{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RY2TXKHF67AJGWLTCK37JRCI5M","short_pith_number":"pith:RY2TXKHF","canonical_record":{"source":{"id":"2605.00505","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-01T08:30:52Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c8d19d1e2d7b2dc5b904e4265d694d77ace67307f6666cafb5a0645780d59049","abstract_canon_sha256":"e52c92cee4d72406a8cecf1b8f11ec55dc3251ac112d14b0cafb53ece80485d1"},"schema_version":"1.0"},"canonical_sha256":"8e353ba8e5f7c093597312b7f4c448eb0e6f55ca850c9e2852adc558b68adb24","source":{"kind":"arxiv","id":"2605.00505","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.00505","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.00505v2","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00505","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"pith_short_12","alias_value":"RY2TXKHF67AJ","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"pith_short_16","alias_value":"RY2TXKHF67AJGWLT","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"pith_short_8","alias_value":"RY2TXKHF","created_at":"2026-05-20T00:04:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RY2TXKHF67AJGWLTCK37JRCI5M","target":"record","payload":{"canonical_record":{"source":{"id":"2605.00505","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-01T08:30:52Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c8d19d1e2d7b2dc5b904e4265d694d77ace67307f6666cafb5a0645780d59049","abstract_canon_sha256":"e52c92cee4d72406a8cecf1b8f11ec55dc3251ac112d14b0cafb53ece80485d1"},"schema_version":"1.0"},"canonical_sha256":"8e353ba8e5f7c093597312b7f4c448eb0e6f55ca850c9e2852adc558b68adb24","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:33.299666Z","signature_b64":"A03M5Hya3CyW+MhQGBoO8j3FQPRoIAsLPcRV1BynwXv4CTT9RdS0j8hgG4nbdqQ7e1sR4FF13MiHrE6GLrE5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e353ba8e5f7c093597312b7f4c448eb0e6f55ca850c9e2852adc558b68adb24","last_reissued_at":"2026-05-20T00:04:33.298604Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:33.298604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.00505","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EBozHUt13sKpYVmyMgMJs1yXhoag93GkCcG2Did9tl7BNT5tD0bxPpjuswaIkz5DmuB38TkTR5tXG6ETb7+OAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T20:33:23.112277Z"},"content_sha256":"faa4ee8b98f334857b67b96e7dd1172a5ae90752648de4837ce0826eb633cb2a","schema_version":"1.0","event_id":"sha256:faa4ee8b98f334857b67b96e7dd1172a5ae90752648de4837ce0826eb633cb2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RY2TXKHF67AJGWLTCK37JRCI5M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Denoising to maximize evidence density and verifiability becomes the central task in information retrieval for large language models.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Cehao Yang, Fanpu Cao, Hao Liu, Hui Xiong, Liang Sun, Lu Dai, Ziyang Rao","submitted_at":"2026-05-01T08:30:52Z","abstract_excerpt":"Modern information retrieval (IR) is no longer consumed primarily by humans but increasingly by large language models (LLMs) via retrieval-augmented generation (RAG) and agentic search. Unlike human users, LLMs are constrained by limited attention budgets and are uniquely vulnerable to noise; misleading or irrelevant information is no longer just a nuisance, but a direct cause of hallucinations and reasoning failures. In this perspective paper, we argue that denoising-maximizing usable evidence density and verifiability within a context window-is becoming the primary bottleneck across the full"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"denoising—maximizing usable evidence density and verifiability within a context window—is becoming the primary bottleneck across the full information access pipeline","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLMs' limited attention budgets and unique vulnerability to noise represent a fundamental paradigm shift in IR that requires a new denoising-first framework, rather than incremental extensions of existing relevance and quality techniques.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Denoising to maximize usable evidence density and verifiability is becoming the primary bottleneck in LLM-oriented information retrieval, conceptualized via a four-stage framework and addressed through a pipeline taxonomy of optimization techniques.