{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QDT6BMMEZPTEVUAC3PRXJM52NA","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":"db07f45681bece674d158c148fe58a52f6b7a356157ef27a844cb93ae43063d1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T00:50:49Z","title_canon_sha256":"d1a808ce9f3a8f3fe7aba4c9b86cee041542025921258416b453cfe9c10d73b6"},"schema_version":"1.0","source":{"id":"2505.12587","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12587","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12587v1","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12587","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"QDT6BMMEZPTE","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"QDT6BMMEZPTEVUAC","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"QDT6BMME","created_at":"2026-07-05T11:05:06Z"}],"graph_snapshots":[{"event_id":"sha256:8bcecd7e180ae9b74b38a6fc73dfe8e353b5034ef526db60178d250e58a25cd1","target":"graph","created_at":"2026-07-05T11:05:06Z","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/2505.12587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code-mixed languages, characterized by frequent within-sentence language transitions, present structural challenges that standard language models fail to address. In this work, we propose CMLFormer, an enhanced multi-layer dual-decoder Transformer with a shared encoder and synchronized decoder cross-attention, designed to model the linguistic and semantic dynamics of code-mixed text. CMLFormer is pre-trained on an augmented Hinglish corpus with switching point and translation annotations with multiple new objectives specifically aimed at capturing switching behavior, cross-lingual structure, a","authors_text":"Aditeya Baral, Allen George Ajith, Mrityunjay Abhijeet Bhanja, Roshan Nayak","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T00:50:49Z","title":"CMLFormer: A Dual Decoder Transformer with Switching Point Learning for Code-Mixed Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12587","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":"sha256:9013464c0d43db3a5d0cf42d5dadd4359cf8602a4281080ed68de391800ea41d","target":"record","created_at":"2026-07-05T11:05:06Z","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":"db07f45681bece674d158c148fe58a52f6b7a356157ef27a844cb93ae43063d1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T00:50:49Z","title_canon_sha256":"d1a808ce9f3a8f3fe7aba4c9b86cee041542025921258416b453cfe9c10d73b6"},"schema_version":"1.0","source":{"id":"2505.12587","kind":"arxiv","version":1}},"canonical_sha256":"80e7e0b184cbe64ad002dbe374b3ba6826a1e07857b3f9461e2607f8c95f6131","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80e7e0b184cbe64ad002dbe374b3ba6826a1e07857b3f9461e2607f8c95f6131","first_computed_at":"2026-07-05T11:05:06.466410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:06.466410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LIb8GSEueXadnrsZmZvdS2LFixYNVwepQDWTJTyDWZoBdr8qJxX9ZVtQ+1uV1tV4Nl29Yr6FDM5v+4e3GRFkCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:06.467108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12587","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9013464c0d43db3a5d0cf42d5dadd4359cf8602a4281080ed68de391800ea41d","sha256:8bcecd7e180ae9b74b38a6fc73dfe8e353b5034ef526db60178d250e58a25cd1"],"state_sha256":"fd7a20b29f4131795e898bff74349439c3d97fd80cf353ada7af21e68559488f"}