{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UKTY3NQTT6T7BAZIPMCRJBEF7N","short_pith_number":"pith:UKTY3NQT","schema_version":"1.0","canonical_sha256":"a2a78db6139fa7f083287b05148485fb41dc7c486caf395a8a66168047975f0f","source":{"kind":"arxiv","id":"2011.07959","version":1},"attestation_state":"computed","paper":{"title":"Text Mining to Identify and Extract Novel Disease Treatments From Unstructured Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Alexander Tropsha, Cleber Melo-Filho, Eugene Muratov, Rada Chirkova, Rahul Yedida, Saad Mohammad Abrar","submitted_at":"2020-10-22T19:52:49Z","abstract_excerpt":"Objective: We aim to learn potential novel cures for diseases from unstructured text sources. More specifically, we seek to extract drug-disease pairs of potential cures to diseases by a simple reasoning over the structure of spoken text.\n  Materials and Methods: We use Google Cloud to transcribe podcast episodes of an NPR radio show. We then build a pipeline for systematically pre-processing the text to ensure quality input to the core classification model, which feeds to a series of post-processing steps for obtaining filtered results. Our classification model itself uses a language model pr"},"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":"2011.07959","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2020-10-22T19:52:49Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"35ad90340dd35707937d8c1e453b6279121126b2c97a52052404b5374f7c488a","abstract_canon_sha256":"39b1f0dd16d3046a21f67c310b1a736f935d54c02b816494125b77b332516571"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:55.943625Z","signature_b64":"6/JynV5B8ejqYXlFh4KXIjcDjjpwgbFNhTNW0gx2q5en/oUzAbPb49VMX0AQcj3Emltw9DEDEOqCWol1ILHLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2a78db6139fa7f083287b05148485fb41dc7c486caf395a8a66168047975f0f","last_reissued_at":"2026-07-05T01:51:55.943285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:55.943285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text Mining to Identify and Extract Novel Disease Treatments From Unstructured Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Alexander Tropsha, Cleber Melo-Filho, Eugene Muratov, Rada Chirkova, Rahul Yedida, Saad Mohammad Abrar","submitted_at":"2020-10-22T19:52:49Z","abstract_excerpt":"Objective: We aim to learn potential novel cures for diseases from unstructured text sources. More specifically, we seek to extract drug-disease pairs of potential cures to diseases by a simple reasoning over the structure of spoken text.\n  Materials and Methods: We use Google Cloud to transcribe podcast episodes of an NPR radio show. We then build a pipeline for systematically pre-processing the text to ensure quality input to the core classification model, which feeds to a series of post-processing steps for obtaining filtered results. Our classification model itself uses a language model pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.07959","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/2011.07959/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":"2011.07959","created_at":"2026-07-05T01:51:55.943347+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.07959v1","created_at":"2026-07-05T01:51:55.943347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.07959","created_at":"2026-07-05T01:51:55.943347+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKTY3NQTT6T7","created_at":"2026-07-05T01:51:55.943347+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKTY3NQTT6T7BAZI","created_at":"2026-07-05T01:51:55.943347+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKTY3NQT","created_at":"2026-07-05T01:51:55.943347+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/UKTY3NQTT6T7BAZIPMCRJBEF7N","json":"https://pith.science/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N.json","graph_json":"https://pith.science/api/pith-number/UKTY3NQTT6T7BAZIPMCRJBEF7N/graph.json","events_json":"https://pith.science/api/pith-number/UKTY3NQTT6T7BAZIPMCRJBEF7N/events.json","paper":"https://pith.science/paper/UKTY3NQT"},"agent_actions":{"view_html":"https://pith.science/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N","download_json":"https://pith.science/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N.json","view_paper":"https://pith.science/paper/UKTY3NQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.07959&json=true","fetch_graph":"https://pith.science/api/pith-number/UKTY3NQTT6T7BAZIPMCRJBEF7N/graph.json","fetch_events":"https://pith.science/api/pith-number/UKTY3NQTT6T7BAZIPMCRJBEF7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N/action/storage_attestation","attest_author":"https://pith.science/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N/action/author_attestation","sign_citation":"https://pith.science/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N/action/citation_signature","submit_replication":"https://pith.science/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N/action/replication_record"}},"created_at":"2026-07-05T01:51:55.943347+00:00","updated_at":"2026-07-05T01:51:55.943347+00:00"}