{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:V66TES35I4IZDW3RL4FJ7QQ4JT","short_pith_number":"pith:V66TES35","canonical_record":{"source":{"id":"2402.01505","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T15:38:47Z","cross_cats_sorted":[],"title_canon_sha256":"e16f1382e1c1d2bfd10bde66368a018a7cc37e5dbc717425b09e741cb79d1789","abstract_canon_sha256":"3cfe3c106130a3fe3dc5b0e60422cd070d3da4bc44f78db5a42b75d4197b2f94"},"schema_version":"1.0"},"canonical_sha256":"afbd324b7d471191db715f0a9fc21c4cdf37fb6345a053eebb357f5aad973b33","source":{"kind":"arxiv","id":"2402.01505","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01505","created_at":"2026-07-05T07:40:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01505v1","created_at":"2026-07-05T07:40:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01505","created_at":"2026-07-05T07:40:45Z"},{"alias_kind":"pith_short_12","alias_value":"V66TES35I4IZ","created_at":"2026-07-05T07:40:45Z"},{"alias_kind":"pith_short_16","alias_value":"V66TES35I4IZDW3R","created_at":"2026-07-05T07:40:45Z"},{"alias_kind":"pith_short_8","alias_value":"V66TES35","created_at":"2026-07-05T07:40:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:V66TES35I4IZDW3RL4FJ7QQ4JT","target":"record","payload":{"canonical_record":{"source":{"id":"2402.01505","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T15:38:47Z","cross_cats_sorted":[],"title_canon_sha256":"e16f1382e1c1d2bfd10bde66368a018a7cc37e5dbc717425b09e741cb79d1789","abstract_canon_sha256":"3cfe3c106130a3fe3dc5b0e60422cd070d3da4bc44f78db5a42b75d4197b2f94"},"schema_version":"1.0"},"canonical_sha256":"afbd324b7d471191db715f0a9fc21c4cdf37fb6345a053eebb357f5aad973b33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:45.115525Z","signature_b64":"YNNedAKAd8oOzNZYTN8/xtZzOgkWw3IJtpI+jr8FQh9UZxAELdQREusXMYSqV+IMXfqrS7Bd998TCezSf4QKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afbd324b7d471191db715f0a9fc21c4cdf37fb6345a053eebb357f5aad973b33","last_reissued_at":"2026-07-05T07:40:45.115068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:45.115068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.01505","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":"2026-07-05T07:40:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aR5C3WUaseRsLqzMubVnmy7upi4cogCIo/q/rNYO7fY8bpc/AIAhhzFI9t/KFjRlJLAbrX7hnfk0pJLLnI7lDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:57:57.351182Z"},"content_sha256":"583d9571642a6fe4d56e7c149a49ae05e648fad2967befaeb16c175b2348b19c","schema_version":"1.0","event_id":"sha256:583d9571642a6fe4d56e7c149a49ae05e648fad2967befaeb16c175b2348b19c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:V66TES35I4IZDW3RL4FJ7QQ4JT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Code-Switched Language Identification is Harder Than You Think","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandra Birch, Kenneth Heafield, Laurie Burchell, Robert P. Thompson","submitted_at":"2024-02-02T15:38:47Z","abstract_excerpt":"Code switching (CS) is a very common phenomenon in written and spoken communication but one that is handled poorly by many natural language processing applications. Looking to the application of building CS corpora, we explore CS language identification (LID) for corpus building. We make the task more realistic by scaling it to more languages and considering models with simpler architectures for faster inference. We also reformulate the task as a sentence-level multi-label tagging problem to make it more tractable. Having defined the task, we investigate three reasonable models for this task a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01505","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/2402.01505/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":"2026-07-05T07:40:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OCoy7ReLX+NsyoVrxqj8KkaF6uW+qb65x8NCR+l0L9e3HMGtdWBncvYh8AtCpz1TB+Q8DcStMQCR6H+PLIVzBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:57:57.351586Z"},"content_sha256":"17581a1ec7a01e7a7423bf41bf4817b5ae87c1fdd0f791e8a9e0059ea723b97e","schema_version":"1.0","event_id":"sha256:17581a1ec7a01e7a7423bf41bf4817b5ae87c1fdd0f791e8a9e0059ea723b97e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V66TES35I4IZDW3RL4FJ7QQ4JT/bundle.json","state_url":"https://pith.science