{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YNC2YE3ZYZ6KPKRTHNG23XAVLO","short_pith_number":"pith:YNC2YE3Z","canonical_record":{"source":{"id":"2502.03824","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T07:19:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d486d437925cc5af7d09aa1f104f561e7cce377ddd0e436e0503c426184c9341","abstract_canon_sha256":"c25b81b4195d7ed5cfc4151b08956cd733cdfc81ba0fa5e8c4eb00e376bd9995"},"schema_version":"1.0"},"canonical_sha256":"c345ac1379c67ca7aa333b4daddc155b8ed06c4a5b86d41105009043e8c0feb7","source":{"kind":"arxiv","id":"2502.03824","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03824","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03824v3","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03824","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"pith_short_12","alias_value":"YNC2YE3ZYZ6K","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"pith_short_16","alias_value":"YNC2YE3ZYZ6KPKRT","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"pith_short_8","alias_value":"YNC2YE3Z","created_at":"2026-07-05T10:14:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YNC2YE3ZYZ6KPKRTHNG23XAVLO","target":"record","payload":{"canonical_record":{"source":{"id":"2502.03824","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T07:19:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d486d437925cc5af7d09aa1f104f561e7cce377ddd0e436e0503c426184c9341","abstract_canon_sha256":"c25b81b4195d7ed5cfc4151b08956cd733cdfc81ba0fa5e8c4eb00e376bd9995"},"schema_version":"1.0"},"canonical_sha256":"c345ac1379c67ca7aa333b4daddc155b8ed06c4a5b86d41105009043e8c0feb7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:08.493131Z","signature_b64":"3wC+uARb0ZrrndcNVoz1xgqr4iqaJ6NrXb41RBl+H0ZZ4oj2I7og/nOhmcwdXrim7zkyFbPS4iSPe7ZaBqYVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c345ac1379c67ca7aa333b4daddc155b8ed06c4a5b86d41105009043e8c0feb7","last_reissued_at":"2026-07-05T10:14:08.492642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:08.492642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.03824","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":"2026-07-05T10:14:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jAQwaTguwi0VSuBrHdcpnkqpvJaCNW9+V7oeBwugitrGzDyQvWh8tf2fxozm6qc0t5ZURXtDDvRH7pyvjR15Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:56:14.813223Z"},"content_sha256":"9f45a66a1623153ad09e666354bd73a4aeaae0292988832b9ebda1fc716ec885","schema_version":"1.0","event_id":"sha256:9f45a66a1623153ad09e666354bd73a4aeaae0292988832b9ebda1fc716ec885"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YNC2YE3ZYZ6KPKRTHNG23XAVLO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Syntriever: How to Train Your Retriever with Synthetic Data from LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Minsang Kim, Seungjun Baek","submitted_at":"2025-02-06T07:19:59Z","abstract_excerpt":"LLMs have boosted progress in many AI applications. Recently, there were attempts to distill the vast knowledge of LLMs into information retrieval systems. Those distillation methods mostly use output probabilities of LLMs which are unavailable in the latest black-box LLMs. We propose Syntriever, a training framework for retrievers using synthetic data from black-box LLMs. Syntriever consists of two stages. Firstly in the distillation stage, we synthesize relevant and plausibly irrelevant passages and augmented queries using chain-of-thoughts for the given queries. LLM is asked to self-verify "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03824","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/2502.03824/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":"2026-07-05T10:14:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XY5IK7pL0H6HgryM7Rqh9lsFJ0E0BvzpjD7MpEhfTVeJBlTh75imrUJaN18up/iNF6drO7sB8muLCJuWPPJPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:56:14.814210Z"},"content_sha256":"7c1c692f12111727582a3ea8ed5d4719bfbd9bd0bbc88b2c16d1a2785e036d2d","schema_version":"1.0","event_id":"sha256:7c1c692f12111727582a3ea8ed5d4719bfbd9bd0bbc88b2c16d1a2785e036d2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YNC2YE3ZYZ6KPKRTHNG23XAVLO/bundle.json","state_url":"https://pith