{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UKTY3NQTT6T7BAZIPMCRJBEF7N","short_pith_number":"pith:UKTY3NQT","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"},"canonical_sha256":"a2a78db6139fa7f083287b05148485fb41dc7c486caf395a8a66168047975f0f","source":{"kind":"arxiv","id":"2011.07959","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.07959","created_at":"2026-07-05T01:51:55Z"},{"alias_kind":"arxiv_version","alias_value":"2011.07959v1","created_at":"2026-07-05T01:51:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.07959","created_at":"2026-07-05T01:51:55Z"},{"alias_kind":"pith_short_12","alias_value":"UKTY3NQTT6T7","created_at":"2026-07-05T01:51:55Z"},{"alias_kind":"pith_short_16","alias_value":"UKTY3NQTT6T7BAZI","created_at":"2026-07-05T01:51:55Z"},{"alias_kind":"pith_short_8","alias_value":"UKTY3NQT","created_at":"2026-07-05T01:51:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UKTY3NQTT6T7BAZIPMCRJBEF7N","target":"record","payload":{"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"},"canonical_sha256":"a2a78db6139fa7f083287b05148485fb41dc7c486caf395a8a66168047975f0f","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"},"source_kind":"arxiv","source_id":"2011.07959","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:51:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cMewWG9FYrWTpggbJvHMgxOGHfuhd0wNd5eo0ewnZoLdniGhAD9unYAv18LOClVS8DQEeuuc3wEJZYwcFKy2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:24:30.696808Z"},"content_sha256":"d388422eab5b2c134a9d21dfd00c5f77dff40c74cd38780535d3b2eda9db4cb4","schema_version":"1.0","event_id":"sha256:d388422eab5b2c134a9d21dfd00c5f77dff40c74cd38780535d3b2eda9db4cb4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UKTY3NQTT6T7BAZIPMCRJBEF7N","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:51:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lkMCVyb/KUVk+SkX+pEJ/8yrj5CIfKgyESnzr8h0UIqbrr4jcH8B1urjYK+gv1jJyEoclg3hbkgx1/mOTt9QCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:24:30.697361Z"},"content_sha256":"e7c3fa7f3c4eea693109f55f66390a2f1dd8e8ee3e8b52ade318b85232a82c39","schema_version":"1.0","event_id":"sha256:e7c3fa7f3c4eea693109f55f66390a2f1dd8e8ee3e8b52ade318b85232a82c39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N/bundle.json","state_url":"https://pith.science/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T23:24:30Z","links":{"resolver":"https://pith.science/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N","bundle":"https://pith.science/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N/bundle.json","state":"https://pith.science/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UKTY3NQTT6T7BAZIPMCRJBEF7N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UKTY3NQTT6T7BAZIPMCRJBEF7N","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"39b1f0dd16d3046a21f67c310b1a736f935d54c02b816494125b77b332516571","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2020-10-22T19:52:49Z","title_canon_sha256":"35ad90340dd35707937d8c1e453b6279121126b2c97a52052404b5374f7c488a"},"schema_version":"1.0","source":{"id":"2011.07959","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.07959","created_at":"2026-07-05T01:51:55Z"},{"alias_kind":"arxiv_version","alias_value":"2011.07959v1","created_at":"2026-07-05T01:51:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.07959","created_at":"2026-07-05T01:51:55Z"},{"alias_kind":"pith_short_12","alias_value":"UKTY3NQTT6T7","created_at":"2026-07-05T01:51:55Z"},{"alias_kind":"pith_short_16","alias_value":"UKTY3NQTT6T7BAZI","created_at":"2026-07-05T01:51:55Z"},{"alias_kind":"pith_short_8","alias_value":"UKTY3NQT","created_at":"2026-07-05T01:51:55Z"}],"graph_snapshots":[{"event_id":"sha256:e7c3fa7f3c4eea693109f55f66390a2f1dd8e8ee3e8b52ade318b85232a82c39","target":"graph","created_at":"2026-07-05T01:51:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.07959/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexander Tropsha, Cleber Melo-Filho, Eugene Muratov, Rada Chirkova, Rahul Yedida, Saad Mohammad Abrar","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2020-10-22T19:52:49Z","title":"Text Mining to Identify and Extract Novel Disease Treatments From Unstructured Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.07959","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d388422eab5b2c134a9d21dfd00c5f77dff40c74cd38780535d3b2eda9db4cb4","target":"record","created_at":"2026-07-05T01:51:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"39b1f0dd16d3046a21f67c310b1a736f935d54c02b816494125b77b332516571","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2020-10-22T19:52:49Z","title_canon_sha256":"35ad90340dd35707937d8c1e453b6279121126b2c97a52052404b5374f7c488a"},"schema_version":"1.0","source":{"id":"2011.07959","kind":"arxiv","version":1}},"canonical_sha256":"a2a78db6139fa7f083287b05148485fb41dc7c486caf395a8a66168047975f0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2a78db6139fa7f083287b05148485fb41dc7c486caf395a8a66168047975f0f","first_computed_at":"2026-07-05T01:51:55.943285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:51:55.943285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6/JynV5B8ejqYXlFh4KXIjcDjjpwgbFNhTNW0gx2q5en/oUzAbPb49VMX0AQcj3Emltw9DEDEOqCWol1ILHLBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:51:55.943625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.07959","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d388422eab5b2c134a9d21dfd00c5f77dff40c74cd38780535d3b2eda9db4cb4","sha256:e7c3fa7f3c4eea693109f55f66390a2f1dd8e8ee3e8b52ade318b85232a82c39"],"state_sha256":"3b7318fcb375b51b3927a757c71da4571a5393484dfe89013f7e15bb957c7ca2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GxyO/2BLcWkr/NYvD5pa090rtPYIvikDIk/m/TT2q9QUjEiJml0DDWwltRIyAlSG7Q56mKLilv6WLNFrl31bBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T23:24:30.700978Z","bundle_sha256":"ec9f7fe7f818bbe57b6515b5579cbd8d78b01df02e177a0ea395c048209913ba"}}