{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SQOT3UAKX3AC2YV2UDRPYYOVCA","short_pith_number":"pith:SQOT3UAK","schema_version":"1.0","canonical_sha256":"941d3dd00abec02d62baa0e2fc61d5101e55b23b8c0bc0ed917233ecaacb9346","source":{"kind":"arxiv","id":"2507.00653","version":1},"attestation_state":"computed","paper":{"title":"Cognitive Load-Aware Inference: A Neuro-Symbolic Framework for Optimizing the Token Economy of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Yilun Zhang","submitted_at":"2025-07-01T10:51:18Z","abstract_excerpt":"The escalating computational costs of Large Language Model (LLM) inference have become a critical barrier to their widespread and sustainable deployment. While existing optimization strategies are effective, they are predominantly based on statistical heuristics or architectural modifications, lacking a guiding cognitive theory to manage the inference process itself. This paper aims to bridge this gap by introducing a novel paradigm: the Cognitive Load-Aware Inference (CLAI) framework, which operationalizes principles from Cognitive Load Theory (CLT) and neuroscience for LLM inference. We form"},"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":"2507.00653","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T10:51:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84df9ed024e6f143187f496263d7e4e54ccd49f5c6acceb5ae1a8e2f4a7fbd53","abstract_canon_sha256":"d41cac8d978d8bb1e55b335a4d98ec47177f60b023a1a829ec40e3c1c22c8f70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:12.351587Z","signature_b64":"Qa1JuJKDasoR+XJwZ0eoSYkqnO53YF6yJMquUuajc6vTGaCJM2h8OgpUNuWBIIopcYwgd/C5ARDgMSYeDXHRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"941d3dd00abec02d62baa0e2fc61d5101e55b23b8c0bc0ed917233ecaacb9346","last_reissued_at":"2026-07-05T11:30:12.351018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:12.351018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cognitive Load-Aware Inference: A Neuro-Symbolic Framework for Optimizing the Token Economy of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Yilun Zhang","submitted_at":"2025-07-01T10:51:18Z","abstract_excerpt":"The escalating computational costs of Large Language Model (LLM) inference have become a critical barrier to their widespread and sustainable deployment. While existing optimization strategies are effective, they are predominantly based on statistical heuristics or architectural modifications, lacking a guiding cognitive theory to manage the inference process itself. This paper aims to bridge this gap by introducing a novel paradigm: the Cognitive Load-Aware Inference (CLAI) framework, which operationalizes principles from Cognitive Load Theory (CLT) and neuroscience for LLM inference. We form"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00653","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/2507.00653/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":"2507.00653","created_at":"2026-07-05T11:30:12.351080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00653v1","created_at":"2026-07-05T11:30:12.351080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00653","created_at":"2026-07-05T11:30:12.351080+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQOT3UAKX3AC","created_at":"2026-07-05T11:30:12.351080+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQOT3UAKX3AC2YV2","created_at":"2026-07-05T11:30:12.351080+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQOT3UAK","created_at":"2026-07-05T11:30:12.351080+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.19827","citing_title":"When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SQOT3UAKX3AC2YV2UDRPYYOVCA","json":"https://pith.science/pith/SQOT3UAKX3AC2YV2UDRPYYOVCA.json","graph_json":"https://pith.science/api/pith-number/SQOT3UAKX3AC2YV2UDRPYYOVCA/graph.json","events_json":"https://pith.science/api/pith-number/SQOT3UAKX3AC2YV2UDRPYYOVCA/events.json","paper":"https://pith.science/paper/SQOT3UAK"},"agent_actions":{"view_html":"https://pith.science/pith/SQOT3UAKX3AC2YV2UDRPYYOVCA","download_json":"https://pith.science/pith/SQOT3UAKX3AC2YV2UDRPYYOVCA.json","view_paper":"https://pith.science/paper/SQOT3UAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00653&json=true","fetch_graph":"https://pith.science/api/pith-number/SQOT3UAKX3AC2YV2UDRPYYOVCA/graph.json","fetch_events":"https://pith.science/api/pith-number/SQOT3UAKX3AC2YV2UDRPYYOVCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQOT3UAKX3AC2YV2UDRPYYOVCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQOT3UAKX3AC2YV2UDRPYYOVCA/action/storage_attestation","attest_author":"https://pith.science/pith/SQOT3UAKX3AC2YV2UDRPYYOVCA/action/author_attestation","sign_citation":"https://pith.science/pith/SQOT3UAKX3AC2YV2UDRPYYOVCA/action/citation_signature","submit_replication":"https://pith.science/pith/SQOT3UAKX3AC2YV2UDRPYYOVCA/action/replication_record"}},"created_at":"2026-07-05T11:30:12.351080+00:00","updated_at":"2026-07-05T11:30:12.351080+00:00"}