{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HXPYZ25SYDFMRHJACEMP5ATDMN","short_pith_number":"pith:HXPYZ25S","canonical_record":{"source":{"id":"1810.04142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-09T17:21:41Z","cross_cats_sorted":[],"title_canon_sha256":"044a35dc444e657425c3cb5656d4ebc7f2519625fe4e9161568f8bbe5ac239d6","abstract_canon_sha256":"3d2694f95a62f6b2872577fc7e3a5c280c75d1e1016a1382266e654716136aab"},"schema_version":"1.0"},"canonical_sha256":"3ddf8cebb2c0cac89d201118fe82636340669894c37537b8380ef56a39fac58a","source":{"kind":"arxiv","id":"1810.04142","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04142","created_at":"2026-05-18T00:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04142v1","created_at":"2026-05-18T00:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04142","created_at":"2026-05-18T00:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"HXPYZ25SYDFM","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HXPYZ25SYDFMRHJA","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HXPYZ25S","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HXPYZ25SYDFMRHJACEMP5ATDMN","target":"record","payload":{"canonical_record":{"source":{"id":"1810.04142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-09T17:21:41Z","cross_cats_sorted":[],"title_canon_sha256":"044a35dc444e657425c3cb5656d4ebc7f2519625fe4e9161568f8bbe5ac239d6","abstract_canon_sha256":"3d2694f95a62f6b2872577fc7e3a5c280c75d1e1016a1382266e654716136aab"},"schema_version":"1.0"},"canonical_sha256":"3ddf8cebb2c0cac89d201118fe82636340669894c37537b8380ef56a39fac58a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:42.178806Z","signature_b64":"DHU0JiwcewBzh2ruYALVb3NW4criJMnpDY1tSXXwWldxPa4gpdWsU6a6DEjdApx1mCC6vRJRovS4q4ebsJPWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ddf8cebb2c0cac89d201118fe82636340669894c37537b8380ef56a39fac58a","last_reissued_at":"2026-05-18T00:03:42.178285Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:42.178285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.04142","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":"2026-05-18T00:03:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wqlOVtQoyGpyddTP9HINnruOVwaNW6/Lubfbi69RqUNRiYf3jKxAkhz+HSfprsw6dvlxE7l+GbPuHgzT/cmiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T21:08:53.057188Z"},"content_sha256":"7057a461d4111f4080829d957575fba4856dffb73e2c36612722e12b8bac8be1","schema_version":"1.0","event_id":"sha256:7057a461d4111f4080829d957575fba4856dffb73e2c36612722e12b8bac8be1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HXPYZ25SYDFMRHJACEMP5ATDMN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Fast, Compact, Accurate Model for Language Identification of Codemixed Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anton Bakalov, Daniel Gillick, David Weiss, Jason Baldridge, Jason Riesa, Yuan Zhang","submitted_at":"2018-10-09T17:21:41Z","abstract_excerpt":"We address fine-grained multilingual language identification: providing a language code for every token in a sentence, including codemixed text containing multiple languages. Such text is prevalent online, in documents, social media, and message boards. We show that a feed-forward network with a simple globally constrained decoder can accurately and rapidly label both codemixed and monolingual text in 100 languages and 100 language pairs. This model outperforms previously published multilingual approaches in terms of both accuracy and speed, yielding an 800x speed-up and a 19.5% averaged absol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04142","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":"2026-05-18T00:03:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5OHDbF4lWE6OmpF12DARC2htVi/nCf39J62MHs6IVbx+DVrrW4D45qkQQ5sp04TQeNbeHpfR/yLfXuiCcmjWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T21:08:53.057557Z"},"content_sha256":"980b60fab38a46f473a9d394a9060e8790eb9d73692dde5848930a229a4c896b","schema_version":"1.0","event_id":"sha256:980b60fab38a46f473a9d394a9060e8790eb9d73692dde5848930a229a4c896b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HXPYZ25SYDFMRHJACEMP5ATDMN/bundle.json","state_url":"https://pith.science