{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZMVJR55C6LCUZTHYFI6L3ZVT5B","short_pith_number":"pith:ZMVJR55C","canonical_record":{"source":{"id":"2504.09816","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-14T02:35:00Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ecac35758c5c69bac03f351eacabc872da17ea2fb4863966d1d0daafec411c10","abstract_canon_sha256":"812608a967318fba701c97a990aa89f479b644a9fd40a6c738cd2bbda3959b75"},"schema_version":"1.0"},"canonical_sha256":"cb2a98f7a2f2c54cccf82a3cbde6b3e87a28ce71c0e50a6e0dda973838980277","source":{"kind":"arxiv","id":"2504.09816","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09816","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09816v1","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09816","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZMVJR55C6LCU","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"pith_short_16","alias_value":"ZMVJR55C6LCUZTHY","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"pith_short_8","alias_value":"ZMVJR55C","created_at":"2026-07-05T10:48:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZMVJR55C6LCUZTHYFI6L3ZVT5B","target":"record","payload":{"canonical_record":{"source":{"id":"2504.09816","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-14T02:35:00Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ecac35758c5c69bac03f351eacabc872da17ea2fb4863966d1d0daafec411c10","abstract_canon_sha256":"812608a967318fba701c97a990aa89f479b644a9fd40a6c738cd2bbda3959b75"},"schema_version":"1.0"},"canonical_sha256":"cb2a98f7a2f2c54cccf82a3cbde6b3e87a28ce71c0e50a6e0dda973838980277","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:43.135221Z","signature_b64":"jEXj1F/4VKz1ghuJEBOXl7opvhAIWA9KmERb7cBjBc3RLE6KLDnVrv+kN5bP4Laj12hA/hIBqZygMcCSM/1PDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb2a98f7a2f2c54cccf82a3cbde6b3e87a28ce71c0e50a6e0dda973838980277","last_reissued_at":"2026-07-05T10:48:43.134796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:43.134796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.09816","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":"2026-07-05T10:48:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jaAkDVajmSbzsxURuru4f93Fwhgv6p0BACnrFVAR4FxwcZDUlVv13fwUzFfWVJZAmR+M0Y58LT6bPAuhvu/eCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:25:52.308095Z"},"content_sha256":"f6757ce8f31709662e75cc84b390c4d6487585c787dd02ac7abda917cf6b3238","schema_version":"1.0","event_id":"sha256:f6757ce8f31709662e75cc84b390c4d6487585c787dd02ac7abda917cf6b3238"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZMVJR55C6LCUZTHYFI6L3ZVT5B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Augmented Relevance Datasets with Fine-Tuned Small LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Matyas Amrouche, Quentin Fitte-Rey, Romain Deveaud","submitted_at":"2025-04-14T02:35:00Z","abstract_excerpt":"Building high-quality datasets and labeling query-document relevance are essential yet resource-intensive tasks, requiring detailed guidelines and substantial effort from human annotators. This paper explores the use of small, fine-tuned large language models (LLMs) to automate relevance assessment, with a focus on improving ranking models' performance by augmenting their training dataset. We fine-tuned small LLMs to enhance relevance assessments, thereby improving dataset creation quality for downstream ranking model training. Our experiments demonstrate that these fine-tuned small LLMs not o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09816","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/2504.09816/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":"2026-07-05T10:48:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wM7ZerzhKhvnr5wltOoVddjVhw7IWTOyma2kcb8Ws2vvAm/4Sc6v887NCdLlFs3wf8/rLJtUVcbGJDUuCBC4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:25:52.309175Z"},"content_sha256":"28182edeac3b218c5211404508f1b0e8a56358fc8b1de008c7ffd7a327776fb6","schema_version":"1.0","event_id":"sha256:28182edeac3b218c5211404508f1b0e8a56358fc8b1de008c7ffd7a327776fb6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZMVJR55C6LCUZTHYFI6L3ZVT5B/bundle.json","state_url":"https://