{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6MOZPE4NVZ3M7IS2UYVEBIZXI4","short_pith_number":"pith:6MOZPE4N","schema_version":"1.0","canonical_sha256":"f31d97938dae76cfa25aa62a40a3374712b9557c6be20d3266e64911ff08487e","source":{"kind":"arxiv","id":"2410.10271","version":1},"attestation_state":"computed","paper":{"title":"Fake it till you predict it: data augmentation strategies to detect initiation and termination of oncology treatment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Bastien Rance, Elizabeth Fabre, Laure Fournier, St\\'ephane Oudard, Valentin Pohyer (HEGP AP-HP)","submitted_at":"2024-10-14T08:22:14Z","abstract_excerpt":"At the hospital, the dispersion of information regarding anti-cancer treatment makes it difficult to extract. We proposed a solution capable of identifying dates, drugs and their temporal relationship within free-text oncology reports with very few manual annotations. We used pattern recognition for dates, dictionaries for drugs and transformer language models for the relationship, combined with a data augmentation strategy. Our models achieved good prediction F1-scores, reaching 0.872. The performance of models with data augmentation outperforms those of models without. By inferring such mode"},"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":"2410.10271","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2024-10-14T08:22:14Z","cross_cats_sorted":[],"title_canon_sha256":"0d7990c0b6d9ef526510f7111905bdbf3f437db6bc1267abd67e0b42318429ae","abstract_canon_sha256":"0f93aaeb8321a1618b19381d70031dbb2b62652ecbdbf09c536c1d4b63dc1d3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:14.162292Z","signature_b64":"/JOakgBiq8c/nhC7t4sBM3DhU0DGaNq3ZB5fRbrTWS41qsgWHs1XNeKSTSzQsUhPvK/HgZdx+yKfm7h7hmz7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f31d97938dae76cfa25aa62a40a3374712b9557c6be20d3266e64911ff08487e","last_reissued_at":"2026-07-05T09:20:14.161798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:14.161798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fake it till you predict it: data augmentation strategies to detect initiation and termination of oncology treatment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Bastien Rance, Elizabeth Fabre, Laure Fournier, St\\'ephane Oudard, Valentin Pohyer (HEGP AP-HP)","submitted_at":"2024-10-14T08:22:14Z","abstract_excerpt":"At the hospital, the dispersion of information regarding anti-cancer treatment makes it difficult to extract. We proposed a solution capable of identifying dates, drugs and their temporal relationship within free-text oncology reports with very few manual annotations. We used pattern recognition for dates, dictionaries for drugs and transformer language models for the relationship, combined with a data augmentation strategy. Our models achieved good prediction F1-scores, reaching 0.872. The performance of models with data augmentation outperforms those of models without. By inferring such mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10271","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/2410.10271/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":"2410.10271","created_at":"2026-07-05T09:20:14.161859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10271v1","created_at":"2026-07-05T09:20:14.161859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10271","created_at":"2026-07-05T09:20:14.161859+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MOZPE4NVZ3M","created_at":"2026-07-05T09:20:14.161859+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MOZPE4NVZ3M7IS2","created_at":"2026-07-05T09:20:14.161859+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MOZPE4N","created_at":"2026-07-05T09:20:14.161859+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/6MOZPE4NVZ3M7IS2UYVEBIZXI4","json":"https://pith.science/pith/6MOZPE4NVZ3M7IS2UYVEBIZXI4.json","graph_json":"https://pith.science/api/pith-number/6MOZPE4NVZ3M7IS2UYVEBIZXI4/graph.json","events_json":"https://pith.science/api/pith-number/6MOZPE4NVZ3M7IS2UYVEBIZXI4/events.json","paper":"https://pith.science/paper/6MOZPE4N"},"agent_actions":{"view_html":"https://pith.science/pith/6MOZPE4NVZ3M7IS2UYVEBIZXI4","download_json":"https://pith.science/pith/6MOZPE4NVZ3M7IS2UYVEBIZXI4.json","view_paper":"https://pith.science/paper/6MOZPE4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10271&json=true","fetch_graph":"https://pith.science/api/pith-number/6MOZPE4NVZ3M7IS2UYVEBIZXI4/graph.json","fetch_events":"https://pith.science/api/pith-number/6MOZPE4NVZ3M7IS2UYVEBIZXI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MOZPE4NVZ3M7IS2UYVEBIZXI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MOZPE4NVZ3M7IS2UYVEBIZXI4/action/storage_attestation","attest_author":"https://pith.science/pith/6MOZPE4NVZ3M7IS2UYVEBIZXI4/action/author_attestation","sign_citation":"https://pith.science/pith/6MOZPE4NVZ3M7IS2UYVEBIZXI4/action/citation_signature","submit_replication":"https://pith.science/pith/6MOZPE4NVZ3M7IS2UYVEBIZXI4/action/replication_record"}},"created_at":"2026-07-05T09:20:14.161859+00:00","updated_at":"2026-07-05T09:20:14.161859+00:00"}