{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IPJUPJ6I5VUYCZR4HTVW5VLC7B","short_pith_number":"pith:IPJUPJ6I","canonical_record":{"source":{"id":"2012.02952","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-05T05:21:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"891ee35baf4b06b12a001b87140093791229fe77c68ef2333d5b149d45c9498c","abstract_canon_sha256":"6731906d931f216e8f537154d214cd063fbd6e8afbf8a6b1e87a6c365c4b1961"},"schema_version":"1.0"},"canonical_sha256":"43d347a7c8ed6981663c3ceb6ed562f85aecafc53fe80573d2510a55815b50be","source":{"kind":"arxiv","id":"2012.02952","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02952","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02952v1","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02952","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"pith_short_12","alias_value":"IPJUPJ6I5VUY","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"pith_short_16","alias_value":"IPJUPJ6I5VUYCZR4","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"pith_short_8","alias_value":"IPJUPJ6I","created_at":"2026-07-05T01:57:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IPJUPJ6I5VUYCZR4HTVW5VLC7B","target":"record","payload":{"canonical_record":{"source":{"id":"2012.02952","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-05T05:21:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"891ee35baf4b06b12a001b87140093791229fe77c68ef2333d5b149d45c9498c","abstract_canon_sha256":"6731906d931f216e8f537154d214cd063fbd6e8afbf8a6b1e87a6c365c4b1961"},"schema_version":"1.0"},"canonical_sha256":"43d347a7c8ed6981663c3ceb6ed562f85aecafc53fe80573d2510a55815b50be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:24.203837Z","signature_b64":"aJWPRY8A9oXA3V8eKBgAGv3dchxOzlQuH+F3CppDeuUNbBsVttLs+nIHF9s26ptwy66u8E25GE3y5Uxs2eHgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43d347a7c8ed6981663c3ceb6ed562f85aecafc53fe80573d2510a55815b50be","last_reissued_at":"2026-07-05T01:57:24.203295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:24.203295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.02952","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":"2026-07-05T01:57:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I3cBuklExCaJsBpfwCW7rXZ5cO5G4/Z1sBdDjYnYG2mO3om9vBIGZ9/NIBJh1v2TAd6lw/gOLP19zH9J1SzyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T18:14:16.161273Z"},"content_sha256":"8c64837e114729f1028ce7740bd36842bd7bbf539ebac7f9e166036de0a68729","schema_version":"1.0","event_id":"sha256:8c64837e114729f1028ce7740bd36842bd7bbf539ebac7f9e166036de0a68729"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IPJUPJ6I5VUYCZR4HTVW5VLC7B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenyan Jia, Guangxuan Xu, Lili Wang, Ruibo Liu, Soroush Vosoughi, Weicheng Ma","submitted_at":"2020-12-05T05:21:57Z","abstract_excerpt":"Data augmentation is proven to be effective in many NLU tasks, especially for those suffering from data scarcity. In this paper, we present a powerful and easy to deploy text augmentation framework, Data Boost, which augments data through reinforcement learning guided conditional generation. We evaluate Data Boost on three diverse text classification tasks under five different classifier architectures. The result shows that Data Boost can boost the performance of classifiers especially in low-resource data scenarios. For instance, Data Boost improves F1 for the three tasks by 8.7% on average w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02952","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/2012.02952/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":"2026-07-05T01:57:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ju9OgrmhNGcRlnz68LSUAHwPTTPZs71YX9+au5VajqxmSIIjQshY1uO0URxDWiQJSVQ10riOsKX2htcdQH2ACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T18:14:16.161675Z"},"content_sha256":"0fa75465153b60b2161479b5dd5bb43345f8816b2f273cda3393cf0e2c2c0de8","schema_version":"1.0","event_id":"sha256:0fa75465153b60b2161479b5dd5bb43345f8816b2f273cda3393cf0e2c2c0de8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IPJUPJ6I5VUYCZR4HTVW5VLC7B/bundle.json","state_url":"https://pith.science/pith/IPJUPJ6I5VUYCZR4