{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N7QZNRI6SIANQ7UTAX7CFFFACY","short_pith_number":"pith:N7QZNRI6","schema_version":"1.0","canonical_sha256":"6fe196c51e9200d87e9305fe2294a0163e47d7cca10a49cfdd76ea0fa7d6721b","source":{"kind":"arxiv","id":"2509.06472","version":2},"attestation_state":"computed","paper":{"title":"Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Haoxiang Jin, Qiguang Miao, Ronghan Li, Zixiang Lu","submitted_at":"2025-09-08T09:37:20Z","abstract_excerpt":"Large Language Models (LLMs) often generate inaccurate responses (hallucinations) when faced with questions beyond their knowledge scope. Retrieval-Augmented Generation (RAG) addresses this by leveraging external knowledge, but a critical challenge remains: determining whether retrieved contexts effectively enhance the model`s ability to answer specific queries. This challenge underscores the importance of knowledge boundary awareness, which current methods-relying on discrete labels or limited signals-fail to address adequately, as they overlook the rich information in LLMs` continuous intern"},"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":"2509.06472","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-09-08T09:37:20Z","cross_cats_sorted":[],"title_canon_sha256":"777eb9c035ef201e0b7a2d1967ac13e72df2fb4d30478763085018552fb308ad","abstract_canon_sha256":"25e441f00348ada0081d9571233d5649b4834d4ccaab4afb568d07bb004df957"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:12.480220Z","signature_b64":"L5ZBjr8tT9Of/PPS9SyCRWCkh5A/Xekx/nT3mTvR47sRXevshc3NivVnlfBj99GDJ6nz1+Y4sC7LjpZEYSRnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fe196c51e9200d87e9305fe2294a0163e47d7cca10a49cfdd76ea0fa7d6721b","last_reissued_at":"2026-07-05T12:07:12.479741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:12.479741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Haoxiang Jin, Qiguang Miao, Ronghan Li, Zixiang Lu","submitted_at":"2025-09-08T09:37:20Z","abstract_excerpt":"Large Language Models (LLMs) often generate inaccurate responses (hallucinations) when faced with questions beyond their knowledge scope. Retrieval-Augmented Generation (RAG) addresses this by leveraging external knowledge, but a critical challenge remains: determining whether retrieved contexts effectively enhance the model`s ability to answer specific queries. This challenge underscores the importance of knowledge boundary awareness, which current methods-relying on discrete labels or limited signals-fail to address adequately, as they overlook the rich information in LLMs` continuous intern"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06472","kind":"arxiv","version":2},"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/2509.06472/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":"2509.06472","created_at":"2026-07-05T12:07:12.479796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06472v2","created_at":"2026-07-05T12:07:12.479796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06472","created_at":"2026-07-05T12:07:12.479796+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7QZNRI6SIAN","created_at":"2026-07-05T12:07:12.479796+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7QZNRI6SIANQ7UT","created_at":"2026-07-05T12:07:12.479796+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7QZNRI6","created_at":"2026-07-05T12:07:12.479796+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/N7QZNRI6SIANQ7UTAX7CFFFACY","json":"https://pith.science/pith/N7QZNRI6SIANQ7UTAX7CFFFACY.json","graph_json":"https://pith.science/api/pith-number/N7QZNRI6SIANQ7UTAX7CFFFACY/graph.json","events_json":"https://pith.science/api/pith-number/N7QZNRI6SIANQ7UTAX7CFFFACY/events.json","paper":"https://pith.science/paper/N7QZNRI6"},"agent_actions":{"view_html":"https://pith.science/pith/N7QZNRI6SIANQ7UTAX7CFFFACY","download_json":"https://pith.science/pith/N7QZNRI6SIANQ7UTAX7CFFFACY.json","view_paper":"https://pith.science/paper/N7QZNRI6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06472&json=true","fetch_graph":"https://pith.science/api/pith-number/N7QZNRI6SIANQ7UTAX7CFFFACY/graph.json","fetch_events":"https://pith.science/api/pith-number/N7QZNRI6SIANQ7UTAX7CFFFACY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7QZNRI6SIANQ7UTAX7CFFFACY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7QZNRI6SIANQ7UTAX7CFFFACY/action/storage_attestation","attest_author":"https://pith.science/pith/N7QZNRI6SIANQ7UTAX7CFFFACY/action/author_attestation","sign_citation":"https://pith.science/pith/N7QZNRI6SIANQ7UTAX7CFFFACY/action/citation_signature","submit_replication":"https://pith.science/pith/N7QZNRI6SIANQ7UTAX7CFFFACY/action/replication_record"}},"created_at":"2026-07-05T12:07:12.479796+00:00","updated_at":"2026-07-05T12:07:12.479796+00:00"}