{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BDFEV4GAEKWCNH6UABYGBUFZVI","short_pith_number":"pith:BDFEV4GA","schema_version":"1.0","canonical_sha256":"08ca4af0c022ac269fd4007060d0b9aa2af5bc86d42c3db8cb606ee6628e3f3b","source":{"kind":"arxiv","id":"2502.10954","version":2},"attestation_state":"computed","paper":{"title":"Learning to Stop Overthinking at Test Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hieu Tran Bao, Hoang Thanh-Tung, Nguyen Cong Dat, Nguyen Duc Anh","submitted_at":"2025-02-16T02:17:05Z","abstract_excerpt":"Test time scaling is currently one of the most active research areas that shows promise after training time scaling has reached its limits. Deep-thinking (DT) models are a class of recurrent models that can perform easy-to-hard generalization by assigning more compute to harder test samples. However, due to their inability to determine the complexity of a test sample, DT models have to use a large amount of computation for both easy and hard test samples. Excessive test time computation is wasteful and can cause the ``overthinking'' problem where more test time computation leads to worse resul"},"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":"2502.10954","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-16T02:17:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"560c2dfba878a73b3b62d47e00ab2a5fc503c3aa217c730a696bdf8e052ee3cb","abstract_canon_sha256":"79ae09abfc06238739d5447ef44ed64f67a66c5728521c70d12252cdb69026e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:49.648629Z","signature_b64":"lW48Itb57EtfecVV4yksrDPrHFjU5ur6LAYnP/kMf+Y4ZKyanAeSxBcGbb00i8t5ztitIAU6srUebZxUNf86Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08ca4af0c022ac269fd4007060d0b9aa2af5bc86d42c3db8cb606ee6628e3f3b","last_reissued_at":"2026-07-05T10:15:49.648110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:49.648110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Stop Overthinking at Test Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hieu Tran Bao, Hoang Thanh-Tung, Nguyen Cong Dat, Nguyen Duc Anh","submitted_at":"2025-02-16T02:17:05Z","abstract_excerpt":"Test time scaling is currently one of the most active research areas that shows promise after training time scaling has reached its limits. Deep-thinking (DT) models are a class of recurrent models that can perform easy-to-hard generalization by assigning more compute to harder test samples. However, due to their inability to determine the complexity of a test sample, DT models have to use a large amount of computation for both easy and hard test samples. Excessive test time computation is wasteful and can cause the ``overthinking'' problem where more test time computation leads to worse resul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10954","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/2502.10954/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":"2502.10954","created_at":"2026-07-05T10:15:49.648164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10954v2","created_at":"2026-07-05T10:15:49.648164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10954","created_at":"2026-07-05T10:15:49.648164+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDFEV4GAEKWC","created_at":"2026-07-05T10:15:49.648164+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDFEV4GAEKWCNH6U","created_at":"2026-07-05T10:15:49.648164+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDFEV4GA","created_at":"2026-07-05T10:15:49.648164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BDFEV4GAEKWCNH6UABYGBUFZVI","json":"https://pith.science/pith/BDFEV4GAEKWCNH6UABYGBUFZVI.json","graph_json":"https://pith.science/api/pith-number/BDFEV4GAEKWCNH6UABYGBUFZVI/graph.json","events_json":"https://pith.science/api/pith-number/BDFEV4GAEKWCNH6UABYGBUFZVI/events.json","paper":"https://pith.science/paper/BDFEV4GA"},"agent_actions":{"view_html":"https://pith.science/pith/BDFEV4GAEKWCNH6UABYGBUFZVI","download_json":"https://pith.science/pith/BDFEV4GAEKWCNH6UABYGBUFZVI.json","view_paper":"https://pith.science/paper/BDFEV4GA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10954&json=true","fetch_graph":"https://pith.science/api/pith-number/BDFEV4GAEKWCNH6UABYGBUFZVI/graph.json","fetch_events":"https://pith.science/api/pith-number/BDFEV4GAEKWCNH6UABYGBUFZVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDFEV4GAEKWCNH6UABYGBUFZVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDFEV4GAEKWCNH6UABYGBUFZVI/action/storage_attestation","attest_author":"https://pith.science/pith/BDFEV4GAEKWCNH6UABYGBUFZVI/action/author_attestation","sign_citation":"https://pith.science/pith/BDFEV4GAEKWCNH6UABYGBUFZVI/action/citation_signature","submit_replication":"https://pith.science/pith/BDFEV4GAEKWCNH6UABYGBUFZVI/action/replication_record"}},"created_at":"2026-07-05T10:15:49.648164+00:00","updated_at":"2026-07-05T10:15:49.648164+00:00"}