{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GF2T6XK5FKJ2AJB7LXIDNTLCOM","short_pith_number":"pith:GF2T6XK5","schema_version":"1.0","canonical_sha256":"31753f5d5d2a93a0243f5dd036cd62733a92b070b21bc74e16b34ab2c411b964","source":{"kind":"arxiv","id":"2310.10845","version":2},"attestation_state":"computed","paper":{"title":"CoTFormer: A Chain-of-Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Amirkeivan Mohtashami, Martin Jaggi, Matteo Pagliardini","submitted_at":"2023-10-16T21:37:34Z","abstract_excerpt":"Scaling language models to larger and deeper sizes has led to significant boosts in performance. Even though the size of these models limits their application in compute-constrained environments, the race to continually develop ever larger and deeper foundational models is underway. At the same time -- regardless of the model size -- task-specific techniques continue to play a pivotal role in achieving optimal downstream performance. One of these techniques, called Chain-of-Thought (CoT), is particularly interesting since, as we point out in this work, it resembles employing a deeper transform"},"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":"2310.10845","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T21:37:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b27ef555d1107be0c3c4a4a54a1182dfb9161f565b7c2dd8f34be1b23394c7c2","abstract_canon_sha256":"01d95b8aa5009923724bd9300495dae71b86bd5d6161eb054a45453b37e49353"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:31.959153Z","signature_b64":"4KNvVv3gHRF+OvqcR0m8Mo4LEeqqdRT7Qd4hJM4YtRSMvYAoDgJX9jvh8GCcCDxqUGTHr5YAXrTknKxL64kPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31753f5d5d2a93a0243f5dd036cd62733a92b070b21bc74e16b34ab2c411b964","last_reissued_at":"2026-07-05T08:55:31.958741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:31.958741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoTFormer: A Chain-of-Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Amirkeivan Mohtashami, Martin Jaggi, Matteo Pagliardini","submitted_at":"2023-10-16T21:37:34Z","abstract_excerpt":"Scaling language models to larger and deeper sizes has led to significant boosts in performance. Even though the size of these models limits their application in compute-constrained environments, the race to continually develop ever larger and deeper foundational models is underway. At the same time -- regardless of the model size -- task-specific techniques continue to play a pivotal role in achieving optimal downstream performance. One of these techniques, called Chain-of-Thought (CoT), is particularly interesting since, as we point out in this work, it resembles employing a deeper transform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10845","kind":"arxiv","version":2},"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/2310.10845/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":"2310.10845","created_at":"2026-07-05T08:55:31.958797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10845v2","created_at":"2026-07-05T08:55:31.958797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10845","created_at":"2026-07-05T08:55:31.958797+00:00"},{"alias_kind":"pith_short_12","alias_value":"GF2T6XK5FKJ2","created_at":"2026-07-05T08:55:31.958797+00:00"},{"alias_kind":"pith_short_16","alias_value":"GF2T6XK5FKJ2AJB7","created_at":"2026-07-05T08:55:31.958797+00:00"},{"alias_kind":"pith_short_8","alias_value":"GF2T6XK5","created_at":"2026-07-05T08:55:31.958797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20737","citing_title":"Repeated Shared Access Enables Grokking, but Edit Propagation Depends on an Addressable Memory","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26733","citing_title":"Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26106","citing_title":"Looped Diffusion Language Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07604","citing_title":"Contribution Weights: A Geometrical Analysis of Self-Attention Transformers","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02181","citing_title":"A Survey of Scaling in Large Language Model Reasoning","ref_index":139,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19376","citing_title":"Generative Recursive Reasoning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19376","citing_title":"Generative Recursive Reasoning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03206","citing_title":"Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08299","citing_title":"SeLaR: Selective Latent Reasoning in Large Language Models","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GF2T6XK5FKJ2AJB7LXIDNTLCOM","json":"https://pith.science/pith/GF2T6XK5FKJ2AJB7LXIDNTLCOM.json","graph_json":"https://pith.science/api/pith-number/GF2T6XK5FKJ2AJB7LXIDNTLCOM/graph.json","events_json":"https://pith.science/api/pith-number/GF2T6XK5FKJ2AJB7LXIDNTLCOM/events.json","paper":"https://pith.science/paper/GF2T6XK5"},"agent_actions":{"view_html":"https://pith.science/pith/GF2T6XK5FKJ2AJB7LXIDNTLCOM","download_json":"https://pith.science/pith/GF2T6XK5FKJ2AJB7LXIDNTLCOM.json","view_paper":"https://pith.science/paper/GF2T6XK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10845&json=true","fetch_graph":"https://pith.science/api/pith-number/GF2T6XK5FKJ2AJB7LXIDNTLCOM/graph.json","fetch_events":"https://pith.science/api/pith-number/GF2T6XK5FKJ2AJB7LXIDNTLCOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GF2T6XK5FKJ2AJB7LXIDNTLCOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GF2T6XK5FKJ2AJB7LXIDNTLCOM/action/storage_attestation","attest_author":"https://pith.science/pith/GF2T6XK5FKJ2AJB7LXIDNTLCOM/action/author_attestation","sign_citation":"https://pith.science/pith/GF2T6XK5FKJ2AJB7LXIDNTLCOM/action/citation_signature","submit_replication":"https://pith.science/pith/GF2T6XK5FKJ2AJB7LXIDNTLCOM/action/replication_record"}},"created_at":"2026-07-05T08:55:31.958797+00:00","updated_at":"2026-07-05T08:55:31.958797+00:00"}