HTVW5VLC7B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IPJUPJ6I5VUYCZR4HTVW5VLC7B/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":"2026-07-26T18:14:16Z","links":{"resolver":"https://pith.science/pith/IPJUPJ6I5VUYCZR4HTVW5VLC7B","bundle":"https://pith.science/pith/IPJUPJ6I5VUYCZR4HTVW5VLC7B/bundle.json","state":"https://pith.science/pith/IPJUPJ6I5VUYCZR4HTVW5VLC7B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IPJUPJ6I5VUYCZR4HTVW5VLC7B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IPJUPJ6I5VUYCZR4HTVW5VLC7B","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":"6731906d931f216e8f537154d214cd063fbd6e8afbf8a6b1e87a6c365c4b1961","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-05T05:21:57Z","title_canon_sha256":"891ee35baf4b06b12a001b87140093791229fe77c68ef2333d5b149d45c9498c"},"schema_version":"1.0","source":{"id":"2012.02952","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02952","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02952v1","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02952","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"pith_short_12","alias_value":"IPJUPJ6I5VUY","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"pith_short_16","alias_value":"IPJUPJ6I5VUYCZR4","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"pith_short_8","alias_value":"IPJUPJ6I","created_at":"2026-07-05T01:57:24Z"}],"graph_snapshots":[{"event_id":"sha256:0fa75465153b60b2161479b5dd5bb43345f8816b2f273cda3393cf0e2c2c0de8","target":"graph","created_at":"2026-07-05T01:57:24Z","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/2012.02952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data augmentation is proven to be effective in many NLU tasks, especially for those suffering from data scarcity. In this paper, we present a powerful and easy to deploy text augmentation framework, Data Boost, which augments data through reinforcement learning guided conditional generation. We evaluate Data Boost on three diverse text classification tasks under five different classifier architectures. The result shows that Data Boost can boost the performance of classifiers especially in low-resource data scenarios. For instance, Data Boost improves F1 for the three tasks by 8.7% on average w","authors_text":"Chenyan Jia, Guangxuan Xu, Lili Wang, Ruibo Liu, Soroush Vosoughi, Weicheng Ma","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-05T05:21:57Z","title":"Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02952","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":"sha256:8c64837e114729f1028ce7740bd36842bd7bbf539ebac7f9e166036de0a68729","target":"record","created_at":"2026-07-05T01:57:24Z","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":"6731906d931f216e8f537154d214cd063fbd6e8afbf8a6b1e87a6c365c4b1961","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-05T05:21:57Z","title_canon_sha256":"891ee35baf4b06b12a001b87140093791229fe77c68ef2333d5b149d45c9498c"},"schema_version":"1.0","source":{"id":"2012.02952","kind":"arxiv","version":1}},"canonical_sha256":"43d347a7c8ed6981663c3ceb6ed562f85aecafc53fe80573d2510a55815b50be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43d347a7c8ed6981663c3ceb6ed562f85aecafc53fe80573d2510a55815b50be","first_computed_at":"2026-07-05T01:57:24.203295Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:57:24.203295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aJWPRY8A9oXA3V8eKBgAGv3dchxOzlQuH+F3CppDeuUNbBsVttLs+nIHF9s26ptwy66u8E25GE3y5Uxs2eHgCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:57:24.203837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.02952","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c64837e114729f1028ce7740bd36842bd7bbf539ebac7f9e166036de0a68729","sha256:0fa75465153b60b2161479b5dd5bb43345f8816b2f273cda3393cf0e2c2c0de8"],"state_sha256":"9850d8ec48118f276879761c8e31eb1d3ba265a2b34a60021d57f37d6151e24b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K31wls18PIBWprkbFJtuCZK9/n1VH0/hmXIcNVujeA4/2s1Q2SF8x1z99ufKri0iiL0JQ981NTelus/3iorWBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T18:14:16.163985Z","bundle_sha256":"cfc66b96f8433550521b1925c49a80d92b7499160b132ee5c4963a7d72a39386"}}