493156+00:00"},{"alias_kind":"pith_short_8","alias_value":"CYVBAMHH","created_at":"2026-07-05T01:03:32.493156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2104.08773","citing_title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CYVBAMHHOE47KFYWCFDC4HQZDS","json":"https://pith.science/pith/CYVBAMHHOE47KFYWCFDC4HQZDS.json","graph_json":"https://pith.science/api/pith-number/CYVBAMHHOE47KFYWCFDC4HQZDS/graph.json","events_json":"https://pith.science/api/pith-number/CYVBAMHHOE47KFYWCFDC4HQZDS/events.json","paper":"https://pith.science/paper/CYVBAMHH"},"agent_actions":{"view_html":"https://pith.science/pith/CYVBAMHHOE47KFYWCFDC4HQZDS","download_json":"https://pith.science/pith/CYVBAMHHOE47KFYWCFDC4HQZDS.json","view_paper":"https://pith.science/paper/CYVBAMHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.08516&json=true","fetch_graph":"https://pith.science/api/pith-number/CYVBAMHHOE47KFYWCFDC4HQZDS/graph.json","fetch_events":"https://pith.science/api/pith-number/CYVBAMHHOE47KFYWCFDC4HQZDS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CYVBAMHHOE47KFYWCFDC4HQZDS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CYVBAMHHOE47KFYWCFDC4HQZDS/action/storage_attestation","attest_author":"https://pith.science/pith/CYVBAMHHOE47KFYWCFDC4HQZDS/action/author_attestation","sign_citation":"https://pith.science/pith/CYVBAMHHOE47KFYWCFDC4HQZDS/action/citation_signature","submit_replication":"https://pith.science/pith/CYVBAMHHOE47KFYWCFDC4HQZDS/action/replication_record"}},"created_at":"2026-07-05T01:03:32.493156+00:00","updated_at":"2026-07-05T01:03:32.493156+00:00"}