{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KETIZPUAHZKSZGQRG2HBIZSK4I","short_pith_number":"pith:KETIZPUA","canonical_record":{"source":{"id":"2403.20327","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T17:56:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c1eafdc9fb6607ef4b650bf568d9044078b8b36a8c844f2e7e937764374b629c","abstract_canon_sha256":"cec03fbda0dd6622b4f1b3f05ee1bccd346cafb53e3d48813a5b000c0a1a8d2b"},"schema_version":"1.0"},"canonical_sha256":"51268cbe803e552c9a11368e14664ae23b05aa3de5839cc17be71e81a3107b57","source":{"kind":"arxiv","id":"2403.20327","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.20327","created_at":"2026-07-05T08:02:17Z"},{"alias_kind":"arxiv_version","alias_value":"2403.20327v1","created_at":"2026-07-05T08:02:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.20327","created_at":"2026-07-05T08:02:17Z"},{"alias_kind":"pith_short_12","alias_value":"KETIZPUAHZKS","created_at":"2026-07-05T08:02:17Z"},{"alias_kind":"pith_short_16","alias_value":"KETIZPUAHZKSZGQR","created_at":"2026-07-05T08:02:17Z"},{"alias_kind":"pith_short_8","alias_value":"KETIZPUA","created_at":"2026-07-05T08:02:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KETIZPUAHZKSZGQRG2HBIZSK4I","target":"record","payload":{"canonical_record":{"source":{"id":"2403.20327","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T17:56:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c1eafdc9fb6607ef4b650bf568d9044078b8b36a8c844f2e7e937764374b629c","abstract_canon_sha256":"cec03fbda0dd6622b4f1b3f05ee1bccd346cafb53e3d48813a5b000c0a1a8d2b"},"schema_version":"1.0"},"canonical_sha256":"51268cbe803e552c9a11368e14664ae23b05aa3de5839cc17be71e81a3107b57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:17.849072Z","signature_b64":"7epGF5kZDECpt4mbRwiqucllCCf262qpwfHCAZs2natwO25QoZixk7QCIC6G7Jb0iq4bieAVcvDZp40pO5iHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51268cbe803e552c9a11368e14664ae23b05aa3de5839cc17be71e81a3107b57","last_reissued_at":"2026-07-05T08:02:17.848582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:17.848582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.20327","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":"2026-07-05T08:02:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kixCQ3Ufz1ZRjjUdudOExVp3kjohP12le3VfQYMY3PP2cJQA88fv03XwtCzkSTknh62uKV1ogr1Sl3Rn1GjwDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T16:06:17.187981Z"},"content_sha256":"0e8b3713d1af732e538bb366c59c8d45d6b6f315c3683580f67ee2d82aac8c4e","schema_version":"1.0","event_id":"sha256:0e8b3713d1af732e538bb366c59c8d45d6b6f315c3683580f67ee2d82aac8c4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KETIZPUAHZKSZGQRG2HBIZSK4I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gecko: Versatile Text Embeddings Distilled from Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditya Kusupati, Blair Chen, Daniel Cer, Gustavo Hernandez Abrego, Iftekhar Naim, Jeremy R. Cole, Jinhyuk Lee, Kai Hui, Michael Boratko, Ming-Wei Chang, Nithi Gupta, Prateek Jain, Rajvi Kapadia, Sai Meher Karthik Duddu, Siddhartha Reddy Jonnalagadda, Weiqiang Shi, Wen Ding, Xiaoqi Ren, Yi Luan, Zhuyun Dai","submitted_at":"2024-03-29T17:56:40Z","abstract_excerpt":"We present Gecko, a compact and versatile text embedding model. Gecko achieves strong retrieval performance by leveraging a key idea: distilling knowledge from large language models (LLMs) into a retriever. Our two-step distillation process begins with generating diverse, synthetic paired data using an LLM. Next, we further refine the data quality by retrieving a set of candidate passages for each query, and relabeling the positive and hard negative passages using the same LLM. The effectiveness of our approach is demonstrated by the compactness of the Gecko. On the Massive Text Embedding Benc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20327","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/2403.20327/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":"2026-07-05T08:02:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NkdOqGNNW1/QtV5RS6moxrguxdvjXy+xVM3eQYge8Mpr+0apPX6+sP0cf8zbLiADH/ov0FMT90NZiNEnb6qRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T16:06:17.188492Z"},"content_sha256":"2b5e1cf70c5c1223ff45536d9689bf28413a61ea4dad6d4dd609a62d3a2b2eb4","schema_version":"1.0","event_id":"sha256:2b5e1cf70c5c1223ff45536d9689bf28413a61ea4dad6d4dd609a62d3a2b2eb4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KETIZPUAHZKSZGQRG2HBIZSK4I/bundle.json","state_url":"https