{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2K3TRM62POZTRL3EJOBSIMEIVX","short_pith_number":"pith:2K3TRM62","canonical_record":{"source":{"id":"2012.04545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T16:37:34Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"7eb2479afbc5e23415176d7a9f74ef68420cce9efc6f3980551082d5c9197dae","abstract_canon_sha256":"b1fddbfa0b5d6e84096bc468614b697577bd173396de19eba6a8de327a7f6536"},"schema_version":"1.0"},"canonical_sha256":"d2b738b3da7bb338af644b83243088adf73dc05afc98ebc63e9598b444c4bfeb","source":{"kind":"arxiv","id":"2012.04545","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04545","created_at":"2026-07-05T03:26:14Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04545v1","created_at":"2026-07-05T03:26:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04545","created_at":"2026-07-05T03:26:14Z"},{"alias_kind":"pith_short_12","alias_value":"2K3TRM62POZT","created_at":"2026-07-05T03:26:14Z"},{"alias_kind":"pith_short_16","alias_value":"2K3TRM62POZTRL3E","created_at":"2026-07-05T03:26:14Z"},{"alias_kind":"pith_short_8","alias_value":"2K3TRM62","created_at":"2026-07-05T03:26:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2K3TRM62POZTRL3EJOBSIMEIVX","target":"record","payload":{"canonical_record":{"source":{"id":"2012.04545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T16:37:34Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"7eb2479afbc5e23415176d7a9f74ef68420cce9efc6f3980551082d5c9197dae","abstract_canon_sha256":"b1fddbfa0b5d6e84096bc468614b697577bd173396de19eba6a8de327a7f6536"},"schema_version":"1.0"},"canonical_sha256":"d2b738b3da7bb338af644b83243088adf73dc05afc98ebc63e9598b444c4bfeb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:14.473190Z","signature_b64":"Qp0XFoZ03OFRB9mjbPvsWBk7yK7wpYTGu/pavk9B7CTLRlzbMGfrC7Te8IgyJVG6CaNergCzuJ4EaqV1U7+rDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2b738b3da7bb338af644b83243088adf73dc05afc98ebc63e9598b444c4bfeb","last_reissued_at":"2026-07-05T03:26:14.472709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:14.472709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.04545","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":"2026-07-05T03:26:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t+Pq01IC0k0l+VhI2pMOPv+ako1kzEg0HrIOPnUu6zp0zxPlIacZyu85wtElcjUcFNkCWldTrULcEvbla1ewCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:05:04.124093Z"},"content_sha256":"9c623b2582bc1930ec716e7a0f09d1eebd7d3fd31fa2fc9dc2d19963abdb396b","schema_version":"1.0","event_id":"sha256:9c623b2582bc1930ec716e7a0f09d1eebd7d3fd31fa2fc9dc2d19963abdb396b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2K3TRM62POZTRL3EJOBSIMEIVX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discovering key topics from short, real-world medical inquiries via natural language processing and unsupervised learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Andreas Mattern, Angelo Ziletti, Christoph Berns, David Ruau, Jagatheswari Virayah, Jennifer Liang, Marion Schwaerzler, Oliver Treichel, Stephanie Kammerath, Thomas Weber, Xin Ma","submitted_at":"2020-12-08T16:37:34Z","abstract_excerpt":"Millions of unsolicited medical inquiries are received by pharmaceutical companies every year. It has been hypothesized that these inquiries represent a treasure trove of information, potentially giving insight into matters regarding medicinal products and the associated medical treatments. However, due to the large volume and specialized nature of the inquiries, it is difficult to perform timely, recurrent, and comprehensive analyses. Here, we propose a machine learning approach based on natural language processing and unsupervised learning to automatically discover key topics in real-world m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04545","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/2012.04545/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":"2026-07-05T03:26:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CJ0KaA5vj/1ZNGksb8X9wrxCFMtQFknP3bPEDZOROgsqiJcsIku0xNdNxrXWdJd3QYi9NBbNt3ROw1rubO0jAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:05:04.124487Z"},"content_sha256":"562560c85a7abbb5a064087b750dd68bb5c320b19e77b91ee1940f61f34ea7b1","schema_version":"1.0","event_id":"sha256:562560c85a7abbb5a064087b750dd68bb5c320b19e77b91ee1940f61f34ea7b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2K3TRM62POZTRL3EJOBSIMEIVX/bundle.json","state_url":"https://pith.science