{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FCGF5R3H3ASYXDLV7RDRBYSDCJ","short_pith_number":"pith:FCGF5R3H","schema_version":"1.0","canonical_sha256":"288c5ec767d8258b8d75fc4710e2431257cf2d45b44218ffc86d02a38da140d6","source":{"kind":"arxiv","id":"2505.19284","version":1},"attestation_state":"computed","paper":{"title":"RankLLM: A Python Package for Reranking with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andre Slavescu, Andrew Xu, Jasper Xian, Jimmy Lin, Ronak Pradeep, Ryan Nguyen, Sahel Sharifymoghaddam, Yidi Chen, Yilin Zhang, Zijian Chen","submitted_at":"2025-05-25T19:29:27Z","abstract_excerpt":"The adoption of large language models (LLMs) as rerankers in multi-stage retrieval systems has gained significant traction in academia and industry. These models refine a candidate list of retrieved documents, often through carefully designed prompts, and are typically used in applications built on retrieval-augmented generation (RAG). This paper introduces RankLLM, an open-source Python package for reranking that is modular, highly configurable, and supports both proprietary and open-source LLMs in customized reranking workflows. To improve usability, RankLLM features optional integration wit"},"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":"2505.19284","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-25T19:29:27Z","cross_cats_sorted":[],"title_canon_sha256":"339805574fc8d941660f7db17ed3d95893a8b4566ce3afbf3a44a31ea08cefaf","abstract_canon_sha256":"f16898a4bc9e4f668cf59d78e3cd5931e98c2f47fb3418efadd360237ce2e7ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:27.621364Z","signature_b64":"GtEU/2GJX72uTC+b6wnX31M+oJFrsmhaWpiB9cWQnv22PZfeJUzx6pKSill2wNX4tfTwhfDcDtG7Bxo+KvfFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"288c5ec767d8258b8d75fc4710e2431257cf2d45b44218ffc86d02a38da140d6","last_reissued_at":"2026-07-05T11:09:27.620860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:27.620860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RankLLM: A Python Package for Reranking with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andre Slavescu, Andrew Xu, Jasper Xian, Jimmy Lin, Ronak Pradeep, Ryan Nguyen, Sahel Sharifymoghaddam, Yidi Chen, Yilin Zhang, Zijian Chen","submitted_at":"2025-05-25T19:29:27Z","abstract_excerpt":"The adoption of large language models (LLMs) as rerankers in multi-stage retrieval systems has gained significant traction in academia and industry. These models refine a candidate list of retrieved documents, often through carefully designed prompts, and are typically used in applications built on retrieval-augmented generation (RAG). This paper introduces RankLLM, an open-source Python package for reranking that is modular, highly configurable, and supports both proprietary and open-source LLMs in customized reranking workflows. To improve usability, RankLLM features optional integration wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19284","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/2505.19284/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":"2505.19284","created_at":"2026-07-05T11:09:27.620919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19284v1","created_at":"2026-07-05T11:09:27.620919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19284","created_at":"2026-07-05T11:09:27.620919+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCGF5R3H3ASY","created_at":"2026-07-05T11:09:27.620919+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCGF5R3H3ASYXDLV","created_at":"2026-07-05T11:09:27.620919+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCGF5R3H","created_at":"2026-07-05T11:09:27.620919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCGF5R3H3ASYXDLV7RDRBYSDCJ","json":"https://pith.science/pith/FCGF5R3H3ASYXDLV7RDRBYSDCJ.json","graph_json":"https://pith.science/api/pith-number/FCGF5R3H3ASYXDLV7RDRBYSDCJ/graph.json","events_json":"https://pith.science/api/pith-number/FCGF5R3H3ASYXDLV7RDRBYSDCJ/events.json","paper":"https://pith.science/paper/FCGF5R3H"},"agent_actions":{"view_html":"https://pith.science/pith/FCGF5R3H3ASYXDLV7RDRBYSDCJ","download_json":"https://pith.science/pith/FCGF5R3H3ASYXDLV7RDRBYSDCJ.json","view_paper":"https://pith.science/paper/FCGF5R3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19284&json=true","fetch_graph":"https://pith.science/api/pith-number/FCGF5R3H3ASYXDLV7RDRBYSDCJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FCGF5R3H3ASYXDLV7RDRBYSDCJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCGF5R3H3ASYXDLV7RDRBYSDCJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCGF5R3H3ASYXDLV7RDRBYSDCJ/action/storage_attestation","attest_author":"https://pith.science/pith/FCGF5R3H3ASYXDLV7RDRBYSDCJ/action/author_attestation","sign_citation":"https://pith.science/pith/FCGF5R3H3ASYXDLV7RDRBYSDCJ/action/citation_signature","submit_replication":"https://pith.science/pith/FCGF5R3H3ASYXDLV7RDRBYSDCJ/action/replication_record"}},"created_at":"2026-07-05T11:09:27.620919+00:00","updated_at":"2026-07-05T11:09:27.620919+00:00"}