{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YOMD7RN5Y6K7X6KSLOLQ7PVZ35","short_pith_number":"pith:YOMD7RN5","canonical_record":{"source":{"id":"2401.00368","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-31T02:13:18Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"473e5d8e407bffe817af66bd6c8f10eed39d33abfd5f4f2be70e6639f8324c4f","abstract_canon_sha256":"0caca6f2a6a5a4a1ca775e22ab32b85f403fcdda060cf9b9a4a7541e18775f11"},"schema_version":"1.0"},"canonical_sha256":"c3983fc5bdc795fbf9525b970fbeb9df7b251f2fde23741abc2a144cf30205ae","source":{"kind":"arxiv","id":"2401.00368","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00368","created_at":"2026-07-05T08:25:30Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00368v3","created_at":"2026-07-05T08:25:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00368","created_at":"2026-07-05T08:25:30Z"},{"alias_kind":"pith_short_12","alias_value":"YOMD7RN5Y6K7","created_at":"2026-07-05T08:25:30Z"},{"alias_kind":"pith_short_16","alias_value":"YOMD7RN5Y6K7X6KS","created_at":"2026-07-05T08:25:30Z"},{"alias_kind":"pith_short_8","alias_value":"YOMD7RN5","created_at":"2026-07-05T08:25:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YOMD7RN5Y6K7X6KSLOLQ7PVZ35","target":"record","payload":{"canonical_record":{"source":{"id":"2401.00368","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-31T02:13:18Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"473e5d8e407bffe817af66bd6c8f10eed39d33abfd5f4f2be70e6639f8324c4f","abstract_canon_sha256":"0caca6f2a6a5a4a1ca775e22ab32b85f403fcdda060cf9b9a4a7541e18775f11"},"schema_version":"1.0"},"canonical_sha256":"c3983fc5bdc795fbf9525b970fbeb9df7b251f2fde23741abc2a144cf30205ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:30.825080Z","signature_b64":"FHQn/EjjCyErAf222T5zJ3tZlMn+fpisthCwASNgu7iaa32Q+i5Y3qgBOdPo7i5JWx8jyfpL+jvJZpUA5z7PCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3983fc5bdc795fbf9525b970fbeb9df7b251f2fde23741abc2a144cf30205ae","last_reissued_at":"2026-07-05T08:25:30.824616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:30.824616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.00368","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v8Qb6wvaqShY52kHBd940DQikL+f+1S69sr0nbr2mJBanekw5k5r1XatasYrbXGOL+k1U6lDPDGqnM5PlIXiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:52:32.678620Z"},"content_sha256":"230c577af51fbfa6061db46081fa44209ee75037fd988b579026ecfa5379cf7e","schema_version":"1.0","event_id":"sha256:230c577af51fbfa6061db46081fa44209ee75037fd988b579026ecfa5379cf7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YOMD7RN5Y6K7X6KSLOLQ7PVZ35","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Text Embeddings with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Liang Wang, Linjun Yang, Nan Yang, Rangan Majumder, Xiaolong Huang","submitted_at":"2023-12-31T02:13:18Z","abstract_excerpt":"In this paper, we introduce a novel and simple method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps. Unlike existing methods that often depend on multi-stage intermediate pre-training with billions of weakly-supervised text pairs, followed by fine-tuning with a few labeled datasets, our method does not require building complex training pipelines or relying on manually collected datasets that are often constrained by task diversity and language coverage. We leverage proprietary LLMs to generate diverse synthetic data for hundreds of thousan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00368","kind":"arxiv","version":3},"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/2401.00368/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":"2026-07-05T08:25:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7GQGY8hLT8rxBs34DyIycRunBrMRRg4MZxG39h2gmCmXRX6WGroeZffxOdQweK2mjztfzJF6Q475XVi1JshPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:52:32.679114Z"},"content_sha256":"fa716724b3b040f1b9ae90c3fde86e72b0c9c092233719bd0a6bfd33bf503e54","schema_version":"1.0","event_id":"sha256:fa716724b3b040f1b9ae90c3fde86e72b0c9c092233719bd0a6bfd33bf503e54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YOMD7RN5Y6K7X6KSLOLQ7PVZ35/bundle.json","state_url":"https://pith.science/pith/YOMD7RN