{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AI3SN6C7E4OXPTDJAZPH6BJ3VB","short_pith_number":"pith:AI3SN6C7","schema_version":"1.0","canonical_sha256":"023726f85f271d77cc69065e7f053ba84f64fb8d58f49f765f3029800b5dbb01","source":{"kind":"arxiv","id":"1906.03672","version":1},"attestation_state":"computed","paper":{"title":"Question Answering as Global Reasoning over Semantic Abstractions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashish Sabharwal, Daniel Khashabi, Dan Roth, Tushar Khot","submitted_at":"2019-06-09T16:56:31Z","abstract_excerpt":"We propose a novel method for exploiting the semantic structure of text to answer multiple-choice questions. The approach is especially suitable for domains that require reasoning over a diverse set of linguistic constructs but have limited training data. To address these challenges, we present the first system, to the best of our knowledge, that reasons over a wide range of semantic abstractions of the text, which are derived using off-the-shelf, general-purpose, pre-trained natural language modules such as semantic role labelers, coreference resolvers, and dependency parsers. Representing mu"},"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":"1906.03672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-09T16:56:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b11b4997ef2d1d02f35a84cca79a97efabde3409a312db18e3e4e3666ff05760","abstract_canon_sha256":"f55ec52f61bc9f0bb7358e672fe93eae7529ba0fe3c7eae9269aa05dbd693706"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:45.427243Z","signature_b64":"W7tmfp/TMBey2sin3kIc3Efv7XWb04TRqklvtkFsxblNGRak/swtKrckcpLo9ycUCg2sG+1/E/YsnrQgVe5PBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"023726f85f271d77cc69065e7f053ba84f64fb8d58f49f765f3029800b5dbb01","last_reissued_at":"2026-05-17T23:43:45.426515Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:45.426515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Question Answering as Global Reasoning over Semantic Abstractions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashish Sabharwal, Daniel Khashabi, Dan Roth, Tushar Khot","submitted_at":"2019-06-09T16:56:31Z","abstract_excerpt":"We propose a novel method for exploiting the semantic structure of text to answer multiple-choice questions. The approach is especially suitable for domains that require reasoning over a diverse set of linguistic constructs but have limited training data. To address these challenges, we present the first system, to the best of our knowledge, that reasons over a wide range of semantic abstractions of the text, which are derived using off-the-shelf, general-purpose, pre-trained natural language modules such as semantic role labelers, coreference resolvers, and dependency parsers. Representing mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03672","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":""},"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":"1906.03672","created_at":"2026-05-17T23:43:45.426651+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.03672v1","created_at":"2026-05-17T23:43:45.426651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03672","created_at":"2026-05-17T23:43:45.426651+00:00"},{"alias_kind":"pith_short_12","alias_value":"AI3SN6C7E4OX","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"AI3SN6C7E4OXPTDJ","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"AI3SN6C7","created_at":"2026-05-18T12:33:12.712433+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/AI3SN6C7E4OXPTDJAZPH6BJ3VB","json":"https://pith.science/pith/AI3SN6C7E4OXPTDJAZPH6BJ3VB.json","graph_json":"https://pith.science/api/pith-number/AI3SN6C7E4OXPTDJAZPH6BJ3VB/graph.json","events_json":"https://pith.science/api/pith-number/AI3SN6C7E4OXPTDJAZPH6BJ3VB/events.json","paper":"https://pith.science/paper/AI3SN6C7"},"agent_actions":{"view_html":"https://pith.science/pith/AI3SN6C7E4OXPTDJAZPH6BJ3VB","download_json":"https://pith.science/pith/AI3SN6C7E4OXPTDJAZPH6BJ3VB.json","view_paper":"https://pith.science/paper/AI3SN6C7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.03672&json=true","fetch_graph":"https://pith.science/api/pith-number/AI3SN6C7E4OXPTDJAZPH6BJ3VB/graph.json","fetch_events":"https://pith.science/api/pith-number/AI3SN6C7E4OXPTDJAZPH6BJ3VB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AI3SN6C7E4OXPTDJAZPH6BJ3VB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AI3SN6C7E4OXPTDJAZPH6BJ3VB/action/storage_attestation","attest_author":"https://pith.science/pith/AI3SN6C7E4OXPTDJAZPH6BJ3VB/action/author_attestation","sign_citation":"https://pith.science/pith/AI3SN6C7E4OXPTDJAZPH6BJ3VB/action/citation_signature","submit_replication":"https://pith.science/pith/AI3SN6C7E4OXPTDJAZPH6BJ3VB/action/replication_record"}},"created_at":"2026-05-17T23:43:45.426651+00:00","updated_at":"2026-05-17T23:43:45.426651+00:00"}