{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OWIH57BCMQSLR6E2FSWFZVYV7U","short_pith_number":"pith:OWIH57BC","schema_version":"1.0","canonical_sha256":"75907efc226424b8f89a2cac5cd715fd32f970de956fdc73d449c5b40c3fc760","source":{"kind":"arxiv","id":"2604.01161","version":2},"attestation_state":"computed","paper":{"title":"Reasoning Shift: How Context Silently Shortens LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"George Yakushev, Gleb Rodionov, Roman Garipov","submitted_at":"2026-04-01T17:14:18Z","abstract_excerpt":"Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks. However, the robustness of these reasoning behaviors remains underexplored. To investigate this, we conduct a systematic evaluation of multiple reasoning models across three scenarios: (1) problems augmented with lengthy, irrelevant context; (2) multi-turn conversational settings with independent tasks; and (3) problems presented as a subtask within a complex task. We observe an interesting p"},"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":"2604.01161","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-01T17:14:18Z","cross_cats_sorted":[],"title_canon_sha256":"90ae6e734d8f5df1256f0c66cb8e524f8466b70618649603aeee726f4f9f95bc","abstract_canon_sha256":"97d018cf94b6b5ce24a3b96079a48f9a5e493da4f2fb8288dfa9d23f36b203e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:49.363495Z","signature_b64":"jIUlB4GBjM5F9sJpzvrr9MrxtcacMtccxh3YvFvVQlcfLbtrnD3Ei9Kn5dS11UhpVCzpz34eD0m6tJGUzGsBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75907efc226424b8f89a2cac5cd715fd32f970de956fdc73d449c5b40c3fc760","last_reissued_at":"2026-06-04T01:09:49.362340Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:49.362340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning Shift: How Context Silently Shortens LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"George Yakushev, Gleb Rodionov, Roman Garipov","submitted_at":"2026-04-01T17:14:18Z","abstract_excerpt":"Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks. However, the robustness of these reasoning behaviors remains underexplored. To investigate this, we conduct a systematic evaluation of multiple reasoning models across three scenarios: (1) problems augmented with lengthy, irrelevant context; (2) multi-turn conversational settings with independent tasks; and (3) problems presented as a subtask within a complex task. We observe an interesting p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.01161","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/2604.01161/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":"2604.01161","created_at":"2026-06-04T01:09:49.362575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.01161v2","created_at":"2026-06-04T01:09:49.362575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.01161","created_at":"2026-06-04T01:09:49.362575+00:00"},{"alias_kind":"pith_short_12","alias_value":"OWIH57BCMQSL","created_at":"2026-06-04T01:09:49.362575+00:00"},{"alias_kind":"pith_short_16","alias_value":"OWIH57BCMQSLR6E2","created_at":"2026-06-04T01:09:49.362575+00:00"},{"alias_kind":"pith_short_8","alias_value":"OWIH57BC","created_at":"2026-06-04T01:09:49.362575+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/OWIH57BCMQSLR6E2FSWFZVYV7U","json":"https://pith.science/pith/OWIH57BCMQSLR6E2FSWFZVYV7U.json","graph_json":"https://pith.science/api/pith-number/OWIH57BCMQSLR6E2FSWFZVYV7U/graph.json","events_json":"https://pith.science/api/pith-number/OWIH57BCMQSLR6E2FSWFZVYV7U/events.json","paper":"https://pith.science/paper/OWIH57BC"},"agent_actions":{"view_html":"https://pith.science/pith/OWIH57BCMQSLR6E2FSWFZVYV7U","download_json":"https://pith.science/pith/OWIH57BCMQSLR6E2FSWFZVYV7U.json","view_paper":"https://pith.science/paper/OWIH57BC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.01161&json=true","fetch_graph":"https://pith.science/api/pith-number/OWIH57BCMQSLR6E2FSWFZVYV7U/graph.json","fetch_events":"https://pith.science/api/pith-number/OWIH57BCMQSLR6E2FSWFZVYV7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OWIH57BCMQSLR6E2FSWFZVYV7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OWIH57BCMQSLR6E2FSWFZVYV7U/action/storage_attestation","attest_author":"https://pith.science/pith/OWIH57BCMQSLR6E2FSWFZVYV7U/action/author_attestation","sign_citation":"https://pith.science/pith/OWIH57BCMQSLR6E2FSWFZVYV7U/action/citation_signature","submit_replication":"https://pith.science/pith/OWIH57BCMQSLR6E2FSWFZVYV7U/action/replication_record"}},"created_at":"2026-06-04T01:09:49.362575+00:00","updated_at":"2026-06-04T01:09:49.362575+00:00"}