{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:73GDUZNDXKN35SX7YM2JLXGL23","short_pith_number":"pith:73GDUZND","canonical_record":{"source":{"id":"2006.05477","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-09T19:40:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"711a4745369e1ccc2a2f94b95dc3257b30609bc20325c1719317197d183c92bc","abstract_canon_sha256":"d779e892549e1179c87c45d3d95de250a77afa7177864ec16d2100f92f702542"},"schema_version":"1.0"},"canonical_sha256":"fecc3a65a3ba9bbecaffc33495dccbd6d090a6b0d2584228356b88aeb512aee2","source":{"kind":"arxiv","id":"2006.05477","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.05477","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"arxiv_version","alias_value":"2006.05477v1","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05477","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"pith_short_12","alias_value":"73GDUZNDXKN3","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"pith_short_16","alias_value":"73GDUZNDXKN35SX7","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"pith_short_8","alias_value":"73GDUZND","created_at":"2026-07-05T01:09:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:73GDUZNDXKN35SX7YM2JLXGL23","target":"record","payload":{"canonical_record":{"source":{"id":"2006.05477","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-09T19:40:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"711a4745369e1ccc2a2f94b95dc3257b30609bc20325c1719317197d183c92bc","abstract_canon_sha256":"d779e892549e1179c87c45d3d95de250a77afa7177864ec16d2100f92f702542"},"schema_version":"1.0"},"canonical_sha256":"fecc3a65a3ba9bbecaffc33495dccbd6d090a6b0d2584228356b88aeb512aee2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:14.033158Z","signature_b64":"qmAWc7IbtVjYZuzHA628ZJ4GEKMZwxzM5Mx+t5yk4kJVgcfL7t9bArblLkg5IYzsrpztwracG4IkgstVJTuZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fecc3a65a3ba9bbecaffc33495dccbd6d090a6b0d2584228356b88aeb512aee2","last_reissued_at":"2026-07-05T01:09:14.032809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:14.032809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.05477","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":"2026-07-05T01:09:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/IYG0pBRyKr3nE47TwpNoFprP1B+Ww2VYK/fEwoLj4+OiIFyRNzjCZGD9JjOyEtqgd/srCoFhIQyt6ChtIvwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:14:04.040725Z"},"content_sha256":"86d6de1405f6f2ed9cc8c1f5903667eacb0c7ab5f79b577a175955339bfd3579","schema_version":"1.0","event_id":"sha256:86d6de1405f6f2ed9cc8c1f5903667eacb0c7ab5f79b577a175955339bfd3579"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:73GDUZNDXKN35SX7YM2JLXGL23","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Paraphrase Generation using Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chaitra Hegde, Shrikumar Patil","submitted_at":"2020-06-09T19:40:19Z","abstract_excerpt":"Large scale Pre-trained Language Models have proven to be very powerful approach in various Natural language tasks. OpenAI's GPT-2 \\cite{radford2019language} is notable for its capability to generate fluent, well formulated, grammatically consistent text and for phrase completions. In this paper we leverage this generation capability of GPT-2 to generate paraphrases without any supervision from labelled data. We examine how the results compare with other supervised and unsupervised approaches and the effect of using paraphrases for data augmentation on downstream tasks such as classification. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05477","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/2006.05477/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":"2026-07-05T01:09:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zG5BVwQCVMP1/ssQIPW9ZBJHQQLZJdtdxpvNlwc6xKXYkRqmOAD136eAtUzsFeSkU3iVA5chJguvBl68YpIgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:14:04.041696Z"},"content_sha256":"9931664e38c43d99d961a097a4ed4671cc16efbb63adeb40219b6089b458ab43","schema_version":"1.0","event_id":"sha256:9931664e38c43d99d961a097a4ed4671cc16efbb63adeb40219b6089b458ab43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/73GDUZNDXKN35SX7YM2JLXGL23/bundle.json","state_url":"https://pith.science/pith/73GDUZNDXKN35SX7YM2JLXGL23/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/73GDUZNDXKN35SX7YM2JLXGL23/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":"2026-08-08T11:14:04Z","links":{"resolver":"https://pith.science/pith/73GDUZNDXKN35SX7YM2JLXGL23","bundle":"https://pith.science/pith/73GDUZNDXKN35SX7YM2JLXGL23/bundle.json","state":"https://pith.science/pith/73GDUZNDXKN35SX7YM2JLXGL23/state.json","well_known_bundle":"https://pith.science/.well-known/pith/73GDUZNDXKN35SX7YM2JLXGL23/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:73GDUZNDXKN35SX7YM2JLXGL23","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":"d779e892549e1179c87c45d3d95de250a77afa7177864ec16d2100f92f702542","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-09T19:40:19Z","title_canon_sha256":"711a4745369e1ccc2a2f94b95dc3257b30609bc20325c1719317197d183c92bc"},"schema_version":"1.0","source":{"id":"2006.05477","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.05477","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"arxiv_version","alias_value":"2006.05477v1","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05477","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"pith_short_12","alias_value":"73GDUZNDXKN3","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"pith_short_16","alias_value":"73GDUZNDXKN35SX7","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"pith_short_8","alias_value":"73GDUZND","created_at":"2026-07-05T01:09:14Z"}],"graph_snapshots":[{"event_id":"sha256:9931664e38c43d99d961a097a4ed4671cc16efbb63adeb40219b6089b458ab43","target":"graph","created_at":"2026-07-05T01:09:14Z","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/2006.05477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large scale Pre-trained Language Models have proven to be very powerful approach in various Natural language tasks. OpenAI's GPT-2 \\cite{radford2019language} is notable for its capability to generate fluent, well formulated, grammatically consistent text and for phrase completions. In this paper we leverage this generation capability of GPT-2 to generate paraphrases without any supervision from labelled data. We examine how the results compare with other supervised and unsupervised approaches and the effect of using paraphrases for data augmentation on downstream tasks such as classification. ","authors_text":"Chaitra Hegde, Shrikumar Patil","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-09T19:40:19Z","title":"Unsupervised Paraphrase Generation using Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05477","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":"sha256:86d6de1405f6f2ed9cc8c1f5903667eacb0c7ab5f79b577a175955339bfd3579","target":"record","created_at":"2026-07-05T01:09:14Z","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":"d779e892549e1179c87c45d3d95de250a77afa7177864ec16d2100f92f702542","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-09T19:40:19Z","title_canon_sha256":"711a4745369e1ccc2a2f94b95dc3257b30609bc20325c1719317197d183c92bc"},"schema_version":"1.0","source":{"id":"2006.05477","kind":"arxiv","version":1}},"canonical_sha256":"fecc3a65a3ba9bbecaffc33495dccbd6d090a6b0d2584228356b88aeb512aee2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fecc3a65a3ba9bbecaffc33495dccbd6d090a6b0d2584228356b88aeb512aee2","first_computed_at":"2026-07-05T01:09:14.032809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:14.032809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qmAWc7IbtVjYZuzHA628ZJ4GEKMZwxzM5Mx+t5yk4kJVgcfL7t9bArblLkg5IYzsrpztwracG4IkgstVJTuZDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:14.033158Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.05477","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86d6de1405f6f2ed9cc8c1f5903667eacb0c7ab5f79b577a175955339bfd3579","sha256:9931664e38c43d99d961a097a4ed4671cc16efbb63adeb40219b6089b458ab43"],"state_sha256":"20e353d503ef0274fa246c402976b38c3e91933666d2927d79a8f8bb419ba362"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MKI6+kPMAeBgQuCd31VG3IRREzNcTzjNk7nHgHlvgW8S2Xg1aV8EdLXNUb0Y55lqwmMoBtxIyx8BKwkbfzODAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:14:04.047752Z","bundle_sha256":"5fce4f61269e735ad2452f20b5f7afa98acaee1dd2a9fb53f51a7ab8e65d814b"}}