{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NNO3HKPYVTH36GODF23IILR7US","short_pith_number":"pith:NNO3HKPY","canonical_record":{"source":{"id":"1903.10915","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-03-26T14:19:19Z","cross_cats_sorted":[],"title_canon_sha256":"ae98f4713a5348d595190913e18c13f22a4c0c0a4f404bb651ad81bb04ca774b","abstract_canon_sha256":"c0be650c00284f6be955559db49cd89e177d4c6fe26522e59f47f79c848ef50c"},"schema_version":"1.0"},"canonical_sha256":"6b5db3a9f8accfbf19c32eb6842e3fa4843f9001142c3c98eccb2bf0b8af36de","source":{"kind":"arxiv","id":"1903.10915","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.10915","created_at":"2026-05-17T23:50:17Z"},{"alias_kind":"arxiv_version","alias_value":"1903.10915v1","created_at":"2026-05-17T23:50:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10915","created_at":"2026-05-17T23:50:17Z"},{"alias_kind":"pith_short_12","alias_value":"NNO3HKPYVTH3","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NNO3HKPYVTH36GOD","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NNO3HKPY","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NNO3HKPYVTH36GODF23IILR7US","target":"record","payload":{"canonical_record":{"source":{"id":"1903.10915","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-03-26T14:19:19Z","cross_cats_sorted":[],"title_canon_sha256":"ae98f4713a5348d595190913e18c13f22a4c0c0a4f404bb651ad81bb04ca774b","abstract_canon_sha256":"c0be650c00284f6be955559db49cd89e177d4c6fe26522e59f47f79c848ef50c"},"schema_version":"1.0"},"canonical_sha256":"6b5db3a9f8accfbf19c32eb6842e3fa4843f9001142c3c98eccb2bf0b8af36de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:17.242242Z","signature_b64":"LpG7qLeungHWZJBaN1SKbUM/NBxOXexFszDXlOE7O5NdT218ytHX3Fn5wB3ubDsS4KmWeJuH0PL2uQdhBuQyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b5db3a9f8accfbf19c32eb6842e3fa4843f9001142c3c98eccb2bf0b8af36de","last_reissued_at":"2026-05-17T23:50:17.241539Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:17.241539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.10915","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":"2026-05-17T23:50:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RnVoA1PE5Xm3LCmUPLda/FyNdAr7HzkyL15MAz1mekuJqT3chSEtImSQeyEkH1GTHnSX3Ae1GtiyZ8OEGXksBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T06:03:48.160100Z"},"content_sha256":"039f9b05633bd3dc7a29d956964e65f28de96a58574639ba2cd55dc0cdf4c55d","schema_version":"1.0","event_id":"sha256:039f9b05633bd3dc7a29d956964e65f28de96a58574639ba2cd55dc0cdf4c55d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NNO3HKPYVTH36GODF23IILR7US","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Model Adaptation for Language and Dialect Identification of Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heidi Jauhiainen, Krister Lind\\'en, Tommi Jauhiainen","submitted_at":"2019-03-26T14:19:19Z","abstract_excerpt":"This article describes an unsupervised language model adaptation approach that can be used to enhance the performance of language identification methods. The approach is applied to a current version of the HeLI language identification method, which is now called HeLI 2.0. We describe the HeLI 2.0 method in detail. The resulting system is evaluated using the datasets from the German dialect identification and Indo-Aryan language identification shared tasks of the VarDial workshops 2017 and 2018. The new approach with language identification provides considerably higher F1-scores than the previo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10915","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":"2026-05-17T23:50:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N/L27BHe7FERAWBSQCnnjT0OUbfRdPJeZKZ4i3ofxqxWn94mkZ69PaB4nTWzunSaVipxw1yqDa6m3PR7EFouBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T06:03:48.160810Z"},"content_sha256":"3576e2eeefbf756c78d7debda32eb9b2bed0c4070f0004761d564ad5246c5305","schema_version":"1.0","event_id":"sha256:3576e2eeefbf756c78d7debda32eb9b2bed0c4070f0004761d564ad5246c5305"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NNO3HKPYVTH36GODF23IILR7US/bundle.json","state_url":"https://pith.science/pith