://pith.science/pith/KETIZPUAHZKSZGQRG2HBIZSK4I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KETIZPUAHZKSZGQRG2HBIZSK4I/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":"2026-08-21T16:06:17Z","links":{"resolver":"https://pith.science/pith/KETIZPUAHZKSZGQRG2HBIZSK4I","bundle":"https://pith.science/pith/KETIZPUAHZKSZGQRG2HBIZSK4I/bundle.json","state":"https://pith.science/pith/KETIZPUAHZKSZGQRG2HBIZSK4I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KETIZPUAHZKSZGQRG2HBIZSK4I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KETIZPUAHZKSZGQRG2HBIZSK4I","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":"cec03fbda0dd6622b4f1b3f05ee1bccd346cafb53e3d48813a5b000c0a1a8d2b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T17:56:40Z","title_canon_sha256":"c1eafdc9fb6607ef4b650bf568d9044078b8b36a8c844f2e7e937764374b629c"},"schema_version":"1.0","source":{"id":"2403.20327","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.20327","created_at":"2026-07-05T08:02:17Z"},{"alias_kind":"arxiv_version","alias_value":"2403.20327v1","created_at":"2026-07-05T08:02:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.20327","created_at":"2026-07-05T08:02:17Z"},{"alias_kind":"pith_short_12","alias_value":"KETIZPUAHZKS","created_at":"2026-07-05T08:02:17Z"},{"alias_kind":"pith_short_16","alias_value":"KETIZPUAHZKSZGQR","created_at":"2026-07-05T08:02:17Z"},{"alias_kind":"pith_short_8","alias_value":"KETIZPUA","created_at":"2026-07-05T08:02:17Z"}],"graph_snapshots":[{"event_id":"sha256:2b5e1cf70c5c1223ff45536d9689bf28413a61ea4dad6d4dd609a62d3a2b2eb4","target":"graph","created_at":"2026-07-05T08:02:17Z","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/2403.20327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Gecko, a compact and versatile text embedding model. Gecko achieves strong retrieval performance by leveraging a key idea: distilling knowledge from large language models (LLMs) into a retriever. Our two-step distillation process begins with generating diverse, synthetic paired data using an LLM. Next, we further refine the data quality by retrieving a set of candidate passages for each query, and relabeling the positive and hard negative passages using the same LLM. The effectiveness of our approach is demonstrated by the compactness of the Gecko. On the Massive Text Embedding Benc","authors_text":"Aditya Kusupati, Blair Chen, Daniel Cer, Gustavo Hernandez Abrego, Iftekhar Naim, Jeremy R. Cole, Jinhyuk Lee, Kai Hui, Michael Boratko, Ming-Wei Chang, Nithi Gupta, Prateek Jain, Rajvi Kapadia, Sai Meher Karthik Duddu, Siddhartha Reddy Jonnalagadda, Weiqiang Shi, Wen Ding, Xiaoqi Ren, Yi Luan, Zhuyun Dai","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T17:56:40Z","title":"Gecko: Versatile Text Embeddings Distilled from Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20327","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":"sha256:0e8b3713d1af732e538bb366c59c8d45d6b6f315c3683580f67ee2d82aac8c4e","target":"record","created_at":"2026-07-05T08:02:17Z","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":"cec03fbda0dd6622b4f1b3f05ee1bccd346cafb53e3d48813a5b000c0a1a8d2b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T17:56:40Z","title_canon_sha256":"c1eafdc9fb6607ef4b650bf568d9044078b8b36a8c844f2e7e937764374b629c"},"schema_version":"1.0","source":{"id":"2403.20327","kind":"arxiv","version":1}},"canonical_sha256":"51268cbe803e552c9a11368e14664ae23b05aa3de5839cc17be71e81a3107b57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51268cbe803e552c9a11368e14664ae23b05aa3de5839cc17be71e81a3107b57","first_computed_at":"2026-07-05T08:02:17.848582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:17.848582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7epGF5kZDECpt4mbRwiqucllCCf262qpwfHCAZs2natwO25QoZixk7QCIC6G7Jb0iq4bieAVcvDZp40pO5iHBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:17.849072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.20327","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e8b3713d1af732e538bb366c59c8d45d6b6f315c3683580f67ee2d82aac8c4e","sha256:2b5e1cf70c5c1223ff45536d9689bf28413a61ea4dad6d4dd609a62d3a2b2eb4"],"state_sha256":"010f28441ade10f6117afb14b5079e9692dd61c7ce95766426312a9bdecb46cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wKyeb64W58Sx6VFL4FDzHbupGfasmWQze8MLBJRzILuNOPQQ3YnRzyOAXrmY7EPX0OpfLSZ9A5UD758UIVKhCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T16:06:17.192980Z","bundle_sha256":"a5c3e13e851698b3c9ba55057143be37157f166ec3dad80efcd85a1065f03385"}}