{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Z22J7HCRJLURGDGPPJGA3UQY4X","short_pith_number":"pith:Z22J7HCR","canonical_record":{"source":{"id":"1810.10222","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-24T07:34:45Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"de3116e935347ee890fd8d8251ff462852ef3d81d6ae5f2db9d2f6932aaa1a76","abstract_canon_sha256":"901ee5506d6eb801c14dffa00ba6a6dc7b2d95d6778eb103667d284d30fe97ea"},"schema_version":"1.0"},"canonical_sha256":"ceb49f9c514ae9130ccf7a4c0dd218e5ec385fee6b2c41b1c1b0344dcebb5f9b","source":{"kind":"arxiv","id":"1810.10222","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.10222","created_at":"2026-05-18T00:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"1810.10222v1","created_at":"2026-05-18T00:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10222","created_at":"2026-05-18T00:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"Z22J7HCRJLUR","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Z22J7HCRJLURGDGP","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Z22J7HCR","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Z22J7HCRJLURGDGPPJGA3UQY4X","target":"record","payload":{"canonical_record":{"source":{"id":"1810.10222","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-24T07:34:45Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"de3116e935347ee890fd8d8251ff462852ef3d81d6ae5f2db9d2f6932aaa1a76","abstract_canon_sha256":"901ee5506d6eb801c14dffa00ba6a6dc7b2d95d6778eb103667d284d30fe97ea"},"schema_version":"1.0"},"canonical_sha256":"ceb49f9c514ae9130ccf7a4c0dd218e5ec385fee6b2c41b1c1b0344dcebb5f9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:23.853158Z","signature_b64":"vOVZ/5dxQHJpKXUYcDa+Shs7JuqQ+eeIV52ypAiN2z3lGA4N7zE+VGY9EO9vYpu5r0A8U0873jq6LHzSn1duAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceb49f9c514ae9130ccf7a4c0dd218e5ec385fee6b2c41b1c1b0344dcebb5f9b","last_reissued_at":"2026-05-18T00:02:23.852678Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:23.852678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.10222","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":"2026-05-18T00:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c1Nn8zOdQ2ofMnJUa9L+LvsWMsGfNhFuSc8d0Nmz8Zeb13d4UVRIqSJWWAasoPI/49S63S8CmP2DKqMY2/wwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:16:27.731263Z"},"content_sha256":"97a6b5303069f92077dfe20360b637a07874f6c4418bcaccd9b847ab6de03a68","schema_version":"1.0","event_id":"sha256:97a6b5303069f92077dfe20360b637a07874f6c4418bcaccd9b847ab6de03a68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Z22J7HCRJLURGDGPPJGA3UQY4X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Universal Language Model Fine-Tuning with Subword Tokenization for Polish","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Jeremy Howard, Marcin Kardas, Piotr Czapla","submitted_at":"2018-10-24T07:34:45Z","abstract_excerpt":"Universal Language Model for Fine-tuning [arXiv:1801.06146] (ULMFiT) is one of the first NLP methods for efficient inductive transfer learning. Unsupervised pretraining results in improvements on many NLP tasks for English. In this paper, we describe a new method that uses subword tokenization to adapt ULMFiT to languages with high inflection. Our approach results in a new state-of-the-art for the Polish language, taking first place in Task 3 of PolEval'18. After further training, our final model outperformed the second best model by 35%. We have open-sourced our pretrained models and code."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10222","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":""},"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":"2026-05-18T00:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4bfb/N6NvE3uNFRFoVkq9DvMsmf5jMHtFrnT9zans9aivtVXhPrtCLpx8hHiQIZPRtZo74JjTa8xA+vv+9SsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:16:27.731961Z"},"content_sha256":"501f6a49da2a8764d8a4265b0662f1ae049bc6f1dcdbbe5e81f1bebc23498774","schema_version":"1.0","event_id":"sha256:501f6a49da2a8764d8a4265b0662f1ae049bc6f1dcdbbe5e81f1bebc23498774"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z22J7HCRJLURGDGPPJGA3UQY4X/bundle.json","state_url":"https