/pith/HXPYZ25SYDFMRHJACEMP5ATDMN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HXPYZ25SYDFMRHJACEMP5ATDMN/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":"2026-05-29T21:08:53Z","links":{"resolver":"https://pith.science/pith/HXPYZ25SYDFMRHJACEMP5ATDMN","bundle":"https://pith.science/pith/HXPYZ25SYDFMRHJACEMP5ATDMN/bundle.json","state":"https://pith.science/pith/HXPYZ25SYDFMRHJACEMP5ATDMN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HXPYZ25SYDFMRHJACEMP5ATDMN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HXPYZ25SYDFMRHJACEMP5ATDMN","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":"3d2694f95a62f6b2872577fc7e3a5c280c75d1e1016a1382266e654716136aab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-09T17:21:41Z","title_canon_sha256":"044a35dc444e657425c3cb5656d4ebc7f2519625fe4e9161568f8bbe5ac239d6"},"schema_version":"1.0","source":{"id":"1810.04142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04142","created_at":"2026-05-18T00:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04142v1","created_at":"2026-05-18T00:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04142","created_at":"2026-05-18T00:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"HXPYZ25SYDFM","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HXPYZ25SYDFMRHJA","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HXPYZ25S","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:980b60fab38a46f473a9d394a9060e8790eb9d73692dde5848930a229a4c896b","target":"graph","created_at":"2026-05-18T00:03:42Z","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":"We address fine-grained multilingual language identification: providing a language code for every token in a sentence, including codemixed text containing multiple languages. Such text is prevalent online, in documents, social media, and message boards. We show that a feed-forward network with a simple globally constrained decoder can accurately and rapidly label both codemixed and monolingual text in 100 languages and 100 language pairs. This model outperforms previously published multilingual approaches in terms of both accuracy and speed, yielding an 800x speed-up and a 19.5% averaged absol","authors_text":"Anton Bakalov, Daniel Gillick, David Weiss, Jason Baldridge, Jason Riesa, Yuan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-09T17:21:41Z","title":"A Fast, Compact, Accurate Model for Language Identification of Codemixed Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04142","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":"sha256:7057a461d4111f4080829d957575fba4856dffb73e2c36612722e12b8bac8be1","target":"record","created_at":"2026-05-18T00:03:42Z","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":"3d2694f95a62f6b2872577fc7e3a5c280c75d1e1016a1382266e654716136aab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-09T17:21:41Z","title_canon_sha256":"044a35dc444e657425c3cb5656d4ebc7f2519625fe4e9161568f8bbe5ac239d6"},"schema_version":"1.0","source":{"id":"1810.04142","kind":"arxiv","version":1}},"canonical_sha256":"3ddf8cebb2c0cac89d201118fe82636340669894c37537b8380ef56a39fac58a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ddf8cebb2c0cac89d201118fe82636340669894c37537b8380ef56a39fac58a","first_computed_at":"2026-05-18T00:03:42.178285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:42.178285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DHU0JiwcewBzh2ruYALVb3NW4criJMnpDY1tSXXwWldxPa4gpdWsU6a6DEjdApx1mCC6vRJRovS4q4ebsJPWDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:42.178806Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.04142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7057a461d4111f4080829d957575fba4856dffb73e2c36612722e12b8bac8be1","sha256:980b60fab38a46f473a9d394a9060e8790eb9d73692dde5848930a229a4c896b"],"state_sha256":"5d7b421b214c78663c6cbc232c3b45d0e876a883414924579552173b28ca7516"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p9V8nUXBcsLgzbWkl71t9G2rN7ITvTMAeUXNtd8mjBXW055FmeMqbnBMKA+ZX9ljExowtBj2KWCrIsP+iMYGBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T21:08:53.059791Z","bundle_sha256":"376ee023ea0bcf06ac192aff43be032a3bc0f6e55b6b74f28034509b6fb9e707"}}