{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CLWVKXIW7GGX6IB377HCD45H5Z","short_pith_number":"pith:CLWVKXIW","canonical_record":{"source":{"id":"2403.16771","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T13:50:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"019cf46187d674d75883592f83fe61f91f076ad0a99673b69e35c685dfd6e83a","abstract_canon_sha256":"68b4b8464a2897dc3a09d1a87594c0d19715705e0787770e9e9f0ec27e48a5d2"},"schema_version":"1.0"},"canonical_sha256":"12ed555d16f98d7f203bffce21f3a7ee6de80e2342496e814c71595264c5c065","source":{"kind":"arxiv","id":"2403.16771","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16771","created_at":"2026-07-05T08:13:31Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16771v2","created_at":"2026-07-05T08:13:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16771","created_at":"2026-07-05T08:13:31Z"},{"alias_kind":"pith_short_12","alias_value":"CLWVKXIW7GGX","created_at":"2026-07-05T08:13:31Z"},{"alias_kind":"pith_short_16","alias_value":"CLWVKXIW7GGX6IB3","created_at":"2026-07-05T08:13:31Z"},{"alias_kind":"pith_short_8","alias_value":"CLWVKXIW","created_at":"2026-07-05T08:13:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CLWVKXIW7GGX6IB377HCD45H5Z","target":"record","payload":{"canonical_record":{"source":{"id":"2403.16771","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T13:50:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"019cf46187d674d75883592f83fe61f91f076ad0a99673b69e35c685dfd6e83a","abstract_canon_sha256":"68b4b8464a2897dc3a09d1a87594c0d19715705e0787770e9e9f0ec27e48a5d2"},"schema_version":"1.0"},"canonical_sha256":"12ed555d16f98d7f203bffce21f3a7ee6de80e2342496e814c71595264c5c065","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:31.325289Z","signature_b64":"iRm9Cz7s/bILdE5AEegh8Hh7u4Mg1xDIyQXmSg2zjXb3X52slIBSGtVhsWgLsCh/eLkGcwo0jyOsQGWvgZu1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12ed555d16f98d7f203bffce21f3a7ee6de80e2342496e814c71595264c5c065","last_reissued_at":"2026-07-05T08:13:31.324776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:31.324776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.16771","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":"2026-07-05T08:13:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"24uTQUeKBn19JALqtqZTJO8eHlu2Zm1tNvz9XBUWO1iRvNBQg/Op0WhxGYgPwYy20oQ1phtNybrOhU8jwphTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T19:04:24.128334Z"},"content_sha256":"7374b96a1ffe41018eb291a83fb19ca5fe43c997452748f0dc94fd211366f04b","schema_version":"1.0","event_id":"sha256:7374b96a1ffe41018eb291a83fb19ca5fe43c997452748f0dc94fd211366f04b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CLWVKXIW7GGX6IB377HCD45H5Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Kartik Kartik, Md Shad Akhtar, Sanjana Soni, Tanmoy Chakraborty","submitted_at":"2024-03-25T13:50:11Z","abstract_excerpt":"The widespread online communication in a modern multilingual world has provided opportunities to blend more than one language (aka code-mixed language) in a single utterance. This has resulted a formidable challenge for the computational models due to the scarcity of annotated data and presence of noise. A potential solution to mitigate the data scarcity problem in low-resource setup is to leverage existing data in resource-rich language through translation. In this paper, we tackle the problem of code-mixed (Hinglish and Bengalish) to English machine translation. First, we synthetically devel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16771","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.16771/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":"2026-07-05T08:13:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kP6LjsZNm2uhWylgB/TE3svR3su5RrIANmBcA9GctS6m3umn+ZbiaXJLOxIuCMVVx/Y/yq8kKsC26Yapz0iiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T19:04:24.128712Z"},"content_sha256":"8aa7b85b56c9c10e8812d19a3ca767a8727ff65ea3760d172edb810a9456d3db","schema_version":"1.0","event_id":"sha256:8aa7b85b56c9c10e8812d19a3ca767a8727ff65ea3760d172edb810a9456d3db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CLWVKXIW7GGX6IB377HCD45H5Z/bundle.json","state_url":"https://pith.science/pith/CLWVKXIW7GGX6IB377HCD45H5Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CLWVKXIW7GGX6IB377HCD45H5Z/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":"2026-07-13T19:04:24Z","links":{"resolver":"https://pith.science/pith/CLWVKXIW7GGX6IB377HCD45H5Z","bundle":"https://pith.science/pith/CLWVKXIW7GGX6IB377HCD45H5Z/bundle.json","state":"https://pith.science/pith/CLWVKXIW7GGX6IB377HCD45H5Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CLWVKXIW7GGX6IB377HCD45H5Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CLWVKXIW7GGX6IB377HCD45H5Z","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":"68b4b8464a2897dc3a09d1a87594c0d19715705e0787770e9e9f0ec27e48a5d2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T13:50:11Z","title_canon_sha256":"019cf46187d674d75883592f83fe61f91f076ad0a99673b69e35c685dfd6e83a"},"schema_version":"1.0","source":{"id":"2403.16771","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16771","created_at":"2026-07-05T08:13:31Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16771v2","created_at":"2026-07-05T08:13:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16771","created_at":"2026-07-05T08:13:31Z"},{"alias_kind":"pith_short_12","alias_value":"CLWVKXIW7GGX","created_at":"2026-07-05T08:13:31Z"},{"alias_kind":"pith_short_16","alias_value":"CLWVKXIW7GGX6IB3","created_at":"2026-07-05T08:13:31Z"},{"alias_kind":"pith_short_8","alias_value":"CLWVKXIW","created_at":"2026-07-05T08:13:31Z"}],"graph_snapshots":[{"event_id":"sha256:8aa7b85b56c9c10e8812d19a3ca767a8727ff65ea3760d172edb810a9456d3db","target":"graph","created_at":"2026-07-05T08:13:31Z","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/2403.16771/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The widespread online communication in a modern multilingual world has provided opportunities to blend more than one language (aka code-mixed language) in a single utterance. This has resulted a formidable challenge for the computational models due to the scarcity of annotated data and presence of noise. A potential solution to mitigate the data scarcity problem in low-resource setup is to leverage existing data in resource-rich language through translation. In this paper, we tackle the problem of code-mixed (Hinglish and Bengalish) to English machine translation. First, we synthetically devel","authors_text":"Anoop Kunchukuttan, Kartik Kartik, Md Shad Akhtar, Sanjana Soni, Tanmoy Chakraborty","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T13:50:11Z","title":"Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16771","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":"sha256:7374b96a1ffe41018eb291a83fb19ca5fe43c997452748f0dc94fd211366f04b","target":"record","created_at":"2026-07-05T08:13:31Z","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":"68b4b8464a2897dc3a09d1a87594c0d19715705e0787770e9e9f0ec27e48a5d2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T13:50:11Z","title_canon_sha256":"019cf46187d674d75883592f83fe61f91f076ad0a99673b69e35c685dfd6e83a"},"schema_version":"1.0","source":{"id":"2403.16771","kind":"arxiv","version":2}},"canonical_sha256":"12ed555d16f98d7f203bffce21f3a7ee6de80e2342496e814c71595264c5c065","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12ed555d16f98d7f203bffce21f3a7ee6de80e2342496e814c71595264c5c065","first_computed_at":"2026-07-05T08:13:31.324776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:13:31.324776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iRm9Cz7s/bILdE5AEegh8Hh7u4Mg1xDIyQXmSg2zjXb3X52slIBSGtVhsWgLsCh/eLkGcwo0jyOsQGWvgZu1Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:13:31.325289Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16771","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7374b96a1ffe41018eb291a83fb19ca5fe43c997452748f0dc94fd211366f04b","sha256:8aa7b85b56c9c10e8812d19a3ca767a8727ff65ea3760d172edb810a9456d3db"],"state_sha256":"bae3af90ba1259c50b00ec75a039479617cbcd2c61df314c34428d6283f9fc52"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BC8UOAdQF9ETgdF4rOKftE+ul4kF52jKIJoGfESt2BBTX+k0v/CQveXyqYYXUAKylQ2WJRYT23C+LTbSgM+/AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T19:04:24.130880Z","bundle_sha256":"acad30e72ca05b088882519add2b067d6c8152f7d9a20a320ddac29ae40685ce"}}