{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ERKZ4LMOQNHC4SGQDFOWZU5WB7","short_pith_number":"pith:ERKZ4LMO","canonical_record":{"source":{"id":"2107.06483","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-14T04:46:39Z","cross_cats_sorted":[],"title_canon_sha256":"3bf7cbbf3493e8ce7fcde18a663b2331f8e3d3a1fbc58457cf1151aa67ec40fa","abstract_canon_sha256":"5d0fee5e4dca31b9e47ad043fe1f4f7f1f9a967ea19f51b58c6bbe82a6462f9b"},"schema_version":"1.0"},"canonical_sha256":"24559e2d8e834e2e48d0195d6cd3b60fd882047ffe5e1318ae9fd570c6d16f0a","source":{"kind":"arxiv","id":"2107.06483","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.06483","created_at":"2026-07-05T02:57:58Z"},{"alias_kind":"arxiv_version","alias_value":"2107.06483v1","created_at":"2026-07-05T02:57:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06483","created_at":"2026-07-05T02:57:58Z"},{"alias_kind":"pith_short_12","alias_value":"ERKZ4LMOQNHC","created_at":"2026-07-05T02:57:58Z"},{"alias_kind":"pith_short_16","alias_value":"ERKZ4LMOQNHC4SGQ","created_at":"2026-07-05T02:57:58Z"},{"alias_kind":"pith_short_8","alias_value":"ERKZ4LMO","created_at":"2026-07-05T02:57:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ERKZ4LMOQNHC4SGQDFOWZU5WB7","target":"record","payload":{"canonical_record":{"source":{"id":"2107.06483","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-14T04:46:39Z","cross_cats_sorted":[],"title_canon_sha256":"3bf7cbbf3493e8ce7fcde18a663b2331f8e3d3a1fbc58457cf1151aa67ec40fa","abstract_canon_sha256":"5d0fee5e4dca31b9e47ad043fe1f4f7f1f9a967ea19f51b58c6bbe82a6462f9b"},"schema_version":"1.0"},"canonical_sha256":"24559e2d8e834e2e48d0195d6cd3b60fd882047ffe5e1318ae9fd570c6d16f0a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:57:58.563266Z","signature_b64":"or42fekC3ehtL0u0Bh62gWYmqGpwdP/dC0lQN8b8kpJCxAns/MfliF2eVoHKYx+p5XF5/tgxAHN9QF9T2Sz6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24559e2d8e834e2e48d0195d6cd3b60fd882047ffe5e1318ae9fd570c6d16f0a","last_reissued_at":"2026-07-05T02:57:58.562870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:57:58.562870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.06483","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":"2026-07-05T02:57:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t5OEDrNdUnH3KIsPhly9R1q05gHRq8681BN9PjCU9lHXTAbs9ebeHJr/hYNUJX5lAyx1ccpHQ+FbETjkRpj2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:24:41.851342Z"},"content_sha256":"bf9c4d59534f57e23bbfdcd40d19e970e3ccab293b66bf36334015f4e20e06ad","schema_version":"1.0","event_id":"sha256:bf9c4d59534f57e23bbfdcd40d19e970e3ccab293b66bf36334015f4e20e06ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ERKZ4LMOQNHC4SGQDFOWZU5WB7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ishan Tarunesh, Preethi Jyothi, Syamantak Kumar","submitted_at":"2021-07-14T04:46:39Z","abstract_excerpt":"Generating code-switched text is a problem of growing interest, especially given the scarcity of corpora containing large volumes of real code-switched text. In this work, we adapt a state-of-the-art neural machine translation model to generate Hindi-English code-switched sentences starting from monolingual Hindi sentences. We outline a carefully designed curriculum of pretraining steps, including the use of synthetic code-switched text, that enable the model to generate high-quality code-switched text. Using text generated from our model as data augmentation, we show significant reductions in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06483","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/2107.06483/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":"2026-07-05T02:57:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S129k886yiV2Ex9eaOfDkrvNwLdhmgFN2Tuuxi8AhbZNDjuFOP3SGNOmqaXmXIUzBVUClWNIVYhLqsd0VSIEDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:24:41.851831Z"},"content_sha256":"44d91c5b2c11b4a12696cf50cbf1823ba7bc1c09466518f2cd7943befd16ca34","schema_version":"1.0","event_id":"sha256:44d91c5b2c11b4a12696cf50cbf1823ba7bc1c09466518f2cd7943befd16ca34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ERKZ4LMOQNHC4SGQDFOWZU5WB7/bundle.json","state_url":"https://pith.science/pith/ERKZ4LMOQNHC4SGQDFOWZU5WB7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ERKZ4LMOQNHC4SGQDFOWZU5WB7/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":"2026-08-15T14:24:41Z","links":{"resolver":"https://pith.science/pith/ERKZ4LMOQNHC4SGQDFOWZU5WB7","bundle":"https://pith.science/pith/ERKZ4LMOQNHC4SGQDFOWZU5WB7/bundle.json","state":"https://pith.science/pith/ERKZ4LMOQNHC4SGQDFOWZU5WB7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ERKZ4LMOQNHC4SGQDFOWZU5WB7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ERKZ4LMOQNHC4SGQDFOWZU5WB7","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":"5d0fee5e4dca31b9e47ad043fe1f4f7f1f9a967ea19f51b58c6bbe82a6462f9b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-14T04:46:39Z","title_canon_sha256":"3bf7cbbf3493e8ce7fcde18a663b2331f8e3d3a1fbc58457cf1151aa67ec40fa"},"schema_version":"1.0","source":{"id":"2107.06483","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.06483","created_at":"2026-07-05T02:57:58Z"},{"alias_kind":"arxiv_version","alias_value":"2107.06483v1","created_at":"2026-07-05T02:57:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06483","created_at":"2026-07-05T02:57:58Z"},{"alias_kind":"pith_short_12","alias_value":"ERKZ4LMOQNHC","created_at":"2026-07-05T02:57:58Z"},{"alias_kind":"pith_short_16","alias_value":"ERKZ4LMOQNHC4SGQ","created_at":"2026-07-05T02:57:58Z"},{"alias_kind":"pith_short_8","alias_value":"ERKZ4LMO","created_at":"2026-07-05T02:57:58Z"}],"graph_snapshots":[{"event_id":"sha256:44d91c5b2c11b4a12696cf50cbf1823ba7bc1c09466518f2cd7943befd16ca34","target":"graph","created_at":"2026-07-05T02:57:58Z","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/2107.06483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating code-switched text is a problem of growing interest, especially given the scarcity of corpora containing large volumes of real code-switched text. In this work, we adapt a state-of-the-art neural machine translation model to generate Hindi-English code-switched sentences starting from monolingual Hindi sentences. We outline a carefully designed curriculum of pretraining steps, including the use of synthetic code-switched text, that enable the model to generate high-quality code-switched text. Using text generated from our model as data augmentation, we show significant reductions in","authors_text":"Ishan Tarunesh, Preethi Jyothi, Syamantak Kumar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-14T04:46:39Z","title":"From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06483","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:bf9c4d59534f57e23bbfdcd40d19e970e3ccab293b66bf36334015f4e20e06ad","target":"record","created_at":"2026-07-05T02:57:58Z","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":"5d0fee5e4dca31b9e47ad043fe1f4f7f1f9a967ea19f51b58c6bbe82a6462f9b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-14T04:46:39Z","title_canon_sha256":"3bf7cbbf3493e8ce7fcde18a663b2331f8e3d3a1fbc58457cf1151aa67ec40fa"},"schema_version":"1.0","source":{"id":"2107.06483","kind":"arxiv","version":1}},"canonical_sha256":"24559e2d8e834e2e48d0195d6cd3b60fd882047ffe5e1318ae9fd570c6d16f0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24559e2d8e834e2e48d0195d6cd3b60fd882047ffe5e1318ae9fd570c6d16f0a","first_computed_at":"2026-07-05T02:57:58.562870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:57:58.562870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"or42fekC3ehtL0u0Bh62gWYmqGpwdP/dC0lQN8b8kpJCxAns/MfliF2eVoHKYx+p5XF5/tgxAHN9QF9T2Sz6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:57:58.563266Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.06483","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf9c4d59534f57e23bbfdcd40d19e970e3ccab293b66bf36334015f4e20e06ad","sha256:44d91c5b2c11b4a12696cf50cbf1823ba7bc1c09466518f2cd7943befd16ca34"],"state_sha256":"b95f8685ce934f378589f287dcb19afe6937d2c8098e1c4b062f059aca463022"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FBpAqzI9QinWpqMm7+KM21CpBV1Wy0Uo6xso81y+czfmkltdGmTgvws4ff+Uo2SMsRP730JG8AkdaP8uHws9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T14:24:41.856016Z","bundle_sha256":"8f6611026cd10998b7e4d3ab237c17239b9863a59b42c89ca522740f0dc6e9a4"}}