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Denoising to maximize evidence density and verifiability becomes the central task in information retrieval for large language models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"75d40d34c9b699fe154c52af6251feae575b826e381e2a413e6e7a5067a15fb7"},"source":{"id":"2605.00505","kind":"arxiv","version":2},"verdict":{"id":"2e0c95ea-5901-4eb9-9730-df21acbec9c5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T18:50:00.916148Z","strongest_claim":"denoising—maximizing usable evidence density and verifiability within a context window—is becoming the primary bottleneck across the full information access pipeline","one_line_summary":"Denoising to maximize usable evidence density and verifiability is becoming the primary bottleneck in LLM-oriented information retrieval, conceptualized via a four-stage framework and addressed through a pipeline taxonomy of optimization techniques.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLMs' limited attention budgets and unique vulnerability to noise represent a fundamental paradigm shift in IR that requires a new denoising-first framework, rather than incremental extensions of existing relevance and quality techniques.","pith_extraction_headline":"Denoising to maximize evidence density and verifiability becomes the central task in information retrieval for large language models."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.00505/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T18:06:21.354858Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6c094512fddda63e4659b38e9d4dd198244ccd9d5891a40a004b49592e58816b"},"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"},"verdict_id":"2e0c95ea-5901-4eb9-9730-df21acbec9c5"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2f37gIm3dqb1jsWPuKxGpXkBgyz6HSZ0Q/pKqS0YIo9MK0uYAIMQduUzigO7jIPRWevR71ujVtFWjX1ipc0BDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T20:33:23.112977Z"},"content_sha256":"9e997a3e3493a889cb72e54119480604f3d98fefc75024720e2b4e2f83f43c0d","schema_version":"1.0","event_id":"sha256:9e997a3e3493a889cb72e54119480604f3d98fefc75024720e2b4e2f83f43c0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RY2TXKHF67AJGWLTCK37JRCI5M/bundle.json","state_url":"https://pith.science/pith/RY2TXKHF67AJGWLTCK37JRCI5M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RY2TXKHF67AJGWLTCK37JRCI5M/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-29T20:33:23Z","links":{"resolver":"https://pith.science/pith/RY2TXKHF67AJGWLTCK37JRCI5M","bundle":"https://pith.science/pith/RY2TXKHF67AJGWLTCK37JRCI5M/bundle.json","state":"https://pith.science/pith/RY2TXKHF67AJGWLTCK37JRCI5M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RY2TXKHF67AJGWLTCK37JRCI5M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RY2TXKHF67AJGWLTCK37JRCI5M","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e52c92cee4d72406a8cecf1b8f11ec55dc3251ac112d14b0cafb53ece80485d1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-01T08:30:52Z","title_canon_sha256":"c8d19d1e2d7b2dc5b904e4265d694d77ace67307f6666cafb5a0645780d59049"},"schema_version":"1.0","source":{"id":"2605.00505","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.00505","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.00505v2","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00505","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"pith_short_12","alias_value":"RY2TXKHF67AJ","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"pith_short_16","alias_value":"RY2TXKHF67AJGWLT","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"pith_short_8","alias_value":"RY2TXKHF","created_at":"2026-05-20T00:04:33Z"}],"graph_snapshots":[{"event_id":"sha256:9e997a3e3493a889cb72e54119480604f3d98fefc75024720e2b4e2f83f43c0d","target":"graph","created_at":"2026-05-20T00:04:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"denoising—maximizing usable evidence density and verifiability within a context window—is becoming the primary bottleneck across the full information access pipeline"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That LLMs' limited attention budgets and unique vulnerability to noise represent a fundamental paradigm shift in IR that requires a new denoising-first framework, rather than incremental extensions of existing relevance and quality techniques."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Denoising to maximize usable evidence density and verifiability is becoming the primary bottleneck in LLM-oriented information retrieval, conceptualized via a four-stage framework and addressed through a pipeline taxonomy of optimization techniques."