{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VINK7SBRCJUXLGNL2D4IUSGPVE","short_pith_number":"pith:VINK7SBR","schema_version":"1.0","canonical_sha256":"aa1aafc83112697599abd0f88a48cfa92855038d126967d0957ea383e6befb8c","source":{"kind":"arxiv","id":"2502.21030","version":1},"attestation_state":"computed","paper":{"title":"Beyond Words: A Latent Memory Approach to Internal Reasoning in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jos\\'e I. Orlicki","submitted_at":"2025-02-28T13:22:29Z","abstract_excerpt":"Recent advances in large language models (LLMs) have popularized the chain-of-thought (CoT) paradigm, in which models produce explicit reasoning steps in natural language. Although this approach improves interpretability and facilitates external auditing, it may not represent the most computationally efficient method for internal reasoning. In contrast, human cognition relies on implicit mental representations that recall past sensory and episodic information without requiring complete verbalization. In this paper, we propose a framework that integrates implicit mental representations into the"},"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":"2502.21030","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T13:22:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b5d3dd76334c401ad8b83b442fce9d67cc6bdba8b38868cbf741d54ea0a7f945","abstract_canon_sha256":"00e9e6241d9effd57bdb88fa747a03f62aa74b70ecb5705bbbb3906535bd3e08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:43.395686Z","signature_b64":"3Dizbwua20Ta4k+hGxMjv0pe34hAEuapkwABgknHqs9eUzzS8A+2CZ0guruqvhfyRQRiDZV5AChYNZBWIdjBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa1aafc83112697599abd0f88a48cfa92855038d126967d0957ea383e6befb8c","last_reissued_at":"2026-07-05T10:21:43.395080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:43.395080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Words: A Latent Memory Approach to Internal Reasoning in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jos\\'e I. Orlicki","submitted_at":"2025-02-28T13:22:29Z","abstract_excerpt":"Recent advances in large language models (LLMs) have popularized the chain-of-thought (CoT) paradigm, in which models produce explicit reasoning steps in natural language. Although this approach improves interpretability and facilitates external auditing, it may not represent the most computationally efficient method for internal reasoning. In contrast, human cognition relies on implicit mental representations that recall past sensory and episodic information without requiring complete verbalization. In this paper, we propose a framework that integrates implicit mental representations into the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.21030","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/2502.21030/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":"2502.21030","created_at":"2026-07-05T10:21:43.395146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.21030v1","created_at":"2026-07-05T10:21:43.395146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.21030","created_at":"2026-07-05T10:21:43.395146+00:00"},{"alias_kind":"pith_short_12","alias_value":"VINK7SBRCJUX","created_at":"2026-07-05T10:21:43.395146+00:00"},{"alias_kind":"pith_short_16","alias_value":"VINK7SBRCJUXLGNL","created_at":"2026-07-05T10:21:43.395146+00:00"},{"alias_kind":"pith_short_8","alias_value":"VINK7SBR","created_at":"2026-07-05T10:21:43.395146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.02547","citing_title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2511.02805","citing_title":"MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08221","citing_title":"NoisyCoconut: Counterfactual Consensus via Latent Space Reasoning","ref_index":93,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VINK7SBRCJUXLGNL2D4IUSGPVE","json":"https://pith.science/pith/VINK7SBRCJUXLGNL2D4IUSGPVE.json","graph_json":"https://pith.science/api/pith-number/VINK7SBRCJUXLGNL2D4IUSGPVE/graph.json","events_json":"https://pith.science/api/pith-number/VINK7SBRCJUXLGNL2D4IUSGPVE/events.json","paper":"https://pith.science/paper/VINK7SBR"},"agent_actions":{"view_html":"https://pith.science/pith/VINK7SBRCJUXLGNL2D4IUSGPVE","download_json":"https://pith.science/pith/VINK7SBRCJUXLGNL2D4IUSGPVE.json","view_paper":"https://pith.science/paper/VINK7SBR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.21030&json=true","fetch_graph":"https://pith.science/api/pith-number/VINK7SBRCJUXLGNL2D4IUSGPVE/graph.json","fetch_events":"https://pith.science/api/pith-number/VINK7SBRCJUXLGNL2D4IUSGPVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VINK7SBRCJUXLGNL2D4IUSGPVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VINK7SBRCJUXLGNL2D4IUSGPVE/action/storage_attestation","attest_author":"https://pith.science/pith/VINK7SBRCJUXLGNL2D4IUSGPVE/action/author_attestation","sign_citation":"https://pith.science/pith/VINK7SBRCJUXLGNL2D4IUSGPVE/action/citation_signature","submit_replication":"https://pith.science/pith/VINK7SBRCJUXLGNL2D4IUSGPVE/action/replication_record"}},"created_at":"2026-07-05T10:21:43.395146+00:00","updated_at":"2026-07-05T10:21:43.395146+00:00"}