{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EXUNDOEU6VSZTL7JF6APWK3CTX","short_pith_number":"pith:EXUNDOEU","schema_version":"1.0","canonical_sha256":"25e8d1b894f56599afe92f80fb2b629dd79b31819702028a694bc6b680c90b29","source":{"kind":"arxiv","id":"2504.03947","version":3},"attestation_state":"computed","paper":{"title":"Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Chris Samarinas, Hamed Zamani","submitted_at":"2025-04-04T21:27:48Z","abstract_excerpt":"We present a novel approach for training small language models for reasoning-intensive document ranking that combines knowledge distillation with reinforcement learning optimization. While existing methods often rely on expensive human annotations or large black-box language models, our methodology leverages web data and a teacher LLM to automatically generate high-quality training examples with relevance explanations. By framing document ranking as a reinforcement learning problem and incentivizing explicit reasoning capabilities, we train a compact 3B parameter language model that achieves s"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.03947","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-04T21:27:48Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6f27c2b66c592f43ac55a710288e545a746d97e549bbafde4f615e6d07a33b7c","abstract_canon_sha256":"ecccb99b0fc34a8e781fd3ded8134a1623f12b279dea0611cad3b8dd337d7a0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:10.148601Z","signature_b64":"K8pTlliUEmjp4c39OksoTGQ2qiYk1RjORUEXenUWGlloQmWKaeQL5kNxyaT4N6a5VHFyt76XNepJE/ei9NdvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25e8d1b894f56599afe92f80fb2b629dd79b31819702028a694bc6b680c90b29","last_reissued_at":"2026-07-05T11:29:10.148153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:10.148153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Chris Samarinas, Hamed Zamani","submitted_at":"2025-04-04T21:27:48Z","abstract_excerpt":"We present a novel approach for training small language models for reasoning-intensive document ranking that combines knowledge distillation with reinforcement learning optimization. While existing methods often rely on expensive human annotations or large black-box language models, our methodology leverages web data and a teacher LLM to automatically generate high-quality training examples with relevance explanations. By framing document ranking as a reinforcement learning problem and incentivizing explicit reasoning capabilities, we train a compact 3B parameter language model that achieves s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03947","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/2504.03947/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.03947","created_at":"2026-07-05T11:29:10.148212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03947v3","created_at":"2026-07-05T11:29:10.148212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03947","created_at":"2026-07-05T11:29:10.148212+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXUNDOEU6VSZ","created_at":"2026-07-05T11:29:10.148212+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXUNDOEU6VSZTL7J","created_at":"2026-07-05T11:29:10.148212+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXUNDOEU","created_at":"2026-07-05T11:29:10.148212+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18405","citing_title":"RaDeR: Reasoning-aware Dense Retrieval Models","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EXUNDOEU6VSZTL7JF6APWK3CTX","json":"https://pith.science/pith/EXUNDOEU6VSZTL7JF6APWK3CTX.json","graph_json":"https://pith.science/api/pith-number/EXUNDOEU6VSZTL7JF6APWK3CTX/graph.json","events_json":"https://pith.science/api/pith-number/EXUNDOEU6VSZTL7JF6APWK3CTX/events.json","paper":"https://pith.science/paper/EXUNDOEU"},"agent_actions":{"view_html":"https://pith.science/pith/EXUNDOEU6VSZTL7JF6APWK3CTX","download_json":"https://pith.science/pith/EXUNDOEU6VSZTL7JF6APWK3CTX.json","view_paper":"https://pith.science/paper/EXUNDOEU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03947&json=true","fetch_graph":"https://pith.science/api/pith-number/EXUNDOEU6VSZTL7JF6APWK3CTX/graph.json","fetch_events":"https://pith.science/api/pith-number/EXUNDOEU6VSZTL7JF6APWK3CTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXUNDOEU6VSZTL7JF6APWK3CTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXUNDOEU6VSZTL7JF6APWK3CTX/action/storage_attestation","attest_author":"https://pith.science/pith/EXUNDOEU6VSZTL7JF6APWK3CTX/action/author_attestation","sign_citation":"https://pith.science/pith/EXUNDOEU6VSZTL7JF6APWK3CTX/action/citation_signature","submit_replication":"https://pith.science/pith/EXUNDOEU6VSZTL7JF6APWK3CTX/action/replication_record"}},"created_at":"2026-07-05T11:29:10.148212+00:00","updated_at":"2026-07-05T11:29:10.148212+00:00"}