{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BS67I6TOV7BFW7DY6RAYVEJ6G2","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":"df51c64d7aad8984dea175173bd4d2efdb9eeb597907e84cf79a6bbda7750cce","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-17T21:35:56Z","title_canon_sha256":"c008fcf9d14b83b5ab5c32da510bb5c8eddb0875231472eeb426346a4cfa427c"},"schema_version":"1.0","source":{"id":"2202.08904","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.08904","created_at":"2026-07-05T04:46:13Z"},{"alias_kind":"arxiv_version","alias_value":"2202.08904v5","created_at":"2026-07-05T04:46:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.08904","created_at":"2026-07-05T04:46:13Z"},{"alias_kind":"pith_short_12","alias_value":"BS67I6TOV7BF","created_at":"2026-07-05T04:46:13Z"},{"alias_kind":"pith_short_16","alias_value":"BS67I6TOV7BFW7DY","created_at":"2026-07-05T04:46:13Z"},{"alias_kind":"pith_short_8","alias_value":"BS67I6TO","created_at":"2026-07-05T04:46:13Z"}],"graph_snapshots":[{"event_id":"sha256:5fe5f4f793a84aba505c48a1b88a3de0771644db60cda5f436589ecf07a45f3b","target":"graph","created_at":"2026-07-05T04:46:13Z","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/2202.08904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Decoder transformers have continued increasing in scale reaching hundreds of billions of parameters. Due to their scale the same decoder sets state-of-the-art results on various language tasks via prompting or fine-tuning. Yet, these large foundation models remain unusable for the related fields of semantic search and sentence embeddings. This prevents possibly new state-of-the-art results and forces organizations to train and maintain separate models. To this end, we propose SGPT to use decoders for sentence embeddings and semantic search via prompting or fine-tuning. At 5.8 billion parameter","authors_text":"Niklas Muennighoff","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.08904","kind":"arxiv","version":5},"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":"sha256:072523579680dc2eecdcf866fb103cd5bdbf88d9ea2a152e10fe0cc3ae53b025","target":"record","created_at":"2026-07-05T04:46:13Z","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":"df51c64d7aad8984dea175173bd4d2efdb9eeb597907e84cf79a6bbda7750cce","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-17T21:35:56Z","title_canon_sha256":"c008fcf9d14b83b5ab5c32da510bb5c8eddb0875231472eeb426346a4cfa427c"},"schema_version":"1.0","source":{"id":"2202.08904","kind":"arxiv","version":5}},"canonical_sha256":"0cbdf47a6eafc25b7c78f4418a913e3695e5077d83ee737c4c5ec10c156032ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cbdf47a6eafc25b7c78f4418a913e3695e5077d83ee737c4c5ec10c156032ff","first_computed_at":"2026-07-05T04:46:13.618305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:13.618305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qGSXhhCXtN5Tnwt2czleDMyUj+8U2n/CVLW47F11uT/Kgb5EFtk0ig5eaDy4SiSh0dlM/lW/hoTZIR5oAohwCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:13.618774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.08904","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:072523579680dc2eecdcf866fb103cd5bdbf88d9ea2a152e10fe0cc3ae53b025","sha256:5fe5f4f793a84aba505c48a1b88a3de0771644db60cda5f436589ecf07a45f3b"],"state_sha256":"6df32a0a3a2ab28d2b6e928451dd2b2a658e9a115ff60af0cd4c54d54e53bf51"}