/pith/V66TES35I4IZDW3RL4FJ7QQ4JT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V66TES35I4IZDW3RL4FJ7QQ4JT/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":"2026-08-03T17:57:57Z","links":{"resolver":"https://pith.science/pith/V66TES35I4IZDW3RL4FJ7QQ4JT","bundle":"https://pith.science/pith/V66TES35I4IZDW3RL4FJ7QQ4JT/bundle.json","state":"https://pith.science/pith/V66TES35I4IZDW3RL4FJ7QQ4JT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V66TES35I4IZDW3RL4FJ7QQ4JT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V66TES35I4IZDW3RL4FJ7QQ4JT","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":"3cfe3c106130a3fe3dc5b0e60422cd070d3da4bc44f78db5a42b75d4197b2f94","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T15:38:47Z","title_canon_sha256":"e16f1382e1c1d2bfd10bde66368a018a7cc37e5dbc717425b09e741cb79d1789"},"schema_version":"1.0","source":{"id":"2402.01505","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01505","created_at":"2026-07-05T07:40:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01505v1","created_at":"2026-07-05T07:40:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01505","created_at":"2026-07-05T07:40:45Z"},{"alias_kind":"pith_short_12","alias_value":"V66TES35I4IZ","created_at":"2026-07-05T07:40:45Z"},{"alias_kind":"pith_short_16","alias_value":"V66TES35I4IZDW3R","created_at":"2026-07-05T07:40:45Z"},{"alias_kind":"pith_short_8","alias_value":"V66TES35","created_at":"2026-07-05T07:40:45Z"}],"graph_snapshots":[{"event_id":"sha256:17581a1ec7a01e7a7423bf41bf4817b5ae87c1fdd0f791e8a9e0059ea723b97e","target":"graph","created_at":"2026-07-05T07:40:45Z","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/2402.01505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code switching (CS) is a very common phenomenon in written and spoken communication but one that is handled poorly by many natural language processing applications. Looking to the application of building CS corpora, we explore CS language identification (LID) for corpus building. We make the task more realistic by scaling it to more languages and considering models with simpler architectures for faster inference. We also reformulate the task as a sentence-level multi-label tagging problem to make it more tractable. Having defined the task, we investigate three reasonable models for this task a","authors_text":"Alexandra Birch, Kenneth Heafield, Laurie Burchell, Robert P. Thompson","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T15:38:47Z","title":"Code-Switched Language Identification is Harder Than You Think"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01505","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":"sha256:583d9571642a6fe4d56e7c149a49ae05e648fad2967befaeb16c175b2348b19c","target":"record","created_at":"2026-07-05T07:40:45Z","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":"3cfe3c106130a3fe3dc5b0e60422cd070d3da4bc44f78db5a42b75d4197b2f94","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T15:38:47Z","title_canon_sha256":"e16f1382e1c1d2bfd10bde66368a018a7cc37e5dbc717425b09e741cb79d1789"},"schema_version":"1.0","source":{"id":"2402.01505","kind":"arxiv","version":1}},"canonical_sha256":"afbd324b7d471191db715f0a9fc21c4cdf37fb6345a053eebb357f5aad973b33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afbd324b7d471191db715f0a9fc21c4cdf37fb6345a053eebb357f5aad973b33","first_computed_at":"2026-07-05T07:40:45.115068Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:45.115068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YNNedAKAd8oOzNZYTN8/xtZzOgkWw3IJtpI+jr8FQh9UZxAELdQREusXMYSqV+IMXfqrS7Bd998TCezSf4QKDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:45.115525Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01505","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:583d9571642a6fe4d56e7c149a49ae05e648fad2967befaeb16c175b2348b19c","sha256:17581a1ec7a01e7a7423bf41bf4817b5ae87c1fdd0f791e8a9e0059ea723b97e"],"state_sha256":"d9afeab1e2431bfec0e1cb9f5fd21bed736fa9096e0cbc12080b8c2c4862416e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q8fUPLD9MaRRzUlzFnSbY60aty5Ix18co3kSL8NpVEB6qmEnGuLsgNNBUht3dKCZ846U4pqGNR8jJfeCUth6Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:57:57.354111Z","bundle_sha256":"2f0642e419fb3c9b35143d64895ec91b3a459c57f466130e7be826e72170fd9e"}}