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Denoising to maximize evidence density and verifiability becomes the central task in information retrieval for large language models."}],"snapshot_sha256":"75d40d34c9b699fe154c52af6251feae575b826e381e2a413e6e7a5067a15fb7"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T18:06:21.354858Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.00505/integrity.json","findings":[],"snapshot_sha256":"6c094512fddda63e4659b38e9d4dd198244ccd9d5891a40a004b49592e58816b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern information retrieval (IR) is no longer consumed primarily by humans but increasingly by large language models (LLMs) via retrieval-augmented generation (RAG) and agentic search. Unlike human users, LLMs are constrained by limited attention budgets and are uniquely vulnerable to noise; misleading or irrelevant information is no longer just a nuisance, but a direct cause of hallucinations and reasoning failures. In this perspective paper, we argue that denoising-maximizing usable evidence density and verifiability within a context window-is becoming the primary bottleneck across the full","authors_text":"Cehao Yang, Fanpu Cao, Hao Liu, Hui Xiong, Liang Sun, Lu Dai, Ziyang Rao","cross_cats":["cs.AI","cs.CL"],"headline":"Denoising to maximize evidence density and verifiability becomes the central task in information retrieval for large language models.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-01T08:30:52Z","title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.00505","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-09T18:50:00.916148Z","id":"2e0c95ea-5901-4eb9-9730-df21acbec9c5","model_set":{"reader":"grok-4.3"},"one_line_summary":"Denoising to maximize usable evidence density and verifiability is becoming the primary bottleneck in LLM-oriented information retrieval, conceptualized via a four-stage framework and addressed through a pipeline taxonomy of optimization techniques.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Denoising to maximize evidence density and verifiability becomes the central task in information retrieval for large language models.","strongest_claim":"denoising—maximizing usable evidence density and verifiability within a context window—is becoming the primary bottleneck across the full information access pipeline","weakest_assumption":"That LLMs' limited attention budgets and unique vulnerability to noise represent a fundamental paradigm shift in IR that requires a new denoising-first framework, rather than incremental extensions of existing relevance and quality techniques."}},"verdict_id":"2e0c95ea-5901-4eb9-9730-df21acbec9c5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:faa4ee8b98f334857b67b96e7dd1172a5ae90752648de4837ce0826eb633cb2a","target":"record","created_at":"2026-05-20T00:04:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e52c92cee4d72406a8cecf1b8f11ec55dc3251ac112d14b0cafb53ece80485d1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-01T08:30:52Z","title_canon_sha256":"c8d19d1e2d7b2dc5b904e4265d694d77ace67307f6666cafb5a0645780d59049"},"schema_version":"1.0","source":{"id":"2605.00505","kind":"arxiv","version":2}},"canonical_sha256":"8e353ba8e5f7c093597312b7f4c448eb0e6f55ca850c9e2852adc558b68adb24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e353ba8e5f7c093597312b7f4c448eb0e6f55ca850c9e2852adc558b68adb24","first_computed_at":"2026-05-20T00:04:33.298604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:33.298604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A03M5Hya3CyW+MhQGBoO8j3FQPRoIAsLPcRV1BynwXv4CTT9RdS0j8hgG4nbdqQ7e1sR4FF13MiHrE6GLrE5BA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:33.299666Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.00505","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:faa4ee8b98f334857b67b96e7dd1172a5ae90752648de4837ce0826eb633cb2a","sha256:9e997a3e3493a889cb72e54119480604f3d98fefc75024720e2b4e2f83f43c0d"],"state_sha256":"746456dce231ed0d3d8f5260270bed2760b16a0d29819ce4e7e728df3c687968"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FwSm2BwmG9sHgpGALlDClbL7QYBfMswwjXToB1eN0g3DGzmLvAGEw/oW6avghbMh/+VSRBn52DExEvwRq88LAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T20:33:23.116847Z","bundle_sha256":"1fd502357aab1a5132da7347d3169b72a697ec669bf7a4104c3e1bb65fc48668"}}