{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TEJPQ3IJDYR5NC45ZEGG5T6JAY","short_pith_number":"pith:TEJPQ3IJ","schema_version":"1.0","canonical_sha256":"9912f86d091e23d68b9dc90c6ecfc90601ee7b95a2ff44ae58b828ad014aea68","source":{"kind":"arxiv","id":"2405.08644","version":1},"attestation_state":"computed","paper":{"title":"Thinking Tokens for Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Herel, Tomas Mikolov","submitted_at":"2024-05-14T14:21:43Z","abstract_excerpt":"How much is 56 times 37? Language models often make mistakes in these types of difficult calculations. This is usually explained by their inability to perform complex reasoning. Since language models rely on large training sets and great memorization capability, naturally they are not equipped to run complex calculations. However, one can argue that humans also cannot perform this calculation immediately and require a considerable amount of time to construct the solution. In order to enhance the generalization capability of language models, and as a parallel to human behavior, we propose to us"},"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":"2405.08644","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-14T14:21:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"586de40c8d9a5629bd0e2868694617b9e098079e011f1bf203c3d034b7f193a6","abstract_canon_sha256":"e3fd0fa2557bbd855da622d25da6d73bdb1499c2abe7c35bc13a5b8318e875a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:03.434604Z","signature_b64":"eoIegqnv+kQDqqiwd3kNQ8MgnNL9ArtlwGOKupMA9dnSQdV5wonAmA/J+jt5T32bU1s+43k4N2JfHCZR0l7dDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9912f86d091e23d68b9dc90c6ecfc90601ee7b95a2ff44ae58b828ad014aea68","last_reissued_at":"2026-07-05T08:19:03.434094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:03.434094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thinking Tokens for Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Herel, Tomas Mikolov","submitted_at":"2024-05-14T14:21:43Z","abstract_excerpt":"How much is 56 times 37? Language models often make mistakes in these types of difficult calculations. This is usually explained by their inability to perform complex reasoning. Since language models rely on large training sets and great memorization capability, naturally they are not equipped to run complex calculations. However, one can argue that humans also cannot perform this calculation immediately and require a considerable amount of time to construct the solution. In order to enhance the generalization capability of language models, and as a parallel to human behavior, we propose to us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08644","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/2405.08644/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":"2405.08644","created_at":"2026-07-05T08:19:03.434162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.08644v1","created_at":"2026-07-05T08:19:03.434162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08644","created_at":"2026-07-05T08:19:03.434162+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEJPQ3IJDYR5","created_at":"2026-07-05T08:19:03.434162+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEJPQ3IJDYR5NC45","created_at":"2026-07-05T08:19:03.434162+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEJPQ3IJ","created_at":"2026-07-05T08:19:03.434162+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18089","citing_title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26797","citing_title":"Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2508.16745","citing_title":"Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2412.09413","citing_title":"Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2511.08983","citing_title":"SpiralThinker: Latent Reasoning through an Iterative Process with Text-Latent Interleaving","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2412.13171","citing_title":"Compressed Chain of Thought: Efficient Reasoning Through Dense Representations","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2506.06941","citing_title":"The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TEJPQ3IJDYR5NC45ZEGG5T6JAY","json":"https://pith.science/pith/TEJPQ3IJDYR5NC45ZEGG5T6JAY.json","graph_json":"https://pith.science/api/pith-number/TEJPQ3IJDYR5NC45ZEGG5T6JAY/graph.json","events_json":"https://pith.science/api/pith-number/TEJPQ3IJDYR5NC45ZEGG5T6JAY/events.json","paper":"https://pith.science/paper/TEJPQ3IJ"},"agent_actions":{"view_html":"https://pith.science/pith/TEJPQ3IJDYR5NC45ZEGG5T6JAY","download_json":"https://pith.science/pith/TEJPQ3IJDYR5NC45ZEGG5T6JAY.json","view_paper":"https://pith.science/paper/TEJPQ3IJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.08644&json=true","fetch_graph":"https://pith.science/api/pith-number/TEJPQ3IJDYR5NC45ZEGG5T6JAY/graph.json","fetch_events":"https://pith.science/api/pith-number/TEJPQ3IJDYR5NC45ZEGG5T6JAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEJPQ3IJDYR5NC45ZEGG5T6JAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEJPQ3IJDYR5NC45ZEGG5T6JAY/action/storage_attestation","attest_author":"https://pith.science/pith/TEJPQ3IJDYR5NC45ZEGG5T6JAY/action/author_attestation","sign_citation":"https://pith.science/pith/TEJPQ3IJDYR5NC45ZEGG5T6JAY/action/citation_signature","submit_replication":"https://pith.science/pith/TEJPQ3IJDYR5NC45ZEGG5T6JAY/action/replication_record"}},"created_at":"2026-07-05T08:19:03.434162+00:00","updated_at":"2026-07-05T08:19:03.434162+00:00"}