{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NOUMESDLXROFRFW3VYC5INU2RQ","short_pith_number":"pith:NOUMESDL","schema_version":"1.0","canonical_sha256":"6ba8c2486bbc5c5896dbae05d4369a8c28263839abc83202403ade1f563ab8b9","source":{"kind":"arxiv","id":"2506.15246","version":1},"attestation_state":"computed","paper":{"title":"TopClustRAG at SIGIR 2025 LiveRAG Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aristidis Likas, John Pavlopoulos, Juli Bakagianni","submitted_at":"2025-06-18T08:24:27Z","abstract_excerpt":"We present TopClustRAG, a retrieval-augmented generation (RAG) system developed for the LiveRAG Challenge, which evaluates end-to-end question answering over large-scale web corpora. Our system employs a hybrid retrieval strategy combining sparse and dense indices, followed by K-Means clustering to group semantically similar passages. Representative passages from each cluster are used to construct cluster-specific prompts for a large language model (LLM), generating intermediate answers that are filtered, reranked, and finally synthesized into a single, comprehensive response. This multi-stage"},"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":"2506.15246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-18T08:24:27Z","cross_cats_sorted":[],"title_canon_sha256":"2e88dbc4a873738de0f5f7f0cf749e3eb826ffcb6579b9ce172417a33db3dca0","abstract_canon_sha256":"aed32d90cfce15a72cc0e4d31b68a806f96ec6986af9916e2fd6f8a754256b9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:40.082903Z","signature_b64":"OyoHMFpblW6ZcoNxlRp1LIBqT6WeepX1UqM4SeZdYJfWBNLwvUN4shoVza8LRFlqVBWcuB++sChcmh4ikpjOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ba8c2486bbc5c5896dbae05d4369a8c28263839abc83202403ade1f563ab8b9","last_reissued_at":"2026-07-05T11:23:40.082489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:40.082489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TopClustRAG at SIGIR 2025 LiveRAG Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aristidis Likas, John Pavlopoulos, Juli Bakagianni","submitted_at":"2025-06-18T08:24:27Z","abstract_excerpt":"We present TopClustRAG, a retrieval-augmented generation (RAG) system developed for the LiveRAG Challenge, which evaluates end-to-end question answering over large-scale web corpora. Our system employs a hybrid retrieval strategy combining sparse and dense indices, followed by K-Means clustering to group semantically similar passages. Representative passages from each cluster are used to construct cluster-specific prompts for a large language model (LLM), generating intermediate answers that are filtered, reranked, and finally synthesized into a single, comprehensive response. This multi-stage"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15246","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/2506.15246/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":"2506.15246","created_at":"2026-07-05T11:23:40.082548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15246v1","created_at":"2026-07-05T11:23:40.082548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15246","created_at":"2026-07-05T11:23:40.082548+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOUMESDLXROF","created_at":"2026-07-05T11:23:40.082548+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOUMESDLXROFRFW3","created_at":"2026-07-05T11:23:40.082548+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOUMESDL","created_at":"2026-07-05T11:23:40.082548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04942","citing_title":"SIGIR 2025 -- LiveRAG Challenge Report","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NOUMESDLXROFRFW3VYC5INU2RQ","json":"https://pith.science/pith/NOUMESDLXROFRFW3VYC5INU2RQ.json","graph_json":"https://pith.science/api/pith-number/NOUMESDLXROFRFW3VYC5INU2RQ/graph.json","events_json":"https://pith.science/api/pith-number/NOUMESDLXROFRFW3VYC5INU2RQ/events.json","paper":"https://pith.science/paper/NOUMESDL"},"agent_actions":{"view_html":"https://pith.science/pith/NOUMESDLXROFRFW3VYC5INU2RQ","download_json":"https://pith.science/pith/NOUMESDLXROFRFW3VYC5INU2RQ.json","view_paper":"https://pith.science/paper/NOUMESDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15246&json=true","fetch_graph":"https://pith.science/api/pith-number/NOUMESDLXROFRFW3VYC5INU2RQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NOUMESDLXROFRFW3VYC5INU2RQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOUMESDLXROFRFW3VYC5INU2RQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOUMESDLXROFRFW3VYC5INU2RQ/action/storage_attestation","attest_author":"https://pith.science/pith/NOUMESDLXROFRFW3VYC5INU2RQ/action/author_attestation","sign_citation":"https://pith.science/pith/NOUMESDLXROFRFW3VYC5INU2RQ/action/citation_signature","submit_replication":"https://pith.science/pith/NOUMESDLXROFRFW3VYC5INU2RQ/action/replication_record"}},"created_at":"2026-07-05T11:23:40.082548+00:00","updated_at":"2026-07-05T11:23:40.082548+00:00"}