pith.science/pith/ZMVJR55C6LCUZTHYFI6L3ZVT5B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZMVJR55C6LCUZTHYFI6L3ZVT5B/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":"2026-08-17T12:25:52Z","links":{"resolver":"https://pith.science/pith/ZMVJR55C6LCUZTHYFI6L3ZVT5B","bundle":"https://pith.science/pith/ZMVJR55C6LCUZTHYFI6L3ZVT5B/bundle.json","state":"https://pith.science/pith/ZMVJR55C6LCUZTHYFI6L3ZVT5B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZMVJR55C6LCUZTHYFI6L3ZVT5B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZMVJR55C6LCUZTHYFI6L3ZVT5B","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":"812608a967318fba701c97a990aa89f479b644a9fd40a6c738cd2bbda3959b75","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-14T02:35:00Z","title_canon_sha256":"ecac35758c5c69bac03f351eacabc872da17ea2fb4863966d1d0daafec411c10"},"schema_version":"1.0","source":{"id":"2504.09816","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09816","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09816v1","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09816","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZMVJR55C6LCU","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"pith_short_16","alias_value":"ZMVJR55C6LCUZTHY","created_at":"2026-07-05T10:48:43Z"},{"alias_kind":"pith_short_8","alias_value":"ZMVJR55C","created_at":"2026-07-05T10:48:43Z"}],"graph_snapshots":[{"event_id":"sha256:28182edeac3b218c5211404508f1b0e8a56358fc8b1de008c7ffd7a327776fb6","target":"graph","created_at":"2026-07-05T10:48:43Z","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/2504.09816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building high-quality datasets and labeling query-document relevance are essential yet resource-intensive tasks, requiring detailed guidelines and substantial effort from human annotators. This paper explores the use of small, fine-tuned large language models (LLMs) to automate relevance assessment, with a focus on improving ranking models' performance by augmenting their training dataset. We fine-tuned small LLMs to enhance relevance assessments, thereby improving dataset creation quality for downstream ranking model training. Our experiments demonstrate that these fine-tuned small LLMs not o","authors_text":"Matyas Amrouche, Quentin Fitte-Rey, Romain Deveaud","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-14T02:35:00Z","title":"Augmented Relevance Datasets with Fine-Tuned Small LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09816","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:f6757ce8f31709662e75cc84b390c4d6487585c787dd02ac7abda917cf6b3238","target":"record","created_at":"2026-07-05T10:48:43Z","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":"812608a967318fba701c97a990aa89f479b644a9fd40a6c738cd2bbda3959b75","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-14T02:35:00Z","title_canon_sha256":"ecac35758c5c69bac03f351eacabc872da17ea2fb4863966d1d0daafec411c10"},"schema_version":"1.0","source":{"id":"2504.09816","kind":"arxiv","version":1}},"canonical_sha256":"cb2a98f7a2f2c54cccf82a3cbde6b3e87a28ce71c0e50a6e0dda973838980277","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb2a98f7a2f2c54cccf82a3cbde6b3e87a28ce71c0e50a6e0dda973838980277","first_computed_at":"2026-07-05T10:48:43.134796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:43.134796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jEXj1F/4VKz1ghuJEBOXl7opvhAIWA9KmERb7cBjBc3RLE6KLDnVrv+kN5bP4Laj12hA/hIBqZygMcCSM/1PDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:43.135221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.09816","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6757ce8f31709662e75cc84b390c4d6487585c787dd02ac7abda917cf6b3238","sha256:28182edeac3b218c5211404508f1b0e8a56358fc8b1de008c7ffd7a327776fb6"],"state_sha256":"ffaccaa79996ec57287375739aff64da560d24ff11aa4943dbbdfcc5bcc56507"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oV5PMxpvkmJVWe82hsBFMwA0VrSlJ9tZKyT3M/tCa7S6jD0/58RQD1MjDfqW4+Eg3kJZN47yjNAwoNl7nMK+Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T12:25:52.314806Z","bundle_sha256":"3916c55bdecb1130e67530c7ebcc6a0953160266bf15e86a22ddc84eb29873e2"}}