{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JMRCVMN5DUIBHEPMTELAD3UHBA","short_pith_number":"pith:JMRCVMN5","canonical_record":{"source":{"id":"1810.07156","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-16T17:35:31Z","cross_cats_sorted":[],"title_canon_sha256":"8e26d742ef08236805a2d89dd52d34d10ca476a4baa876192f94a5213c936252","abstract_canon_sha256":"9477e0a1996b7415885bc2e4ca6486e7cafb76083fb0a51251b4f74fc67dbdda"},"schema_version":"1.0"},"canonical_sha256":"4b222ab1bd1d101391ec991601ee87081af76f4e77510c13682da34c5027a243","source":{"kind":"arxiv","id":"1810.07156","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.07156","created_at":"2026-05-18T00:01:48Z"},{"alias_kind":"arxiv_version","alias_value":"1810.07156v2","created_at":"2026-05-18T00:01:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07156","created_at":"2026-05-18T00:01:48Z"},{"alias_kind":"pith_short_12","alias_value":"JMRCVMN5DUIB","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JMRCVMN5DUIBHEPM","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JMRCVMN5","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JMRCVMN5DUIBHEPMTELAD3UHBA","target":"record","payload":{"canonical_record":{"source":{"id":"1810.07156","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-16T17:35:31Z","cross_cats_sorted":[],"title_canon_sha256":"8e26d742ef08236805a2d89dd52d34d10ca476a4baa876192f94a5213c936252","abstract_canon_sha256":"9477e0a1996b7415885bc2e4ca6486e7cafb76083fb0a51251b4f74fc67dbdda"},"schema_version":"1.0"},"canonical_sha256":"4b222ab1bd1d101391ec991601ee87081af76f4e77510c13682da34c5027a243","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:48.602266Z","signature_b64":"iZInYX0fWMK9nCQeK5BzpFDfeWBzF2Ek2cc/6Xw+YC32e6Hqmaf5tfnUvXBv3sT99kjbR+tIVF/yXS0wFRQXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b222ab1bd1d101391ec991601ee87081af76f4e77510c13682da34c5027a243","last_reissued_at":"2026-05-18T00:01:48.601703Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:48.601703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.07156","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":"2026-05-18T00:01:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o2GCIKi1DMPbAy43/gjzDN1mZ2n5P0CSTIk16a7nVMnipPnc+atFwMoYBHCInVr2SCjuAppkfMvSrGdt+HmTAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T20:46:45.854056Z"},"content_sha256":"93431eecdc631505c42546352b2319cd7f04e9cc3cc50a03b8584235161a6538","schema_version":"1.0","event_id":"sha256:93431eecdc631505c42546352b2319cd7f04e9cc3cc50a03b8584235161a6538"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JMRCVMN5DUIBHEPMTELAD3UHBA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Strategies for Language Identification in Code-Mixed Low Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sankalp Sanand, Soumil Mandal","submitted_at":"2018-10-16T17:35:31Z","abstract_excerpt":"In recent years, substantial work has been done on language tagging of code-mixed data, but most of them use large amounts of data to build their models. In this article, we present three strategies to build a word level language tagger for code-mixed data using very low resources. Each of them secured an accuracy higher than our baseline model, and the best performing system got an accuracy around 91%. Combining all, the ensemble system achieved an accuracy of around 92.6%."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07156","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":""},"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":"2026-05-18T00:01:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F26izNNlVclvhoTBGRyfgt0hhsTa9yZqra/TTWdF2J31Kl0ywSF0KwZjfuM/rd8+Fzw/syYIx0RsP4wpWovlAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T20:46:45.854402Z"},"content_sha256":"cb528737d116a9a6bc63151559a663db86c98c78c7a64c463135d25eb733c0dd","schema_version":"1.0","event_id":"sha256:cb528737d116a9a6bc63151559a663db86c98c78c7a64c463135d25eb733c0dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMRCVMN5DUIBHEPMTELAD3UHBA/bundle.json","state