{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BVG3AUWZGD62VSRXCDMPVT5UXY","short_pith_number":"pith:BVG3AUWZ","schema_version":"1.0","canonical_sha256":"0d4db052d930fdaaca3710d8facfb4be290f8c9d8068aacfa3bc36801021250f","source":{"kind":"arxiv","id":"2311.04535","version":1},"attestation_state":"computed","paper":{"title":"RankAug: Augmented data ranking for text classification","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Priyam Basu, Tiasa Singha Roy","submitted_at":"2023-11-08T08:47:49Z","abstract_excerpt":"Research on data generation and augmentation has been focused majorly on enhancing generation models, leaving a notable gap in the exploration and refinement of methods for evaluating synthetic data. There are several text similarity metrics within the context of generated data filtering which can impact the performance of specific Natural Language Understanding (NLU) tasks, specifically focusing on intent and sentiment classification. In this study, we propose RankAug, a text-ranking approach that detects and filters out the top augmented texts in terms of being most similar in meaning with l"},"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":"2311.04535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T08:47:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"56c96f80383f734cb175d9480f272f468919225dd86e6efc340f53d70b1eab7d","abstract_canon_sha256":"c724e583edfaa203033d1914906c6d2b77a511d1f971c93be898401e59d6fd69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:37.469994Z","signature_b64":"XqdeuHhkQYFHMLcIElBXrkJkHBKzVc3m6zTy6LtLC72SM95opx9F7y89EDpVWHJj9Zl4nn6o3P5CktCvNkzLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d4db052d930fdaaca3710d8facfb4be290f8c9d8068aacfa3bc36801021250f","last_reissued_at":"2026-07-05T07:10:37.469602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:37.469602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RankAug: Augmented data ranking for text classification","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Priyam Basu, Tiasa Singha Roy","submitted_at":"2023-11-08T08:47:49Z","abstract_excerpt":"Research on data generation and augmentation has been focused majorly on enhancing generation models, leaving a notable gap in the exploration and refinement of methods for evaluating synthetic data. There are several text similarity metrics within the context of generated data filtering which can impact the performance of specific Natural Language Understanding (NLU) tasks, specifically focusing on intent and sentiment classification. In this study, we propose RankAug, a text-ranking approach that detects and filters out the top augmented texts in terms of being most similar in meaning with l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04535","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/2311.04535/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":"2311.04535","created_at":"2026-07-05T07:10:37.469653+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04535v1","created_at":"2026-07-05T07:10:37.469653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04535","created_at":"2026-07-05T07:10:37.469653+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVG3AUWZGD62","created_at":"2026-07-05T07:10:37.469653+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVG3AUWZGD62VSRX","created_at":"2026-07-05T07:10:37.469653+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVG3AUWZ","created_at":"2026-07-05T07:10:37.469653+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/BVG3AUWZGD62VSRXCDMPVT5UXY","json":"https://pith.science/pith/BVG3AUWZGD62VSRXCDMPVT5UXY.json","graph_json":"https://pith.science/api/pith-number/BVG3AUWZGD62VSRXCDMPVT5UXY/graph.json","events_json":"https://pith.science/api/pith-number/BVG3AUWZGD62VSRXCDMPVT5UXY/events.json","paper":"https://pith.science/paper/BVG3AUWZ"},"agent_actions":{"view_html":"https://pith.science/pith/BVG3AUWZGD62VSRXCDMPVT5UXY","download_json":"https://pith.science/pith/BVG3AUWZGD62VSRXCDMPVT5UXY.json","view_paper":"https://pith.science/paper/BVG3AUWZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04535&json=true","fetch_graph":"https://pith.science/api/pith-number/BVG3AUWZGD62VSRXCDMPVT5UXY/graph.json","fetch_events":"https://pith.science/api/pith-number/BVG3AUWZGD62VSRXCDMPVT5UXY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVG3AUWZGD62VSRXCDMPVT5UXY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVG3AUWZGD62VSRXCDMPVT5UXY/action/storage_attestation","attest_author":"https://pith.science/pith/BVG3AUWZGD62VSRXCDMPVT5UXY/action/author_attestation","sign_citation":"https://pith.science/pith/BVG3AUWZGD62VSRXCDMPVT5UXY/action/citation_signature","submit_replication":"https://pith.science/pith/BVG3AUWZGD62VSRXCDMPVT5UXY/action/replication_record"}},"created_at":"2026-07-05T07:10:37.469653+00:00","updated_at":"2026-07-05T07:10:37.469653+00:00"}