{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:X6YTMHAZHHXAYJLSWVD7YPGD4Z","short_pith_number":"pith:X6YTMHAZ","canonical_record":{"source":{"id":"2503.08323","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T11:34:57Z","cross_cats_sorted":[],"title_canon_sha256":"2b46b07d4dc50b9e3b186e3768025a9e9a409bbb26e76aa27d64ac8c8e444631","abstract_canon_sha256":"f2de33a5ec80436425ad0e5d341f20d684bbf4b5fbbbc8e8f9fdeb306bc3fd00"},"schema_version":"1.0"},"canonical_sha256":"bfb1361c1939ee0c2572b547fc3cc3e6642124db22b2b3beff531f4c4a35d1cf","source":{"kind":"arxiv","id":"2503.08323","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08323","created_at":"2026-07-05T10:28:56Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08323v1","created_at":"2026-07-05T10:28:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08323","created_at":"2026-07-05T10:28:56Z"},{"alias_kind":"pith_short_12","alias_value":"X6YTMHAZHHXA","created_at":"2026-07-05T10:28:56Z"},{"alias_kind":"pith_short_16","alias_value":"X6YTMHAZHHXAYJLS","created_at":"2026-07-05T10:28:56Z"},{"alias_kind":"pith_short_8","alias_value":"X6YTMHAZ","created_at":"2026-07-05T10:28:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:X6YTMHAZHHXAYJLSWVD7YPGD4Z","target":"record","payload":{"canonical_record":{"source":{"id":"2503.08323","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T11:34:57Z","cross_cats_sorted":[],"title_canon_sha256":"2b46b07d4dc50b9e3b186e3768025a9e9a409bbb26e76aa27d64ac8c8e444631","abstract_canon_sha256":"f2de33a5ec80436425ad0e5d341f20d684bbf4b5fbbbc8e8f9fdeb306bc3fd00"},"schema_version":"1.0"},"canonical_sha256":"bfb1361c1939ee0c2572b547fc3cc3e6642124db22b2b3beff531f4c4a35d1cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:56.686883Z","signature_b64":"F6x8tRNIscCDhFqeL3+WbjJchJ6n9eLaZUzsqyASyaV4vZOhwVnmNaPdPrt1nnw/UjX4o+5MTFAMuEd4k+k0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfb1361c1939ee0c2572b547fc3cc3e6642124db22b2b3beff531f4c4a35d1cf","last_reissued_at":"2026-07-05T10:28:56.686148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:56.686148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.08323","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":"2026-07-05T10:28:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7i3g3Ci0ou9Y06FCWmBE/arAQzLtpqC0dQmZZ74rjaBWa6HLYfV3qODc+Ff81r0/ged42rxw96BWQ9efHlGBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:20:09.120920Z"},"content_sha256":"231094fa8013e58bb2053699627488954a73a38b842cfca35abba0bddcd2636a","schema_version":"1.0","event_id":"sha256:231094fa8013e58bb2053699627488954a73a38b842cfca35abba0bddcd2636a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:X6YTMHAZHHXAYJLSWVD7YPGD4Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Scalable and Cross-Lingual Specialist Language Models for Oncology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andreas Wicki, Farhad Nooralahzadeh, Michael Krauthammer, Morteza Rohanian, Nicola Miglino, Tarun Mehra","submitted_at":"2025-03-11T11:34:57Z","abstract_excerpt":"Clinical oncology generates vast, unstructured data that often contain inconsistencies, missing information, and ambiguities, making it difficult to extract reliable insights for data-driven decision-making. General-purpose large language models (LLMs) struggle with these challenges due to their lack of domain-specific reasoning, including specialized clinical terminology, context-dependent interpretations, and multi-modal data integration. We address these issues with an oncology-specialized, efficient, and adaptable NLP framework that combines instruction tuning, retrieval-augmented generati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08323","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/2503.08323/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":"2026-07-05T10:28:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Qwbw1sPJ0TB6HSz1DAwWSZA0PszeDEiNPmgiPb7Csc4lxxYmYJEQaieTojgcUfPVuQOjzFkxFwB9QwqbQHdCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:20:09.121877Z"},"content_sha256":"d71bd491eff2d45fee7d8d6bca28e9b94ca4e0c48477a912a715e06390d0d1bf","schema_version":"1.0","event_id":"sha256:d71bd491eff2d45fee7d8d6bca28e9b94ca4e0c48477a912a715e06390d0d1bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X6YTMHAZHHXAYJLSWVD7YPGD4Z/bundle.json","state_url":"https://pith.science