.science/pith/YNC2YE3ZYZ6KPKRTHNG23XAVLO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YNC2YE3ZYZ6KPKRTHNG23XAVLO/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":"2026-08-03T22:56:14Z","links":{"resolver":"https://pith.science/pith/YNC2YE3ZYZ6KPKRTHNG23XAVLO","bundle":"https://pith.science/pith/YNC2YE3ZYZ6KPKRTHNG23XAVLO/bundle.json","state":"https://pith.science/pith/YNC2YE3ZYZ6KPKRTHNG23XAVLO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YNC2YE3ZYZ6KPKRTHNG23XAVLO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YNC2YE3ZYZ6KPKRTHNG23XAVLO","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":"c25b81b4195d7ed5cfc4151b08956cd733cdfc81ba0fa5e8c4eb00e376bd9995","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T07:19:59Z","title_canon_sha256":"d486d437925cc5af7d09aa1f104f561e7cce377ddd0e436e0503c426184c9341"},"schema_version":"1.0","source":{"id":"2502.03824","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03824","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03824v3","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03824","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"pith_short_12","alias_value":"YNC2YE3ZYZ6K","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"pith_short_16","alias_value":"YNC2YE3ZYZ6KPKRT","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"pith_short_8","alias_value":"YNC2YE3Z","created_at":"2026-07-05T10:14:08Z"}],"graph_snapshots":[{"event_id":"sha256:7c1c692f12111727582a3ea8ed5d4719bfbd9bd0bbc88b2c16d1a2785e036d2d","target":"graph","created_at":"2026-07-05T10:14:08Z","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/2502.03824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLMs have boosted progress in many AI applications. Recently, there were attempts to distill the vast knowledge of LLMs into information retrieval systems. Those distillation methods mostly use output probabilities of LLMs which are unavailable in the latest black-box LLMs. We propose Syntriever, a training framework for retrievers using synthetic data from black-box LLMs. Syntriever consists of two stages. Firstly in the distillation stage, we synthesize relevant and plausibly irrelevant passages and augmented queries using chain-of-thoughts for the given queries. LLM is asked to self-verify ","authors_text":"Minsang Kim, Seungjun Baek","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T07:19:59Z","title":"Syntriever: How to Train Your Retriever with Synthetic Data from LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03824","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":"sha256:9f45a66a1623153ad09e666354bd73a4aeaae0292988832b9ebda1fc716ec885","target":"record","created_at":"2026-07-05T10:14:08Z","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":"c25b81b4195d7ed5cfc4151b08956cd733cdfc81ba0fa5e8c4eb00e376bd9995","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T07:19:59Z","title_canon_sha256":"d486d437925cc5af7d09aa1f104f561e7cce377ddd0e436e0503c426184c9341"},"schema_version":"1.0","source":{"id":"2502.03824","kind":"arxiv","version":3}},"canonical_sha256":"c345ac1379c67ca7aa333b4daddc155b8ed06c4a5b86d41105009043e8c0feb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c345ac1379c67ca7aa333b4daddc155b8ed06c4a5b86d41105009043e8c0feb7","first_computed_at":"2026-07-05T10:14:08.492642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:08.492642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3wC+uARb0ZrrndcNVoz1xgqr4iqaJ6NrXb41RBl+H0ZZ4oj2I7og/nOhmcwdXrim7zkyFbPS4iSPe7ZaBqYVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:08.493131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03824","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f45a66a1623153ad09e666354bd73a4aeaae0292988832b9ebda1fc716ec885","sha256:7c1c692f12111727582a3ea8ed5d4719bfbd9bd0bbc88b2c16d1a2785e036d2d"],"state_sha256":"e485f723d8f6a38ea286a60112210be4050fef234d005f39c0f868e0440ec725"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MLETCim5LjapEevkg5q6GZwJr3n7yHcIG31u2C3Rdyc1dKoWN8yCWDilh3YRkd2QHk+vkcHuIMwOM/uxrIq1DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:56:14.822238Z","bundle_sha256":"005eed841e6659473beefc513e73048653b2538792e6a1d6e75e6f4c39bec950"}}