_url":"https://pith.science/pith/JMRCVMN5DUIBHEPMTELAD3UHBA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMRCVMN5DUIBHEPMTELAD3UHBA/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":"2026-07-13T20:46:45Z","links":{"resolver":"https://pith.science/pith/JMRCVMN5DUIBHEPMTELAD3UHBA","bundle":"https://pith.science/pith/JMRCVMN5DUIBHEPMTELAD3UHBA/bundle.json","state":"https://pith.science/pith/JMRCVMN5DUIBHEPMTELAD3UHBA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMRCVMN5DUIBHEPMTELAD3UHBA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JMRCVMN5DUIBHEPMTELAD3UHBA","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":"9477e0a1996b7415885bc2e4ca6486e7cafb76083fb0a51251b4f74fc67dbdda","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-16T17:35:31Z","title_canon_sha256":"8e26d742ef08236805a2d89dd52d34d10ca476a4baa876192f94a5213c936252"},"schema_version":"1.0","source":{"id":"1810.07156","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.07156","created_at":"2026-05-18T00:01:48Z"},{"alias_kind":"arxiv_version","alias_value":"1810.07156v2","created_at":"2026-05-18T00:01:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07156","created_at":"2026-05-18T00:01:48Z"},{"alias_kind":"pith_short_12","alias_value":"JMRCVMN5DUIB","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JMRCVMN5DUIBHEPM","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JMRCVMN5","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:cb528737d116a9a6bc63151559a663db86c98c78c7a64c463135d25eb733c0dd","target":"graph","created_at":"2026-05-18T00:01:48Z","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":"In recent years, substantial work has been done on language tagging of code-mixed data, but most of them use large amounts of data to build their models. In this article, we present three strategies to build a word level language tagger for code-mixed data using very low resources. Each of them secured an accuracy higher than our baseline model, and the best performing system got an accuracy around 91%. Combining all, the ensemble system achieved an accuracy of around 92.6%.","authors_text":"Sankalp Sanand, Soumil Mandal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-16T17:35:31Z","title":"Strategies for Language Identification in Code-Mixed Low Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07156","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":"sha256:93431eecdc631505c42546352b2319cd7f04e9cc3cc50a03b8584235161a6538","target":"record","created_at":"2026-05-18T00:01:48Z","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":"9477e0a1996b7415885bc2e4ca6486e7cafb76083fb0a51251b4f74fc67dbdda","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-16T17:35:31Z","title_canon_sha256":"8e26d742ef08236805a2d89dd52d34d10ca476a4baa876192f94a5213c936252"},"schema_version":"1.0","source":{"id":"1810.07156","kind":"arxiv","version":2}},"canonical_sha256":"4b222ab1bd1d101391ec991601ee87081af76f4e77510c13682da34c5027a243","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b222ab1bd1d101391ec991601ee87081af76f4e77510c13682da34c5027a243","first_computed_at":"2026-05-18T00:01:48.601703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:48.601703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iZInYX0fWMK9nCQeK5BzpFDfeWBzF2Ek2cc/6Xw+YC32e6Hqmaf5tfnUvXBv3sT99kjbR+tIVF/yXS0wFRQXAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:48.602266Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.07156","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93431eecdc631505c42546352b2319cd7f04e9cc3cc50a03b8584235161a6538","sha256:cb528737d116a9a6bc63151559a663db86c98c78c7a64c463135d25eb733c0dd"],"state_sha256":"9bb767c2a215e438e694ded3838082fc173872aefa95e6aab2a70dd822de1249"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AK3/upJWxuGwO95BWZUUmzIT8burE++9VRaHpeCFJUYX9oGXdfNBxrrbPuDFHQDKZaNPU6vYkkYGFsl6KYtsBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T20:46:45.856475Z","bundle_sha256":"0209dfa2d6952f5fd335ffad408d1ccfa82a8668a91a656c094f1a87a6db0e69"}}