{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DQ2QB34ODENA2WGAF5J423C357","short_pith_number":"pith:DQ2QB34O","schema_version":"1.0","canonical_sha256":"1c3500ef8e191a0d58c02f53cd6c5befef1ca93d2a817dae7087cd0c924702db","source":{"kind":"arxiv","id":"2606.07108","version":1},"attestation_state":"computed","paper":{"title":"DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hui-Ling Zhen, Jinghua Piao, Libo Qin, Min Zhang, Tengyao Tu, Yong Li, Yulin Li, Zhoujun Wei, Zhuotao Tian","submitted_at":"2026-06-05T10:02:19Z","abstract_excerpt":"Recent advances in Large Reasoning Models (LRMs) demonstrate remarkable performance improvements by iteratively reflecting, exploring, and executing complex tasks, yet suffer from inefficiencies due to redundant reasoning, known as \"overthinking\". Existing methods to mitigate this issue either rely on static difficulty estimates or require task-specific training, and thus fail to adapt to the dynamic complexity during reasoning. In this work, we empirically show that the problem difficulty evolves dynamically throughout the reasoning process and is linearly encoded in the LRM's step-level embe"},"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":"2606.07108","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T10:02:19Z","cross_cats_sorted":[],"title_canon_sha256":"c349377bc2c88301e6598902f19078e8261ecc7343cd872b143c81ae5792b270","abstract_canon_sha256":"e5d3ed24bba4a3c7dd36de2fbe8f4958c33f3c31954270e3fa8421ffa79556d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:46.785107Z","signature_b64":"MSD5O6fKShnvIlRTS10VvdRxOAGfvYOAqnui8qWUZ6xU1aJOFHu5UUIpcUmWmNS5HxKQnqIX0wVWaMqllvctAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c3500ef8e191a0d58c02f53cd6c5befef1ca93d2a817dae7087cd0c924702db","last_reissued_at":"2026-06-08T01:04:46.784289Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:46.784289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hui-Ling Zhen, Jinghua Piao, Libo Qin, Min Zhang, Tengyao Tu, Yong Li, Yulin Li, Zhoujun Wei, Zhuotao Tian","submitted_at":"2026-06-05T10:02:19Z","abstract_excerpt":"Recent advances in Large Reasoning Models (LRMs) demonstrate remarkable performance improvements by iteratively reflecting, exploring, and executing complex tasks, yet suffer from inefficiencies due to redundant reasoning, known as \"overthinking\". Existing methods to mitigate this issue either rely on static difficulty estimates or require task-specific training, and thus fail to adapt to the dynamic complexity during reasoning. In this work, we empirically show that the problem difficulty evolves dynamically throughout the reasoning process and is linearly encoded in the LRM's step-level embe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07108","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/2606.07108/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":"2606.07108","created_at":"2026-06-08T01:04:46.784403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07108v1","created_at":"2026-06-08T01:04:46.784403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07108","created_at":"2026-06-08T01:04:46.784403+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQ2QB34ODENA","created_at":"2026-06-08T01:04:46.784403+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQ2QB34ODENA2WGA","created_at":"2026-06-08T01:04:46.784403+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQ2QB34O","created_at":"2026-06-08T01:04:46.784403+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/DQ2QB34ODENA2WGAF5J423C357","json":"https://pith.science/pith/DQ2QB34ODENA2WGAF5J423C357.json","graph_json":"https://pith.science/api/pith-number/DQ2QB34ODENA2WGAF5J423C357/graph.json","events_json":"https://pith.science/api/pith-number/DQ2QB34ODENA2WGAF5J423C357/events.json","paper":"https://pith.science/paper/DQ2QB34O"},"agent_actions":{"view_html":"https://pith.science/pith/DQ2QB34ODENA2WGAF5J423C357","download_json":"https://pith.science/pith/DQ2QB34ODENA2WGAF5J423C357.json","view_paper":"https://pith.science/paper/DQ2QB34O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07108&json=true","fetch_graph":"https://pith.science/api/pith-number/DQ2QB34ODENA2WGAF5J423C357/graph.json","fetch_events":"https://pith.science/api/pith-number/DQ2QB34ODENA2WGAF5J423C357/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQ2QB34ODENA2WGAF5J423C357/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQ2QB34ODENA2WGAF5J423C357/action/storage_attestation","attest_author":"https://pith.science/pith/DQ2QB34ODENA2WGAF5J423C357/action/author_attestation","sign_citation":"https://pith.science/pith/DQ2QB34ODENA2WGAF5J423C357/action/citation_signature","submit_replication":"https://pith.science/pith/DQ2QB34ODENA2WGAF5J423C357/action/replication_record"}},"created_at":"2026-06-08T01:04:46.784403+00:00","updated_at":"2026-06-08T01:04:46.784403+00:00"}