{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VLRLGRG6TOV33DEUZFGG7O2ANA","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":"a08b3ca0316b6f31565217b590d9d268ad5153a41b91dc5da4f319f64f483bc9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-30T16:47:06Z","title_canon_sha256":"e6cafe158ebed7f736de044931f9a0b34acff6fbf7da018f4f94a5a2c8251d46"},"schema_version":"1.0","source":{"id":"2404.00415","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00415","created_at":"2026-07-05T08:02:32Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00415v1","created_at":"2026-07-05T08:02:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00415","created_at":"2026-07-05T08:02:32Z"},{"alias_kind":"pith_short_12","alias_value":"VLRLGRG6TOV3","created_at":"2026-07-05T08:02:32Z"},{"alias_kind":"pith_short_16","alias_value":"VLRLGRG6TOV33DEU","created_at":"2026-07-05T08:02:32Z"},{"alias_kind":"pith_short_8","alias_value":"VLRLGRG6","created_at":"2026-07-05T08:02:32Z"}],"graph_snapshots":[{"event_id":"sha256:6fddebb621267aaaae5fc98e59a0bdc87eab01ae9edd62cd7daf55c9f9561c7f","target":"graph","created_at":"2026-07-05T08:02:32Z","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/2404.00415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present CoDa (Constrained Generation based Data Augmentation), a controllable, effective, and training-free data augmentation technique for low-resource (data-scarce) NLP. Our approach is based on prompting off-the-shelf instruction-following Large Language Models (LLMs) for generating text that satisfies a set of constraints. Precisely, we extract a set of simple constraints from every instance in the low-resource dataset and verbalize them to prompt an LLM to generate novel and diverse training instances. Our findings reveal that synthetic data that follows simple constraints in the downs","authors_text":"Chandra Kiran Reddy Evuru, Dinesh Manocha, Ramaneswaran S, Sonal Kumar, Sreyan Ghosh, Utkarsh Tyagi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-30T16:47:06Z","title":"CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00415","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:ebb6c49451bf133ba98f74e8379304edb14737f7ff6f7e421c579f01305a180c","target":"record","created_at":"2026-07-05T08:02:32Z","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":"a08b3ca0316b6f31565217b590d9d268ad5153a41b91dc5da4f319f64f483bc9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-30T16:47:06Z","title_canon_sha256":"e6cafe158ebed7f736de044931f9a0b34acff6fbf7da018f4f94a5a2c8251d46"},"schema_version":"1.0","source":{"id":"2404.00415","kind":"arxiv","version":1}},"canonical_sha256":"aae2b344de9babbd8c94c94c6fbb406807bd608a7ede6693585a3b3f56066687","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aae2b344de9babbd8c94c94c6fbb406807bd608a7ede6693585a3b3f56066687","first_computed_at":"2026-07-05T08:02:32.937356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:32.937356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5EUyHLHh3p7dYgERuSCOujjgePSvrQP7jduBuTEaRb5yaZ56x/se4pO1k6aY3z3eKRI3VrQjloNfPxs53871Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:32.937832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.00415","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebb6c49451bf133ba98f74e8379304edb14737f7ff6f7e421c579f01305a180c","sha256:6fddebb621267aaaae5fc98e59a0bdc87eab01ae9edd62cd7daf55c9f9561c7f"],"state_sha256":"694f04e598c33b11e20783b19f9525fcdc17fb4a13e2bceb6ea25eb869bd87bc"}