5Y6K7X6KSLOLQ7PVZ35/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YOMD7RN5Y6K7X6KSLOLQ7PVZ35/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":"2026-08-05T09:52:32Z","links":{"resolver":"https://pith.science/pith/YOMD7RN5Y6K7X6KSLOLQ7PVZ35","bundle":"https://pith.science/pith/YOMD7RN5Y6K7X6KSLOLQ7PVZ35/bundle.json","state":"https://pith.science/pith/YOMD7RN5Y6K7X6KSLOLQ7PVZ35/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YOMD7RN5Y6K7X6KSLOLQ7PVZ35/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YOMD7RN5Y6K7X6KSLOLQ7PVZ35","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":"0caca6f2a6a5a4a1ca775e22ab32b85f403fcdda060cf9b9a4a7541e18775f11","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-31T02:13:18Z","title_canon_sha256":"473e5d8e407bffe817af66bd6c8f10eed39d33abfd5f4f2be70e6639f8324c4f"},"schema_version":"1.0","source":{"id":"2401.00368","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00368","created_at":"2026-07-05T08:25:30Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00368v3","created_at":"2026-07-05T08:25:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00368","created_at":"2026-07-05T08:25:30Z"},{"alias_kind":"pith_short_12","alias_value":"YOMD7RN5Y6K7","created_at":"2026-07-05T08:25:30Z"},{"alias_kind":"pith_short_16","alias_value":"YOMD7RN5Y6K7X6KS","created_at":"2026-07-05T08:25:30Z"},{"alias_kind":"pith_short_8","alias_value":"YOMD7RN5","created_at":"2026-07-05T08:25:30Z"}],"graph_snapshots":[{"event_id":"sha256:fa716724b3b040f1b9ae90c3fde86e72b0c9c092233719bd0a6bfd33bf503e54","target":"graph","created_at":"2026-07-05T08:25:30Z","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/2401.00368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce a novel and simple method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps. Unlike existing methods that often depend on multi-stage intermediate pre-training with billions of weakly-supervised text pairs, followed by fine-tuning with a few labeled datasets, our method does not require building complex training pipelines or relying on manually collected datasets that are often constrained by task diversity and language coverage. We leverage proprietary LLMs to generate diverse synthetic data for hundreds of thousan","authors_text":"Furu Wei, Liang Wang, Linjun Yang, Nan Yang, Rangan Majumder, Xiaolong Huang","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-31T02:13:18Z","title":"Improving Text Embeddings with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00368","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":"sha256:230c577af51fbfa6061db46081fa44209ee75037fd988b579026ecfa5379cf7e","target":"record","created_at":"2026-07-05T08:25:30Z","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":"0caca6f2a6a5a4a1ca775e22ab32b85f403fcdda060cf9b9a4a7541e18775f11","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-31T02:13:18Z","title_canon_sha256":"473e5d8e407bffe817af66bd6c8f10eed39d33abfd5f4f2be70e6639f8324c4f"},"schema_version":"1.0","source":{"id":"2401.00368","kind":"arxiv","version":3}},"canonical_sha256":"c3983fc5bdc795fbf9525b970fbeb9df7b251f2fde23741abc2a144cf30205ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3983fc5bdc795fbf9525b970fbeb9df7b251f2fde23741abc2a144cf30205ae","first_computed_at":"2026-07-05T08:25:30.824616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:30.824616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FHQn/EjjCyErAf222T5zJ3tZlMn+fpisthCwASNgu7iaa32Q+i5Y3qgBOdPo7i5JWx8jyfpL+jvJZpUA5z7PCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:30.825080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00368","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:230c577af51fbfa6061db46081fa44209ee75037fd988b579026ecfa5379cf7e","sha256:fa716724b3b040f1b9ae90c3fde86e72b0c9c092233719bd0a6bfd33bf503e54"],"state_sha256":"85334d081d066cba824b3a17d9da104fb74632ebe575d9b8c4189815fe70dc75"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BA2Qo20UiciVRv66tigMGTDCt9T19K7l79H4zG/CR/NbhDq/zyq/oJ/uYjqtN/kLcVeaqVD92cEyyd4F8oM4BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:52:32.682219Z","bundle_sha256":"d4d87944f57e7536d9ad19a618aa3df8a43f50cd05439cb8fe020c38155d9310"}}