{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3VJPWDZBCO55EHQ3CTHRH77NMS","short_pith_number":"pith:3VJPWDZB","schema_version":"1.0","canonical_sha256":"dd52fb0f2113bbd21e1b14cf13ffed64b56d45c0f6e35cdd73b62775f074f84e","source":{"kind":"arxiv","id":"2606.11907","version":1},"attestation_state":"computed","paper":{"title":"Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chuanpeng Wang, Jiaming Fang, Kuangyu Li, Tuo Xia, Ziyu Song","submitted_at":"2026-06-10T10:37:19Z","abstract_excerpt":"Adaptive context selection is critical for retrieval-augmented generation (RAG) systems, as fixed Top-K retrieval fails under query-dependent and heavy-tailed similarity distributions. While Extreme Value Theory (EVT) offers a principled framework for adaptive truncation, existing approaches apply EVT globally across the entire ranked list, incurring prohibitive computational costs and statistical instability. We propose Tail-Aware Adaptive-k(TAA-k), a training-free framework that operationalizes EVT through a localized validation strategy. The key insight is that ranked similarity curves exhi"},"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":"2606.11907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-10T10:37:19Z","cross_cats_sorted":[],"title_canon_sha256":"d0ba38b5f45483e27e22bbb7cb5fd6feed286b4f23f387d7e1e0102fa60e60e0","abstract_canon_sha256":"36944ad23c2d27107dc5a707d85aeea680a3ffcd93b68165930d82e858f40d3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:15.045010Z","signature_b64":"nvMxf5FJSPwzoVmOhxS9c1EC2UU05bq4s9trU9UJLfqXU6BPKhOeYl+5mZsIKdqgXIUt9DZjQGsGUM/0/0AJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd52fb0f2113bbd21e1b14cf13ffed64b56d45c0f6e35cdd73b62775f074f84e","last_reissued_at":"2026-06-11T01:10:15.043961Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:15.043961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chuanpeng Wang, Jiaming Fang, Kuangyu Li, Tuo Xia, Ziyu Song","submitted_at":"2026-06-10T10:37:19Z","abstract_excerpt":"Adaptive context selection is critical for retrieval-augmented generation (RAG) systems, as fixed Top-K retrieval fails under query-dependent and heavy-tailed similarity distributions. While Extreme Value Theory (EVT) offers a principled framework for adaptive truncation, existing approaches apply EVT globally across the entire ranked list, incurring prohibitive computational costs and statistical instability. We propose Tail-Aware Adaptive-k(TAA-k), a training-free framework that operationalizes EVT through a localized validation strategy. The key insight is that ranked similarity curves exhi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11907","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/2606.11907/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":"2606.11907","created_at":"2026-06-11T01:10:15.044107+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11907v1","created_at":"2026-06-11T01:10:15.044107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11907","created_at":"2026-06-11T01:10:15.044107+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VJPWDZBCO55","created_at":"2026-06-11T01:10:15.044107+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VJPWDZBCO55EHQ3","created_at":"2026-06-11T01:10:15.044107+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VJPWDZB","created_at":"2026-06-11T01:10:15.044107+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/3VJPWDZBCO55EHQ3CTHRH77NMS","json":"https://pith.science/pith/3VJPWDZBCO55EHQ3CTHRH77NMS.json","graph_json":"https://pith.science/api/pith-number/3VJPWDZBCO55EHQ3CTHRH77NMS/graph.json","events_json":"https://pith.science/api/pith-number/3VJPWDZBCO55EHQ3CTHRH77NMS/events.json","paper":"https://pith.science/paper/3VJPWDZB"},"agent_actions":{"view_html":"https://pith.science/pith/3VJPWDZBCO55EHQ3CTHRH77NMS","download_json":"https://pith.science/pith/3VJPWDZBCO55EHQ3CTHRH77NMS.json","view_paper":"https://pith.science/paper/3VJPWDZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11907&json=true","fetch_graph":"https://pith.science/api/pith-number/3VJPWDZBCO55EHQ3CTHRH77NMS/graph.json","fetch_events":"https://pith.science/api/pith-number/3VJPWDZBCO55EHQ3CTHRH77NMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VJPWDZBCO55EHQ3CTHRH77NMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VJPWDZBCO55EHQ3CTHRH77NMS/action/storage_attestation","attest_author":"https://pith.science/pith/3VJPWDZBCO55EHQ3CTHRH77NMS/action/author_attestation","sign_citation":"https://pith.science/pith/3VJPWDZBCO55EHQ3CTHRH77NMS/action/citation_signature","submit_replication":"https://pith.science/pith/3VJPWDZBCO55EHQ3CTHRH77NMS/action/replication_record"}},"created_at":"2026-06-11T01:10:15.044107+00:00","updated_at":"2026-06-11T01:10:15.044107+00:00"}