{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TUBHIXALJ4MKVV4Q3UJ5FCWKZG","short_pith_number":"pith:TUBHIXAL","schema_version":"1.0","canonical_sha256":"9d02745c0b4f18aad790dd13d28acac98a0ea70b3af0565f10ca2e708e40743f","source":{"kind":"arxiv","id":"2502.19298","version":1},"attestation_state":"computed","paper":{"title":"Agent-centric Information Access","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Evangelos Kanoulas, Gabrielle Poerwawinata, Jingfen Qiao, Panagiotis Eustratiadis, Vaishali Pal, Yongkang Li, Yougang Lyu, Zihan Wang","submitted_at":"2025-02-26T16:56:19Z","abstract_excerpt":"As large language models (LLMs) become more specialized, we envision a future where millions of expert LLMs exist, each trained on proprietary data and excelling in specific domains. In such a system, answering a query requires selecting a small subset of relevant models, querying them efficiently, and synthesizing their responses. This paper introduces a framework for agent-centric information access, where LLMs function as knowledge agents that are dynamically ranked and queried based on their demonstrated expertise. Unlike traditional document retrieval, this approach requires inferring exp"},"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":"2502.19298","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-26T16:56:19Z","cross_cats_sorted":[],"title_canon_sha256":"80020dfc830cea89af71871a021c80149fdd4d126a52d0698ca4af62e33942e9","abstract_canon_sha256":"2c30435efa1f35260237e99fdd504b8cdc50f1fa7c693ff18f6a9019c3ac28c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:29.632550Z","signature_b64":"zDUc+PAByza766x1xF22UytW18D/ZgrqVFHpTWwiW3+Een94MXloyOEY1CKVwmIimAKjBOFhQCayCJaggZQ7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d02745c0b4f18aad790dd13d28acac98a0ea70b3af0565f10ca2e708e40743f","last_reissued_at":"2026-07-05T10:20:29.632020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:29.632020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent-centric Information Access","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Evangelos Kanoulas, Gabrielle Poerwawinata, Jingfen Qiao, Panagiotis Eustratiadis, Vaishali Pal, Yongkang Li, Yougang Lyu, Zihan Wang","submitted_at":"2025-02-26T16:56:19Z","abstract_excerpt":"As large language models (LLMs) become more specialized, we envision a future where millions of expert LLMs exist, each trained on proprietary data and excelling in specific domains. In such a system, answering a query requires selecting a small subset of relevant models, querying them efficiently, and synthesizing their responses. This paper introduces a framework for agent-centric information access, where LLMs function as knowledge agents that are dynamically ranked and queried based on their demonstrated expertise. Unlike traditional document retrieval, this approach requires inferring exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19298","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/2502.19298/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":"2502.19298","created_at":"2026-07-05T10:20:29.632081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.19298v1","created_at":"2026-07-05T10:20:29.632081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19298","created_at":"2026-07-05T10:20:29.632081+00:00"},{"alias_kind":"pith_short_12","alias_value":"TUBHIXALJ4MK","created_at":"2026-07-05T10:20:29.632081+00:00"},{"alias_kind":"pith_short_16","alias_value":"TUBHIXALJ4MKVV4Q","created_at":"2026-07-05T10:20:29.632081+00:00"},{"alias_kind":"pith_short_8","alias_value":"TUBHIXAL","created_at":"2026-07-05T10:20:29.632081+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14256","citing_title":"Evaluation of Agents under Simulated AI Marketplace Dynamics","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TUBHIXALJ4MKVV4Q3UJ5FCWKZG","json":"https://pith.science/pith/TUBHIXALJ4MKVV4Q3UJ5FCWKZG.json","graph_json":"https://pith.science/api/pith-number/TUBHIXALJ4MKVV4Q3UJ5FCWKZG/graph.json","events_json":"https://pith.science/api/pith-number/TUBHIXALJ4MKVV4Q3UJ5FCWKZG/events.json","paper":"https://pith.science/paper/TUBHIXAL"},"agent_actions":{"view_html":"https://pith.science/pith/TUBHIXALJ4MKVV4Q3UJ5FCWKZG","download_json":"https://pith.science/pith/TUBHIXALJ4MKVV4Q3UJ5FCWKZG.json","view_paper":"https://pith.science/paper/TUBHIXAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.19298&json=true","fetch_graph":"https://pith.science/api/pith-number/TUBHIXALJ4MKVV4Q3UJ5FCWKZG/graph.json","fetch_events":"https://pith.science/api/pith-number/TUBHIXALJ4MKVV4Q3UJ5FCWKZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TUBHIXALJ4MKVV4Q3UJ5FCWKZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TUBHIXALJ4MKVV4Q3UJ5FCWKZG/action/storage_attestation","attest_author":"https://pith.science/pith/TUBHIXALJ4MKVV4Q3UJ5FCWKZG/action/author_attestation","sign_citation":"https://pith.science/pith/TUBHIXALJ4MKVV4Q3UJ5FCWKZG/action/citation_signature","submit_replication":"https://pith.science/pith/TUBHIXALJ4MKVV4Q3UJ5FCWKZG/action/replication_record"}},"created_at":"2026-07-05T10:20:29.632081+00:00","updated_at":"2026-07-05T10:20:29.632081+00:00"}