/NNO3HKPYVTH36GODF23IILR7US/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NNO3HKPYVTH36GODF23IILR7US/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":"2026-06-08T06:03:48Z","links":{"resolver":"https://pith.science/pith/NNO3HKPYVTH36GODF23IILR7US","bundle":"https://pith.science/pith/NNO3HKPYVTH36GODF23IILR7US/bundle.json","state":"https://pith.science/pith/NNO3HKPYVTH36GODF23IILR7US/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NNO3HKPYVTH36GODF23IILR7US/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NNO3HKPYVTH36GODF23IILR7US","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":"c0be650c00284f6be955559db49cd89e177d4c6fe26522e59f47f79c848ef50c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-03-26T14:19:19Z","title_canon_sha256":"ae98f4713a5348d595190913e18c13f22a4c0c0a4f404bb651ad81bb04ca774b"},"schema_version":"1.0","source":{"id":"1903.10915","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.10915","created_at":"2026-05-17T23:50:17Z"},{"alias_kind":"arxiv_version","alias_value":"1903.10915v1","created_at":"2026-05-17T23:50:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10915","created_at":"2026-05-17T23:50:17Z"},{"alias_kind":"pith_short_12","alias_value":"NNO3HKPYVTH3","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NNO3HKPYVTH36GOD","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NNO3HKPY","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:3576e2eeefbf756c78d7debda32eb9b2bed0c4070f0004761d564ad5246c5305","target":"graph","created_at":"2026-05-17T23:50:17Z","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":"This article describes an unsupervised language model adaptation approach that can be used to enhance the performance of language identification methods. The approach is applied to a current version of the HeLI language identification method, which is now called HeLI 2.0. We describe the HeLI 2.0 method in detail. The resulting system is evaluated using the datasets from the German dialect identification and Indo-Aryan language identification shared tasks of the VarDial workshops 2017 and 2018. The new approach with language identification provides considerably higher F1-scores than the previo","authors_text":"Heidi Jauhiainen, Krister Lind\\'en, Tommi Jauhiainen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-03-26T14:19:19Z","title":"Language Model Adaptation for Language and Dialect Identification of Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10915","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":"sha256:039f9b05633bd3dc7a29d956964e65f28de96a58574639ba2cd55dc0cdf4c55d","target":"record","created_at":"2026-05-17T23:50:17Z","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":"c0be650c00284f6be955559db49cd89e177d4c6fe26522e59f47f79c848ef50c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-03-26T14:19:19Z","title_canon_sha256":"ae98f4713a5348d595190913e18c13f22a4c0c0a4f404bb651ad81bb04ca774b"},"schema_version":"1.0","source":{"id":"1903.10915","kind":"arxiv","version":1}},"canonical_sha256":"6b5db3a9f8accfbf19c32eb6842e3fa4843f9001142c3c98eccb2bf0b8af36de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b5db3a9f8accfbf19c32eb6842e3fa4843f9001142c3c98eccb2bf0b8af36de","first_computed_at":"2026-05-17T23:50:17.241539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:17.241539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LpG7qLeungHWZJBaN1SKbUM/NBxOXexFszDXlOE7O5NdT218ytHX3Fn5wB3ubDsS4KmWeJuH0PL2uQdhBuQyDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:17.242242Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.10915","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:039f9b05633bd3dc7a29d956964e65f28de96a58574639ba2cd55dc0cdf4c55d","sha256:3576e2eeefbf756c78d7debda32eb9b2bed0c4070f0004761d564ad5246c5305"],"state_sha256":"42772a4e8ba10188c5891566a1be43d83fe6b3f41453b6dc21ee9249812a3774"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"piEmuffnfUg7ANkc/ExzpizAvSuqbeVU6rZr10bcPwfNJegWJcSUOqstJnl5yK4qSGzemJ6cYnhKLt/Ln1fgAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T06:03:48.164523Z","bundle_sha256":"d30c3b92c5cc0ce125df148a9784e7b61cee3acb1c473ff682be8e1aeabac87f"}}