{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4AR5QD6GID6C5FZLUFESEE4V4N","short_pith_number":"pith:4AR5QD6G","canonical_record":{"source":{"id":"2601.09722","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-27T10:00:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e60801ae820c76153a3685d9100be8c96fab82231d8ccba6cea4cb8be84a0f0","abstract_canon_sha256":"8ef76df58019a5f62bdaa031758eadeffc71897ccc3ed78670056cb144341e97"},"schema_version":"1.0"},"canonical_sha256":"e023d80fc640fc2e972ba149221395e36ca1ae97908c6aab0b6f43b2d05d36c8","source":{"kind":"arxiv","id":"2601.09722","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.09722","created_at":"2026-05-20T00:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2601.09722v2","created_at":"2026-05-20T00:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.09722","created_at":"2026-05-20T00:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"4AR5QD6GID6C","created_at":"2026-05-20T00:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"4AR5QD6GID6C5FZL","created_at":"2026-05-20T00:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"4AR5QD6G","created_at":"2026-05-20T00:04:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4AR5QD6GID6C5FZLUFESEE4V4N","target":"record","payload":{"canonical_record":{"source":{"id":"2601.09722","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-27T10:00:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e60801ae820c76153a3685d9100be8c96fab82231d8ccba6cea4cb8be84a0f0","abstract_canon_sha256":"8ef76df58019a5f62bdaa031758eadeffc71897ccc3ed78670056cb144341e97"},"schema_version":"1.0"},"canonical_sha256":"e023d80fc640fc2e972ba149221395e36ca1ae97908c6aab0b6f43b2d05d36c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:22.133990Z","signature_b64":"NcICJebT7ZCvcQY/lNNxtKg6QzXdBcXOl7248gZvUyZrzT08CFoWeAyj3BUyoeLKot0FVe+iNr714liQkFgPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e023d80fc640fc2e972ba149221395e36ca1ae97908c6aab0b6f43b2d05d36c8","last_reissued_at":"2026-05-20T00:04:22.133307Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:22.133307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.09722","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OL9Ux7p7m5snO6t/feLTFQpFIg5QvtJ8Assnjlo1DwtvKsNNcJku3GH6lwrlKUcLJVO5HHi8wo0BkFcq6yNPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:13:06.782235Z"},"content_sha256":"ab84528c3e307d59d47fb8bdf330a872ac1051e4959c2b992080248756b793ab","schema_version":"1.0","event_id":"sha256:ab84528c3e307d59d47fb8bdf330a872ac1051e4959c2b992080248756b793ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4AR5QD6GID6C5FZLUFESEE4V4N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ADMEDTAGGER: an annotation framework for distillation of expert knowledge for the Polish medical language","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrzej Czy\\.zewski, Franciszek G\\'orski","submitted_at":"2025-12-27T10:00:52Z","abstract_excerpt":"In this work, we present an annotation framework that demonstrates how a multilingual LLM pretrained on a large corpus can be used as a teacher model to distill the expert knowledge needed for tagging medical texts in Polish. This work is part of a larger project called ADMEDVOICE, within which we collected an extensive corpus of medical texts representing five clinical categories - Radiology, Oncology, Cardiology, Hypertension, and Pathology. Using this data, we had to develop a multi-class classifier, but the fundamental problem turned out to be the lack of resources for annotating an adequa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.09722","kind":"arxiv","version":2},"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/2601.09722/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":"2026-05-20T00:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VyMsKc86HBnMgIAztJx7LgteNG5VA486cVaz0iRlS+r3eHkj5GO17zMYSlPInlAxBUTrrMpVP1sZtSkUeSxFDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:13:06.782650Z"},"content_sha256":"d8daf518379ae5ad2a2fcee5d100987c3b3826748f13d6ac1d5396773c2e88f5","schema_version":"1.0","event_id":"sha256:d8daf518379ae5ad2a2fcee5d100987c3b3826748f13d6ac1d5396773c2e88f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4AR5QD6GID6C5FZLUFESEE4V4N/bundle.json","state_url":"https://pith.science/pith/4AR5QD6GID6C5FZLUFESEE4V4N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4AR5QD6GID6C5FZLUFESEE4V4N/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":"2026-05-27T05:13:06Z","links":{"resolver":"https://pith.science/pith/4AR5QD6GID6C5FZLUFESEE4V4N","bundle":"https://pith.science/pith/4AR5QD6GID6C5FZLUFESEE4V4N/bundle.json","state":"https://pith.science/pith/4AR5QD6GID6C5FZLUFESEE4V4N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4AR5QD6GID6C5FZLUFESEE4V4N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4AR5QD6GID6C5FZLUFESEE4V4N","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":"8ef76df58019a5f62bdaa031758eadeffc71897ccc3ed78670056cb144341e97","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-27T10:00:52Z","title_canon_sha256":"7e60801ae820c76153a3685d9100be8c96fab82231d8ccba6cea4cb8be84a0f0"},"schema_version":"1.0","source":{"id":"2601.09722","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.09722","created_at":"2026-05-20T00:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2601.09722v2","created_at":"2026-05-20T00:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.09722","created_at":"2026-05-20T00:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"4AR5QD6GID6C","created_at":"2026-05-20T00:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"4AR5QD6GID6C5FZL","created_at":"2026-05-20T00:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"4AR5QD6G","created_at":"2026-05-20T00:04:22Z"}],"graph_snapshots":[{"event_id":"sha256:d8daf518379ae5ad2a2fcee5d100987c3b3826748f13d6ac1d5396773c2e88f5","target":"graph","created_at":"2026-05-20T00:04:22Z","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/2601.09722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we present an annotation framework that demonstrates how a multilingual LLM pretrained on a large corpus can be used as a teacher model to distill the expert knowledge needed for tagging medical texts in Polish. This work is part of a larger project called ADMEDVOICE, within which we collected an extensive corpus of medical texts representing five clinical categories - Radiology, Oncology, Cardiology, Hypertension, and Pathology. Using this data, we had to develop a multi-class classifier, but the fundamental problem turned out to be the lack of resources for annotating an adequa","authors_text":"Andrzej Czy\\.zewski, Franciszek G\\'orski","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-27T10:00:52Z","title":"ADMEDTAGGER: an annotation framework for distillation of expert knowledge for the Polish medical language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.09722","kind":"arxiv","version":2},"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:ab84528c3e307d59d47fb8bdf330a872ac1051e4959c2b992080248756b793ab","target":"record","created_at":"2026-05-20T00:04:22Z","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":"8ef76df58019a5f62bdaa031758eadeffc71897ccc3ed78670056cb144341e97","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-27T10:00:52Z","title_canon_sha256":"7e60801ae820c76153a3685d9100be8c96fab82231d8ccba6cea4cb8be84a0f0"},"schema_version":"1.0","source":{"id":"2601.09722","kind":"arxiv","version":2}},"canonical_sha256":"e023d80fc640fc2e972ba149221395e36ca1ae97908c6aab0b6f43b2d05d36c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e023d80fc640fc2e972ba149221395e36ca1ae97908c6aab0b6f43b2d05d36c8","first_computed_at":"2026-05-20T00:04:22.133307Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:22.133307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NcICJebT7ZCvcQY/lNNxtKg6QzXdBcXOl7248gZvUyZrzT08CFoWeAyj3BUyoeLKot0FVe+iNr714liQkFgPCg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:22.133990Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.09722","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab84528c3e307d59d47fb8bdf330a872ac1051e4959c2b992080248756b793ab","sha256:d8daf518379ae5ad2a2fcee5d100987c3b3826748f13d6ac1d5396773c2e88f5"],"state_sha256":"b56ee90ef84f67ffa7db84d3699db74b5f224ea2b1e49bb4fcbb7f6c53029a9d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vnOnGKJoFshYFZ0LRNS6BlJRkM0gaoYmyORK2YGWchY3jh1awtHv7ew2n95YAbKFOFRIyMs7DEowFt5HgaywBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T05:13:06.784955Z","bundle_sha256":"9064a69e47bb136c407c79c9da71b4038ebbd6acf0471a7b9ec64884c2f17bbd"}}