://pith.science/pith/Z22J7HCRJLURGDGPPJGA3UQY4X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z22J7HCRJLURGDGPPJGA3UQY4X/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":"2026-05-25T20:16:27Z","links":{"resolver":"https://pith.science/pith/Z22J7HCRJLURGDGPPJGA3UQY4X","bundle":"https://pith.science/pith/Z22J7HCRJLURGDGPPJGA3UQY4X/bundle.json","state":"https://pith.science/pith/Z22J7HCRJLURGDGPPJGA3UQY4X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z22J7HCRJLURGDGPPJGA3UQY4X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Z22J7HCRJLURGDGPPJGA3UQY4X","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":"901ee5506d6eb801c14dffa00ba6a6dc7b2d95d6778eb103667d284d30fe97ea","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-24T07:34:45Z","title_canon_sha256":"de3116e935347ee890fd8d8251ff462852ef3d81d6ae5f2db9d2f6932aaa1a76"},"schema_version":"1.0","source":{"id":"1810.10222","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.10222","created_at":"2026-05-18T00:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"1810.10222v1","created_at":"2026-05-18T00:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10222","created_at":"2026-05-18T00:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"Z22J7HCRJLUR","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Z22J7HCRJLURGDGP","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Z22J7HCR","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:501f6a49da2a8764d8a4265b0662f1ae049bc6f1dcdbbe5e81f1bebc23498774","target":"graph","created_at":"2026-05-18T00:02:23Z","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"},"paper":{"abstract_excerpt":"Universal Language Model for Fine-tuning [arXiv:1801.06146] (ULMFiT) is one of the first NLP methods for efficient inductive transfer learning. Unsupervised pretraining results in improvements on many NLP tasks for English. In this paper, we describe a new method that uses subword tokenization to adapt ULMFiT to languages with high inflection. Our approach results in a new state-of-the-art for the Polish language, taking first place in Task 3 of PolEval'18. After further training, our final model outperformed the second best model by 35%. We have open-sourced our pretrained models and code.","authors_text":"Jeremy Howard, Marcin Kardas, Piotr Czapla","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-24T07:34:45Z","title":"Universal Language Model Fine-Tuning with Subword Tokenization for Polish"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10222","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":"sha256:97a6b5303069f92077dfe20360b637a07874f6c4418bcaccd9b847ab6de03a68","target":"record","created_at":"2026-05-18T00:02:23Z","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":"901ee5506d6eb801c14dffa00ba6a6dc7b2d95d6778eb103667d284d30fe97ea","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-24T07:34:45Z","title_canon_sha256":"de3116e935347ee890fd8d8251ff462852ef3d81d6ae5f2db9d2f6932aaa1a76"},"schema_version":"1.0","source":{"id":"1810.10222","kind":"arxiv","version":1}},"canonical_sha256":"ceb49f9c514ae9130ccf7a4c0dd218e5ec385fee6b2c41b1c1b0344dcebb5f9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ceb49f9c514ae9130ccf7a4c0dd218e5ec385fee6b2c41b1c1b0344dcebb5f9b","first_computed_at":"2026-05-18T00:02:23.852678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:23.852678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vOVZ/5dxQHJpKXUYcDa+Shs7JuqQ+eeIV52ypAiN2z3lGA4N7zE+VGY9EO9vYpu5r0A8U0873jq6LHzSn1duAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:23.853158Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.10222","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97a6b5303069f92077dfe20360b637a07874f6c4418bcaccd9b847ab6de03a68","sha256:501f6a49da2a8764d8a4265b0662f1ae049bc6f1dcdbbe5e81f1bebc23498774"],"state_sha256":"72805d1d80b129be9bd8fe528f846dd3a7bb1f727d0442aaae5acaed46379675"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MBJ8y4k6DOuPN2ZWrEDheFXcn8AJju7+PL3FUDS8GbzXGsL7xRnT0IIrmT/LXWzc/uPFB/sUh17gkh84ev7JBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:16:27.735911Z","bundle_sha256":"b2ae7db749ced48e7470246271689f073c7c89051899dff6aad531224bbbbfbf"}}