{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RGVRP7DFKLAVXKVTA6JHIWISZY","short_pith_number":"pith:RGVRP7DF","schema_version":"1.0","canonical_sha256":"89ab17fc6552c15baab30792745912ce103c29458576a79b05730c4069cc4d26","source":{"kind":"arxiv","id":"2506.20476","version":1},"attestation_state":"computed","paper":{"title":"Knowledge-Aware Diverse Reranking for Cross-Source Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Tong Zhou","submitted_at":"2025-06-25T14:23:21Z","abstract_excerpt":"This paper presents Team Marikarp's solution for the SIGIR 2025 LiveRAG competition. The competition's evaluation set, automatically generated by DataMorgana from internet corpora, encompassed a wide range of target topics, question types, question formulations, audience types, and knowledge organization methods. It offered a fair evaluation of retrieving question-relevant supporting documents from a 15M documents subset of the FineWeb corpus. Our proposed knowledge-aware diverse reranking RAG pipeline achieved first place in the competition."},"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":"2506.20476","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T14:23:21Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"e122e88d97748e7d6c7d82dbc152339b5b56b74d56abf291fff6b5c4188674f4","abstract_canon_sha256":"ab9ebbfc343b60ceda6e9b8b519061d645e040cfd9d2bc4526474ca2baa5f5ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:06.408942Z","signature_b64":"UpPbGZ5uHQr88Id7+e79MNfw42vRI/tAqFaJtGmvIMVqVYv3XrARZQ9TNXks/hW+yuZsUS0xyl9v5OTz8/tJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89ab17fc6552c15baab30792745912ce103c29458576a79b05730c4069cc4d26","last_reissued_at":"2026-07-05T11:27:06.408571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:06.408571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge-Aware Diverse Reranking for Cross-Source Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Tong Zhou","submitted_at":"2025-06-25T14:23:21Z","abstract_excerpt":"This paper presents Team Marikarp's solution for the SIGIR 2025 LiveRAG competition. The competition's evaluation set, automatically generated by DataMorgana from internet corpora, encompassed a wide range of target topics, question types, question formulations, audience types, and knowledge organization methods. It offered a fair evaluation of retrieving question-relevant supporting documents from a 15M documents subset of the FineWeb corpus. Our proposed knowledge-aware diverse reranking RAG pipeline achieved first place in the competition."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20476","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/2506.20476/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":"2506.20476","created_at":"2026-07-05T11:27:06.408627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20476v1","created_at":"2026-07-05T11:27:06.408627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20476","created_at":"2026-07-05T11:27:06.408627+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGVRP7DFKLAV","created_at":"2026-07-05T11:27:06.408627+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGVRP7DFKLAVXKVT","created_at":"2026-07-05T11:27:06.408627+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGVRP7DF","created_at":"2026-07-05T11:27:06.408627+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09441","citing_title":"SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RGVRP7DFKLAVXKVTA6JHIWISZY","json":"https://pith.science/pith/RGVRP7DFKLAVXKVTA6JHIWISZY.json","graph_json":"https://pith.science/api/pith-number/RGVRP7DFKLAVXKVTA6JHIWISZY/graph.json","events_json":"https://pith.science/api/pith-number/RGVRP7DFKLAVXKVTA6JHIWISZY/events.json","paper":"https://pith.science/paper/RGVRP7DF"},"agent_actions":{"view_html":"https://pith.science/pith/RGVRP7DFKLAVXKVTA6JHIWISZY","download_json":"https://pith.science/pith/RGVRP7DFKLAVXKVTA6JHIWISZY.json","view_paper":"https://pith.science/paper/RGVRP7DF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20476&json=true","fetch_graph":"https://pith.science/api/pith-number/RGVRP7DFKLAVXKVTA6JHIWISZY/graph.json","fetch_events":"https://pith.science/api/pith-number/RGVRP7DFKLAVXKVTA6JHIWISZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGVRP7DFKLAVXKVTA6JHIWISZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGVRP7DFKLAVXKVTA6JHIWISZY/action/storage_attestation","attest_author":"https://pith.science/pith/RGVRP7DFKLAVXKVTA6JHIWISZY/action/author_attestation","sign_citation":"https://pith.science/pith/RGVRP7DFKLAVXKVTA6JHIWISZY/action/citation_signature","submit_replication":"https://pith.science/pith/RGVRP7DFKLAVXKVTA6JHIWISZY/action/replication_record"}},"created_at":"2026-07-05T11:27:06.408627+00:00","updated_at":"2026-07-05T11:27:06.408627+00:00"}