{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WMRDAUZOVNLEAVFRQTKWZV26Q5","short_pith_number":"pith:WMRDAUZO","schema_version":"1.0","canonical_sha256":"b32230532eab564054b184d56cd75e876d7a3219b29e27f4f7a82bd02de32aff","source":{"kind":"arxiv","id":"2307.07099","version":3},"attestation_state":"computed","paper":{"title":"Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingbo Shang, Letian Peng, Yuwei Zhang","submitted_at":"2023-07-14T00:10:03Z","abstract_excerpt":"Prompting large language models (LLMs) for data augmentation has recently become a common practice in few-shot NLP tasks. In this paper, we propose Chain-of-Thought Attribute Manipulation (CoTAM), a novel approach that generates new data from existing examples by only tweaking in the user-provided, task-specific attribute, e.g., sentiment polarity or topic in movie reviews. Instead of conventional latent representation controlling, we leverage the chain-of-thought prompting to directly edit the text in three steps, (1) attribute decomposition, (2) manipulation proposal, and (3) sentence recons"},"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":"2307.07099","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-14T00:10:03Z","cross_cats_sorted":[],"title_canon_sha256":"5ac3fa7edaeb1e864b55a4c2142b291c2dd1408ad2e9a1c49bbc03c00a44d906","abstract_canon_sha256":"630426126cb0e5f586c44886729cbc75e4eb5ff4f9d544467867f16829f03363"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:40.031131Z","signature_b64":"R1fGLvyHZKDo7hdUyfkYhjx2dz0nlcpF0To2g9HCY1XKC7VtA48zBEgjgZMU7UpkGl9NZC1RPDCbnc3+15i6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b32230532eab564054b184d56cd75e876d7a3219b29e27f4f7a82bd02de32aff","last_reissued_at":"2026-07-05T08:21:40.030556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:40.030556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingbo Shang, Letian Peng, Yuwei Zhang","submitted_at":"2023-07-14T00:10:03Z","abstract_excerpt":"Prompting large language models (LLMs) for data augmentation has recently become a common practice in few-shot NLP tasks. In this paper, we propose Chain-of-Thought Attribute Manipulation (CoTAM), a novel approach that generates new data from existing examples by only tweaking in the user-provided, task-specific attribute, e.g., sentiment polarity or topic in movie reviews. Instead of conventional latent representation controlling, we leverage the chain-of-thought prompting to directly edit the text in three steps, (1) attribute decomposition, (2) manipulation proposal, and (3) sentence recons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07099","kind":"arxiv","version":3},"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/2307.07099/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":"2307.07099","created_at":"2026-07-05T08:21:40.030615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07099v3","created_at":"2026-07-05T08:21:40.030615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07099","created_at":"2026-07-05T08:21:40.030615+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMRDAUZOVNLE","created_at":"2026-07-05T08:21:40.030615+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMRDAUZOVNLEAVFR","created_at":"2026-07-05T08:21:40.030615+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMRDAUZO","created_at":"2026-07-05T08:21:40.030615+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00672","citing_title":"Toward Edge General Intelligence with Multiple-Large Language Model (Multi-LLM): Architecture, Trust, and Orchestration","ref_index":75,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMRDAUZOVNLEAVFRQTKWZV26Q5","json":"https://pith.science/pith/WMRDAUZOVNLEAVFRQTKWZV26Q5.json","graph_json":"https://pith.science/api/pith-number/WMRDAUZOVNLEAVFRQTKWZV26Q5/graph.json","events_json":"https://pith.science/api/pith-number/WMRDAUZOVNLEAVFRQTKWZV26Q5/events.json","paper":"https://pith.science/paper/WMRDAUZO"},"agent_actions":{"view_html":"https://pith.science/pith/WMRDAUZOVNLEAVFRQTKWZV26Q5","download_json":"https://pith.science/pith/WMRDAUZOVNLEAVFRQTKWZV26Q5.json","view_paper":"https://pith.science/paper/WMRDAUZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07099&json=true","fetch_graph":"https://pith.science/api/pith-number/WMRDAUZOVNLEAVFRQTKWZV26Q5/graph.json","fetch_events":"https://pith.science/api/pith-number/WMRDAUZOVNLEAVFRQTKWZV26Q5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMRDAUZOVNLEAVFRQTKWZV26Q5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMRDAUZOVNLEAVFRQTKWZV26Q5/action/storage_attestation","attest_author":"https://pith.science/pith/WMRDAUZOVNLEAVFRQTKWZV26Q5/action/author_attestation","sign_citation":"https://pith.science/pith/WMRDAUZOVNLEAVFRQTKWZV26Q5/action/citation_signature","submit_replication":"https://pith.science/pith/WMRDAUZOVNLEAVFRQTKWZV26Q5/action/replication_record"}},"created_at":"2026-07-05T08:21:40.030615+00:00","updated_at":"2026-07-05T08:21:40.030615+00:00"}