/pith/X6YTMHAZHHXAYJLSWVD7YPGD4Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X6YTMHAZHHXAYJLSWVD7YPGD4Z/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":"2026-08-14T19:20:09Z","links":{"resolver":"https://pith.science/pith/X6YTMHAZHHXAYJLSWVD7YPGD4Z","bundle":"https://pith.science/pith/X6YTMHAZHHXAYJLSWVD7YPGD4Z/bundle.json","state":"https://pith.science/pith/X6YTMHAZHHXAYJLSWVD7YPGD4Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X6YTMHAZHHXAYJLSWVD7YPGD4Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X6YTMHAZHHXAYJLSWVD7YPGD4Z","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":"f2de33a5ec80436425ad0e5d341f20d684bbf4b5fbbbc8e8f9fdeb306bc3fd00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T11:34:57Z","title_canon_sha256":"2b46b07d4dc50b9e3b186e3768025a9e9a409bbb26e76aa27d64ac8c8e444631"},"schema_version":"1.0","source":{"id":"2503.08323","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08323","created_at":"2026-07-05T10:28:56Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08323v1","created_at":"2026-07-05T10:28:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08323","created_at":"2026-07-05T10:28:56Z"},{"alias_kind":"pith_short_12","alias_value":"X6YTMHAZHHXA","created_at":"2026-07-05T10:28:56Z"},{"alias_kind":"pith_short_16","alias_value":"X6YTMHAZHHXAYJLS","created_at":"2026-07-05T10:28:56Z"},{"alias_kind":"pith_short_8","alias_value":"X6YTMHAZ","created_at":"2026-07-05T10:28:56Z"}],"graph_snapshots":[{"event_id":"sha256:d71bd491eff2d45fee7d8d6bca28e9b94ca4e0c48477a912a715e06390d0d1bf","target":"graph","created_at":"2026-07-05T10:28:56Z","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/2503.08323/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Clinical oncology generates vast, unstructured data that often contain inconsistencies, missing information, and ambiguities, making it difficult to extract reliable insights for data-driven decision-making. General-purpose large language models (LLMs) struggle with these challenges due to their lack of domain-specific reasoning, including specialized clinical terminology, context-dependent interpretations, and multi-modal data integration. We address these issues with an oncology-specialized, efficient, and adaptable NLP framework that combines instruction tuning, retrieval-augmented generati","authors_text":"Andreas Wicki, Farhad Nooralahzadeh, Michael Krauthammer, Morteza Rohanian, Nicola Miglino, Tarun Mehra","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T11:34:57Z","title":"Towards Scalable and Cross-Lingual Specialist Language Models for Oncology"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08323","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":"sha256:231094fa8013e58bb2053699627488954a73a38b842cfca35abba0bddcd2636a","target":"record","created_at":"2026-07-05T10:28:56Z","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":"f2de33a5ec80436425ad0e5d341f20d684bbf4b5fbbbc8e8f9fdeb306bc3fd00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T11:34:57Z","title_canon_sha256":"2b46b07d4dc50b9e3b186e3768025a9e9a409bbb26e76aa27d64ac8c8e444631"},"schema_version":"1.0","source":{"id":"2503.08323","kind":"arxiv","version":1}},"canonical_sha256":"bfb1361c1939ee0c2572b547fc3cc3e6642124db22b2b3beff531f4c4a35d1cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfb1361c1939ee0c2572b547fc3cc3e6642124db22b2b3beff531f4c4a35d1cf","first_computed_at":"2026-07-05T10:28:56.686148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:56.686148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F6x8tRNIscCDhFqeL3+WbjJchJ6n9eLaZUzsqyASyaV4vZOhwVnmNaPdPrt1nnw/UjX4o+5MTFAMuEd4k+k0Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:56.686883Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08323","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:231094fa8013e58bb2053699627488954a73a38b842cfca35abba0bddcd2636a","sha256:d71bd491eff2d45fee7d8d6bca28e9b94ca4e0c48477a912a715e06390d0d1bf"],"state_sha256":"470fc699b82c7577dcedc88972bf4dd77a8dee0b05d9166d5236c100f5b93526"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mlnGWAHHE4R29l57/Vj6GqahAwA44fssrEIO74nzAlKNcq0Xm3lT0Qizkz3HwB0ovWTxIdGtWEjyHao16G6yCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:20:09.128369Z","bundle_sha256":"3b2dcfde32c67cff79ff4257a979efe43d2932519edc68d45b46fa417e66fa67"}}