{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EREK6QREDCCZQGK67UCM4ZSHKD","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":"0f865f3e666ed4484a2b0443b05689cefaf1ee36dfe2eba55a6ceb3470e4cf99","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-15T15:51:41Z","title_canon_sha256":"d3ee266f524396d589d4e95423747d6c24ab910e16b6f37582c62062262bb339"},"schema_version":"1.0","source":{"id":"2104.07540","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.07540","created_at":"2026-07-05T03:19:43Z"},{"alias_kind":"arxiv_version","alias_value":"2104.07540v3","created_at":"2026-07-05T03:19:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07540","created_at":"2026-07-05T03:19:43Z"},{"alias_kind":"pith_short_12","alias_value":"EREK6QREDCCZ","created_at":"2026-07-05T03:19:43Z"},{"alias_kind":"pith_short_16","alias_value":"EREK6QREDCCZQGK6","created_at":"2026-07-05T03:19:43Z"},{"alias_kind":"pith_short_8","alias_value":"EREK6QRE","created_at":"2026-07-05T03:19:43Z"}],"graph_snapshots":[{"event_id":"sha256:a27befc435f6ce2cb539981a38119d5eb54fa731450fbf9c74535181e6b13be7","target":"graph","created_at":"2026-07-05T03:19:43Z","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/2104.07540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To obtain high-quality sentence embeddings from pretrained language models (PLMs), they must either be augmented with additional pretraining objectives or finetuned on a large set of labeled text pairs. While the latter approach typically outperforms the former, it requires great human effort to generate suitable datasets of sufficient size. In this paper, we show how PLMs can be leveraged to obtain high-quality sentence embeddings without the need for labeled data, finetuning or modifications to the pretraining objective: We utilize the generative abilities of large and high-performing PLMs t","authors_text":"Hinrich Sch\\\"utze, Timo Schick","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-15T15:51:41Z","title":"Generating Datasets with Pretrained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07540","kind":"arxiv","version":3},"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:f4002798897dde00eb9a71f2753367dfe462461755f7a0635561a2efe96bea39","target":"record","created_at":"2026-07-05T03:19:43Z","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":"0f865f3e666ed4484a2b0443b05689cefaf1ee36dfe2eba55a6ceb3470e4cf99","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-15T15:51:41Z","title_canon_sha256":"d3ee266f524396d589d4e95423747d6c24ab910e16b6f37582c62062262bb339"},"schema_version":"1.0","source":{"id":"2104.07540","kind":"arxiv","version":3}},"canonical_sha256":"2448af4224188598195efd04ce664750d8d52711ddd35c24da4a81564a4dfd2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2448af4224188598195efd04ce664750d8d52711ddd35c24da4a81564a4dfd2a","first_computed_at":"2026-07-05T03:19:43.136739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:19:43.136739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rW+BpjtOihWFO8ktX4FDib21kD/wkLpCTIZlksNW754TLMnAoUw7dFINbcK3Tfkw0alnzfIxzf4E7MXiNF4aBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:19:43.137249Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.07540","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4002798897dde00eb9a71f2753367dfe462461755f7a0635561a2efe96bea39","sha256:a27befc435f6ce2cb539981a38119d5eb54fa731450fbf9c74535181e6b13be7"],"state_sha256":"d055aaeb7d0df88ef3b30d56697287e16e4f925d2ea03756932ab83b378ffee8"}