{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BVG3AUWZGD62VSRXCDMPVT5UXY","short_pith_number":"pith:BVG3AUWZ","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"},"canonical_sha256":"0d4db052d930fdaaca3710d8facfb4be290f8c9d8068aacfa3bc36801021250f","source":{"kind":"arxiv","id":"2311.04535","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04535","created_at":"2026-07-05T07:10:37Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04535v1","created_at":"2026-07-05T07:10:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04535","created_at":"2026-07-05T07:10:37Z"},{"alias_kind":"pith_short_12","alias_value":"BVG3AUWZGD62","created_at":"2026-07-05T07:10:37Z"},{"alias_kind":"pith_short_16","alias_value":"BVG3AUWZGD62VSRX","created_at":"2026-07-05T07:10:37Z"},{"alias_kind":"pith_short_8","alias_value":"BVG3AUWZ","created_at":"2026-07-05T07:10:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BVG3AUWZGD62VSRXCDMPVT5UXY","target":"record","payload":{"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"},"canonical_sha256":"0d4db052d930fdaaca3710d8facfb4be290f8c9d8068aacfa3bc36801021250f","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"},"source_kind":"arxiv","source_id":"2311.04535","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:10:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iA9UwKPCdzn4QIpqLtNCS+sha1aYjHlWiD7MC2Zo58Kid1YbaXhV11B5ggoJpA7uFs4GVGjp7LyfGSLyRAuvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:56:56.974567Z"},"content_sha256":"11666add76dac1e086a16c8477a3c51c31ce900698ec5a7542de52cd4cda2831","schema_version":"1.0","event_id":"sha256:11666add76dac1e086a16c8477a3c51c31ce900698ec5a7542de52cd4cda2831"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BVG3AUWZGD62VSRXCDMPVT5UXY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:10:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8e713HLaUUogT9HQmZhR6poGrSdCK3GNg/L27KNWYU7OnI0+vI2UTGFv7vErU0GdmYYiPumm65fKSEFvOwmTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:56:56.975179Z"},"content_sha256":"b375d616f838a3624651b4e6f9c25aa16f481c0c25aa3d85958c75ceba953d5c","schema_version":"1.0","event_id":"sha256:b375d616f838a3624651b4e6f9c25aa16f481c0c25aa3d85958c75ceba953d5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BVG3AUWZGD62VSRXCDMPVT5UXY/bundle.json","state_url":"https://pith.science/pith/BVG3AUWZGD62VSRXCDMPVT5UXY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BVG3AUWZGD62VSRXCDMPVT5UXY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T05:56:56Z","links":{"resolver":"https://pith.science/pith/BVG3AUWZGD62VSRXCDMPVT5UXY","bundle":"https://pith.science/pith/BVG3AUWZGD62VSRXCDMPVT5UXY/bundle.json","state":"https://pith.science/pith/BVG3AUWZGD62VSRXCDMPVT5UXY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BVG3AUWZGD62VSRXCDMPVT5UXY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BVG3AUWZGD62VSRXCDMPVT5UXY","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":"c724e583edfaa203033d1914906c6d2b77a511d1f971c93be898401e59d6fd69","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T08:47:49Z","title_canon_sha256":"56c96f80383f734cb175d9480f272f468919225dd86e6efc340f53d70b1eab7d"},"schema_version":"1.0","source":{"id":"2311.04535","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04535","created_at":"2026-07-05T07:10:37Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04535v1","created_at":"2026-07-05T07:10:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04535","created_at":"2026-07-05T07:10:37Z"},{"alias_kind":"pith_short_12","alias_value":"BVG3AUWZGD62","created_at":"2026-07-05T07:10:37Z"},{"alias_kind":"pith_short_16","alias_value":"BVG3AUWZGD62VSRX","created_at":"2026-07-05T07:10:37Z"},{"alias_kind":"pith_short_8","alias_value":"BVG3AUWZ","created_at":"2026-07-05T07:10:37Z"}],"graph_snapshots":[{"event_id":"sha256:b375d616f838a3624651b4e6f9c25aa16f481c0c25aa3d85958c75ceba953d5c","target":"graph","created_at":"2026-07-05T07:10:37Z","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/2311.04535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Priyam Basu, Tiasa Singha Roy","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T08:47:49Z","title":"RankAug: Augmented data ranking for text classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04535","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":"sha256:11666add76dac1e086a16c8477a3c51c31ce900698ec5a7542de52cd4cda2831","target":"record","created_at":"2026-07-05T07:10:37Z","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":"c724e583edfaa203033d1914906c6d2b77a511d1f971c93be898401e59d6fd69","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T08:47:49Z","title_canon_sha256":"56c96f80383f734cb175d9480f272f468919225dd86e6efc340f53d70b1eab7d"},"schema_version":"1.0","source":{"id":"2311.04535","kind":"arxiv","version":1}},"canonical_sha256":"0d4db052d930fdaaca3710d8facfb4be290f8c9d8068aacfa3bc36801021250f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d4db052d930fdaaca3710d8facfb4be290f8c9d8068aacfa3bc36801021250f","first_computed_at":"2026-07-05T07:10:37.469602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:37.469602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XqdeuHhkQYFHMLcIElBXrkJkHBKzVc3m6zTy6LtLC72SM95opx9F7y89EDpVWHJj9Zl4nn6o3P5CktCvNkzLDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:37.469994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.04535","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11666add76dac1e086a16c8477a3c51c31ce900698ec5a7542de52cd4cda2831","sha256:b375d616f838a3624651b4e6f9c25aa16f481c0c25aa3d85958c75ceba953d5c"],"state_sha256":"870ba1dab7f07becaa58db1b4cf636faa13dc5a1421a9e8cc557e5008d60c3ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4hg0m5KALJv2NIQsJfzxx1sav5djqF1aZJruDp/POxrJyuyUflSejOH70wC2nR2NQVmxm/h2eJ5rqbV9hiSZAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:56:56.978441Z","bundle_sha256":"84768bd2396aae24b2691dcafbe15ab7a979f4843b85198e479a30e11e6b8c26"}}