{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YFKS77Q5NA36A5R7EQ57WS3A6J","short_pith_number":"pith:YFKS77Q5","schema_version":"1.0","canonical_sha256":"c1552ffe1d6837e0763f243bfb4b60f2622092c550c4e0dccafe252c4016bd3d","source":{"kind":"arxiv","id":"2302.12784","version":1},"attestation_state":"computed","paper":{"title":"STA: Self-controlled Text Augmentation for Improving Text Classifications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Congcong Wang, Gonzalo Fiz Pontiveros, Steven Derby, Tri Kurniawan Wijaya","submitted_at":"2023-02-24T17:54:12Z","abstract_excerpt":"Despite recent advancements in Machine Learning, many tasks still involve working in low-data regimes which can make solving natural language problems difficult. Recently, a number of text augmentation techniques have emerged in the field of Natural Language Processing (NLP) which can enrich the training data with new examples, though they are not without their caveats. For instance, simple rule-based heuristic methods are effective, but lack variation in semantic content and syntactic structure with respect to the original text. On the other hand, more complex deep learning approaches can cau"},"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":"2302.12784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-24T17:54:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6d279a0768e8af306fd1de8fc8741538e734cfdab646f92388d6d95631832d0d","abstract_canon_sha256":"07ebb45c20673c3d796f6fc20d6bf3eb8e18f08b5b0ddb3b1753c5b7b0fe8842"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:21.173768Z","signature_b64":"QUdd3tq7f+H5XD+cuIQ+4GHTBVUqM0tS3PhNX9mHWrqioIB+oFvjI255LH17qkJbIvKto5EOihsTTA+MgqewAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1552ffe1d6837e0763f243bfb4b60f2622092c550c4e0dccafe252c4016bd3d","last_reissued_at":"2026-07-05T05:45:21.173352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:21.173352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STA: Self-controlled Text Augmentation for Improving Text Classifications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Congcong Wang, Gonzalo Fiz Pontiveros, Steven Derby, Tri Kurniawan Wijaya","submitted_at":"2023-02-24T17:54:12Z","abstract_excerpt":"Despite recent advancements in Machine Learning, many tasks still involve working in low-data regimes which can make solving natural language problems difficult. Recently, a number of text augmentation techniques have emerged in the field of Natural Language Processing (NLP) which can enrich the training data with new examples, though they are not without their caveats. For instance, simple rule-based heuristic methods are effective, but lack variation in semantic content and syntactic structure with respect to the original text. On the other hand, more complex deep learning approaches can cau"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12784","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/2302.12784/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":"2302.12784","created_at":"2026-07-05T05:45:21.173409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12784v1","created_at":"2026-07-05T05:45:21.173409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12784","created_at":"2026-07-05T05:45:21.173409+00:00"},{"alias_kind":"pith_short_12","alias_value":"YFKS77Q5NA36","created_at":"2026-07-05T05:45:21.173409+00:00"},{"alias_kind":"pith_short_16","alias_value":"YFKS77Q5NA36A5R7","created_at":"2026-07-05T05:45:21.173409+00:00"},{"alias_kind":"pith_short_8","alias_value":"YFKS77Q5","created_at":"2026-07-05T05:45:21.173409+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YFKS77Q5NA36A5R7EQ57WS3A6J","json":"https://pith.science/pith/YFKS77Q5NA36A5R7EQ57WS3A6J.json","graph_json":"https://pith.science/api/pith-number/YFKS77Q5NA36A5R7EQ57WS3A6J/graph.json","events_json":"https://pith.science/api/pith-number/YFKS77Q5NA36A5R7EQ57WS3A6J/events.json","paper":"https://pith.science/paper/YFKS77Q5"},"agent_actions":{"view_html":"https://pith.science/pith/YFKS77Q5NA36A5R7EQ57WS3A6J","download_json":"https://pith.science/pith/YFKS77Q5NA36A5R7EQ57WS3A6J.json","view_paper":"https://pith.science/paper/YFKS77Q5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12784&json=true","fetch_graph":"https://pith.science/api/pith-number/YFKS77Q5NA36A5R7EQ57WS3A6J/graph.json","fetch_events":"https://pith.science/api/pith-number/YFKS77Q5NA36A5R7EQ57WS3A6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YFKS77Q5NA36A5R7EQ57WS3A6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YFKS77Q5NA36A5R7EQ57WS3A6J/action/storage_attestation","attest_author":"https://pith.science/pith/YFKS77Q5NA36A5R7EQ57WS3A6J/action/author_attestation","sign_citation":"https://pith.science/pith/YFKS77Q5NA36A5R7EQ57WS3A6J/action/citation_signature","submit_replication":"https://pith.science/pith/YFKS77Q5NA36A5R7EQ57WS3A6J/action/replication_record"}},"created_at":"2026-07-05T05:45:21.173409+00:00","updated_at":"2026-07-05T05:45:21.173409+00:00"}