{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VLRLGRG6TOV33DEUZFGG7O2ANA","short_pith_number":"pith:VLRLGRG6","schema_version":"1.0","canonical_sha256":"aae2b344de9babbd8c94c94c6fbb406807bd608a7ede6693585a3b3f56066687","source":{"kind":"arxiv","id":"2404.00415","version":1},"attestation_state":"computed","paper":{"title":"CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chandra Kiran Reddy Evuru, Dinesh Manocha, Ramaneswaran S, Sonal Kumar, Sreyan Ghosh, Utkarsh Tyagi","submitted_at":"2024-03-30T16:47:06Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.00415","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-30T16:47:06Z","cross_cats_sorted":[],"title_canon_sha256":"e6cafe158ebed7f736de044931f9a0b34acff6fbf7da018f4f94a5a2c8251d46","abstract_canon_sha256":"a08b3ca0316b6f31565217b590d9d268ad5153a41b91dc5da4f319f64f483bc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:32.937832Z","signature_b64":"5EUyHLHh3p7dYgERuSCOujjgePSvrQP7jduBuTEaRb5yaZ56x/se4pO1k6aY3z3eKRI3VrQjloNfPxs53871Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aae2b344de9babbd8c94c94c6fbb406807bd608a7ede6693585a3b3f56066687","last_reissued_at":"2026-07-05T08:02:32.937356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:32.937356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chandra Kiran Reddy Evuru, Dinesh Manocha, Ramaneswaran S, Sonal Kumar, Sreyan Ghosh, Utkarsh Tyagi","submitted_at":"2024-03-30T16:47:06Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00415","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/2404.00415/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.00415","created_at":"2026-07-05T08:02:32.937415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00415v1","created_at":"2026-07-05T08:02:32.937415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00415","created_at":"2026-07-05T08:02:32.937415+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLRLGRG6TOV3","created_at":"2026-07-05T08:02:32.937415+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLRLGRG6TOV33DEU","created_at":"2026-07-05T08:02:32.937415+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLRLGRG6","created_at":"2026-07-05T08:02:32.937415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08512","citing_title":"Measuring Diversity in Synthetic Datasets","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLRLGRG6TOV33DEUZFGG7O2ANA","json":"https://pith.science/pith/VLRLGRG6TOV33DEUZFGG7O2ANA.json","graph_json":"https://pith.science/api/pith-number/VLRLGRG6TOV33DEUZFGG7O2ANA/graph.json","events_json":"https://pith.science/api/pith-number/VLRLGRG6TOV33DEUZFGG7O2ANA/events.json","paper":"https://pith.science/paper/VLRLGRG6"},"agent_actions":{"view_html":"https://pith.science/pith/VLRLGRG6TOV33DEUZFGG7O2ANA","download_json":"https://pith.science/pith/VLRLGRG6TOV33DEUZFGG7O2ANA.json","view_paper":"https://pith.science/paper/VLRLGRG6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00415&json=true","fetch_graph":"https://pith.science/api/pith-number/VLRLGRG6TOV33DEUZFGG7O2ANA/graph.json","fetch_events":"https://pith.science/api/pith-number/VLRLGRG6TOV33DEUZFGG7O2ANA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLRLGRG6TOV33DEUZFGG7O2ANA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLRLGRG6TOV33DEUZFGG7O2ANA/action/storage_attestation","attest_author":"https://pith.science/pith/VLRLGRG6TOV33DEUZFGG7O2ANA/action/author_attestation","sign_citation":"https://pith.science/pith/VLRLGRG6TOV33DEUZFGG7O2ANA/action/citation_signature","submit_replication":"https://pith.science/pith/VLRLGRG6TOV33DEUZFGG7O2ANA/action/replication_record"}},"created_at":"2026-07-05T08:02:32.937415+00:00","updated_at":"2026-07-05T08:02:32.937415+00:00"}