/pith/2K3TRM62POZTRL3EJOBSIMEIVX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2K3TRM62POZTRL3EJOBSIMEIVX/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":"2026-07-05T09:05:04Z","links":{"resolver":"https://pith.science/pith/2K3TRM62POZTRL3EJOBSIMEIVX","bundle":"https://pith.science/pith/2K3TRM62POZTRL3EJOBSIMEIVX/bundle.json","state":"https://pith.science/pith/2K3TRM62POZTRL3EJOBSIMEIVX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2K3TRM62POZTRL3EJOBSIMEIVX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2K3TRM62POZTRL3EJOBSIMEIVX","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":"b1fddbfa0b5d6e84096bc468614b697577bd173396de19eba6a8de327a7f6536","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T16:37:34Z","title_canon_sha256":"7eb2479afbc5e23415176d7a9f74ef68420cce9efc6f3980551082d5c9197dae"},"schema_version":"1.0","source":{"id":"2012.04545","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04545","created_at":"2026-07-05T03:26:14Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04545v1","created_at":"2026-07-05T03:26:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04545","created_at":"2026-07-05T03:26:14Z"},{"alias_kind":"pith_short_12","alias_value":"2K3TRM62POZT","created_at":"2026-07-05T03:26:14Z"},{"alias_kind":"pith_short_16","alias_value":"2K3TRM62POZTRL3E","created_at":"2026-07-05T03:26:14Z"},{"alias_kind":"pith_short_8","alias_value":"2K3TRM62","created_at":"2026-07-05T03:26:14Z"}],"graph_snapshots":[{"event_id":"sha256:562560c85a7abbb5a064087b750dd68bb5c320b19e77b91ee1940f61f34ea7b1","target":"graph","created_at":"2026-07-05T03:26:14Z","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/2012.04545/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Millions of unsolicited medical inquiries are received by pharmaceutical companies every year. It has been hypothesized that these inquiries represent a treasure trove of information, potentially giving insight into matters regarding medicinal products and the associated medical treatments. However, due to the large volume and specialized nature of the inquiries, it is difficult to perform timely, recurrent, and comprehensive analyses. Here, we propose a machine learning approach based on natural language processing and unsupervised learning to automatically discover key topics in real-world m","authors_text":"Andreas Mattern, Angelo Ziletti, Christoph Berns, David Ruau, Jagatheswari Virayah, Jennifer Liang, Marion Schwaerzler, Oliver Treichel, Stephanie Kammerath, Thomas Weber, Xin Ma","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T16:37:34Z","title":"Discovering key topics from short, real-world medical inquiries via natural language processing and unsupervised learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04545","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":"sha256:9c623b2582bc1930ec716e7a0f09d1eebd7d3fd31fa2fc9dc2d19963abdb396b","target":"record","created_at":"2026-07-05T03:26:14Z","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":"b1fddbfa0b5d6e84096bc468614b697577bd173396de19eba6a8de327a7f6536","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-08T16:37:34Z","title_canon_sha256":"7eb2479afbc5e23415176d7a9f74ef68420cce9efc6f3980551082d5c9197dae"},"schema_version":"1.0","source":{"id":"2012.04545","kind":"arxiv","version":1}},"canonical_sha256":"d2b738b3da7bb338af644b83243088adf73dc05afc98ebc63e9598b444c4bfeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2b738b3da7bb338af644b83243088adf73dc05afc98ebc63e9598b444c4bfeb","first_computed_at":"2026-07-05T03:26:14.472709Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:14.472709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qp0XFoZ03OFRB9mjbPvsWBk7yK7wpYTGu/pavk9B7CTLRlzbMGfrC7Te8IgyJVG6CaNergCzuJ4EaqV1U7+rDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:14.473190Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.04545","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c623b2582bc1930ec716e7a0f09d1eebd7d3fd31fa2fc9dc2d19963abdb396b","sha256:562560c85a7abbb5a064087b750dd68bb5c320b19e77b91ee1940f61f34ea7b1"],"state_sha256":"d0d7df757b6d2a1c9a8b6e5e39d632117bc0a9332a691a7a5c96de6c14884d07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4chy3LQaDDxlfESY9HNdJuWAcM6uLHRuEZIo9qTaS8nQ9hAZ51+CFWfr206WyZT+sPVJVc6A46idsmYE/AWzAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T09:05:04.126434Z","bundle_sha256":"4902e155f5326200c15daaae6793f7748c940b6330dffd115e9156260c33aee1"}}