{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WXOJFF4BU5ZE42PXP7YAFQ6P7O","short_pith_number":"pith:WXOJFF4B","schema_version":"1.0","canonical_sha256":"b5dc929781a7724e69f77ff002c3cffba76a43273c46bb67cb18f52a70aae258","source":{"kind":"arxiv","id":"2606.00683","version":1},"attestation_state":"computed","paper":{"title":"OCC-RAG: Optimal Cognitive Core for Faithful Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Gambashidze, Alla Chepurova, Andrey Galichin, Daria Pugacheva, Dmitrii Tarasov, Ivan Oseledets, Maksim Savkin, Mikhail Goncharov, Nikita Andriianov, Vasily Konovalov","submitted_at":"2026-05-30T11:42:19Z","abstract_excerpt":"Recent progress in the development of language models has been defined by scale, with each generation absorbing more of the world's knowledge into its weights. However, many practical applications benefit more from robust reasoning than from extensive parametric knowledge. In this setting, task-specialized small language models (SLMs) offer a principled design choice. We introduce Optimal Cognitive Core (OCC), a family of SLMs built around this premise. As a variant of OCC, we present OCC-RAG, optimized for faithful question answering (QA) grounded in the provided context. This task directly a"},"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":"2606.00683","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-30T11:42:19Z","cross_cats_sorted":[],"title_canon_sha256":"7b88d35e1695b5673d2ab54ca9c02bd6615004c22cbc2d3f12728efc94613930","abstract_canon_sha256":"07ef75c14780ca3cb8ccaf7e49c4e1091dc0a31e5a67cdc64f5f086133e9f92b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:02.607922Z","signature_b64":"J+AYccE9eDki7KQCzhX/dwVkOfZK9fJE6XpVKwpd5urKtJ10b8eA+o63ptQl5QTcf1Df4KGkP8zrkkuerBEDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5dc929781a7724e69f77ff002c3cffba76a43273c46bb67cb18f52a70aae258","last_reissued_at":"2026-06-02T01:04:02.607499Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:02.607499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OCC-RAG: Optimal Cognitive Core for Faithful Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Gambashidze, Alla Chepurova, Andrey Galichin, Daria Pugacheva, Dmitrii Tarasov, Ivan Oseledets, Maksim Savkin, Mikhail Goncharov, Nikita Andriianov, Vasily Konovalov","submitted_at":"2026-05-30T11:42:19Z","abstract_excerpt":"Recent progress in the development of language models has been defined by scale, with each generation absorbing more of the world's knowledge into its weights. However, many practical applications benefit more from robust reasoning than from extensive parametric knowledge. In this setting, task-specialized small language models (SLMs) offer a principled design choice. We introduce Optimal Cognitive Core (OCC), a family of SLMs built around this premise. As a variant of OCC, we present OCC-RAG, optimized for faithful question answering (QA) grounded in the provided context. This task directly a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00683","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/2606.00683/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":"2606.00683","created_at":"2026-06-02T01:04:02.607545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00683v1","created_at":"2026-06-02T01:04:02.607545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00683","created_at":"2026-06-02T01:04:02.607545+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXOJFF4BU5ZE","created_at":"2026-06-02T01:04:02.607545+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXOJFF4BU5ZE42PX","created_at":"2026-06-02T01:04:02.607545+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXOJFF4B","created_at":"2026-06-02T01:04:02.607545+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/WXOJFF4BU5ZE42PXP7YAFQ6P7O","json":"https://pith.science/pith/WXOJFF4BU5ZE42PXP7YAFQ6P7O.json","graph_json":"https://pith.science/api/pith-number/WXOJFF4BU5ZE42PXP7YAFQ6P7O/graph.json","events_json":"https://pith.science/api/pith-number/WXOJFF4BU5ZE42PXP7YAFQ6P7O/events.json","paper":"https://pith.science/paper/WXOJFF4B"},"agent_actions":{"view_html":"https://pith.science/pith/WXOJFF4BU5ZE42PXP7YAFQ6P7O","download_json":"https://pith.science/pith/WXOJFF4BU5ZE42PXP7YAFQ6P7O.json","view_paper":"https://pith.science/paper/WXOJFF4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00683&json=true","fetch_graph":"https://pith.science/api/pith-number/WXOJFF4BU5ZE42PXP7YAFQ6P7O/graph.json","fetch_events":"https://pith.science/api/pith-number/WXOJFF4BU5ZE42PXP7YAFQ6P7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXOJFF4BU5ZE42PXP7YAFQ6P7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXOJFF4BU5ZE42PXP7YAFQ6P7O/action/storage_attestation","attest_author":"https://pith.science/pith/WXOJFF4BU5ZE42PXP7YAFQ6P7O/action/author_attestation","sign_citation":"https://pith.science/pith/WXOJFF4BU5ZE42PXP7YAFQ6P7O/action/citation_signature","submit_replication":"https://pith.science/pith/WXOJFF4BU5ZE42PXP7YAFQ6P7O/action/replication_record"}},"created_at":"2026-06-02T01:04:02.607545+00:00","updated_at":"2026-06-02T01:04:02.607545+00:00"}