{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6O2EWFNBIDXIJKS33G7BBNOGZJ","short_pith_number":"pith:6O2EWFNB","schema_version":"1.0","canonical_sha256":"f3b44b15a140ee84aa5bd9be10b5c6ca58b1f317a31e2a712e41e361518eef16","source":{"kind":"arxiv","id":"2504.21659","version":2},"attestation_state":"computed","paper":{"title":"Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Dacheng Tao, Haiying He, Haotian Luo, Jinluan Yang, Li Shen, Naiqiang Tan, Rui Liu, Xiaochun Cao, Yibo Wang","submitted_at":"2025-04-30T14:01:45Z","abstract_excerpt":"Recently, long-thought reasoning models achieve strong performance on complex reasoning tasks, but often incur substantial inference overhead, making efficiency a critical concern. Our empirical analysis reveals that the benefit of using Long-CoT varies across problems: while some problems require elaborate reasoning, others show no improvement, or even degraded accuracy. This motivates adaptive reasoning strategies that tailor reasoning depth to the input. However, prior work primarily reduces redundancy within long reasoning paths, limiting exploration of more efficient strategies beyond the"},"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":"2504.21659","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-30T14:01:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0ffe4b3f624c8b91d4ad5688090400d6b65dcb933d2994e5b5cfba8f06043bde","abstract_canon_sha256":"9dda98c8ee33eb6bdce8f88e991cff43e2ac517c467378171f234264bb2878ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:31.298140Z","signature_b64":"eTKJ6KNKyJxYBoniCIEPjYx31jaUg/kJcyH070qcBx1raIqVOLV8hPGXWkB30QeOJw/44pn5dz5OI7unqzFRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3b44b15a140ee84aa5bd9be10b5c6ca58b1f317a31e2a712e41e361518eef16","last_reissued_at":"2026-07-05T11:06:31.297621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:31.297621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Dacheng Tao, Haiying He, Haotian Luo, Jinluan Yang, Li Shen, Naiqiang Tan, Rui Liu, Xiaochun Cao, Yibo Wang","submitted_at":"2025-04-30T14:01:45Z","abstract_excerpt":"Recently, long-thought reasoning models achieve strong performance on complex reasoning tasks, but often incur substantial inference overhead, making efficiency a critical concern. Our empirical analysis reveals that the benefit of using Long-CoT varies across problems: while some problems require elaborate reasoning, others show no improvement, or even degraded accuracy. This motivates adaptive reasoning strategies that tailor reasoning depth to the input. However, prior work primarily reduces redundancy within long reasoning paths, limiting exploration of more efficient strategies beyond the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21659","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/2504.21659/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":"2504.21659","created_at":"2026-07-05T11:06:31.297683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21659v2","created_at":"2026-07-05T11:06:31.297683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21659","created_at":"2026-07-05T11:06:31.297683+00:00"},{"alias_kind":"pith_short_12","alias_value":"6O2EWFNBIDXI","created_at":"2026-07-05T11:06:31.297683+00:00"},{"alias_kind":"pith_short_16","alias_value":"6O2EWFNBIDXIJKS3","created_at":"2026-07-05T11:06:31.297683+00:00"},{"alias_kind":"pith_short_8","alias_value":"6O2EWFNB","created_at":"2026-07-05T11:06:31.297683+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19358","citing_title":"Taming the Thinker: Conditional Entropy Shaping for Adaptive LLM Reasoning","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2503.16419","citing_title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06165","citing_title":"Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost","ref_index":228,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6O2EWFNBIDXIJKS33G7BBNOGZJ","json":"https://pith.science/pith/6O2EWFNBIDXIJKS33G7BBNOGZJ.json","graph_json":"https://pith.science/api/pith-number/6O2EWFNBIDXIJKS33G7BBNOGZJ/graph.json","events_json":"https://pith.science/api/pith-number/6O2EWFNBIDXIJKS33G7BBNOGZJ/events.json","paper":"https://pith.science/paper/6O2EWFNB"},"agent_actions":{"view_html":"https://pith.science/pith/6O2EWFNBIDXIJKS33G7BBNOGZJ","download_json":"https://pith.science/pith/6O2EWFNBIDXIJKS33G7BBNOGZJ.json","view_paper":"https://pith.science/paper/6O2EWFNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21659&json=true","fetch_graph":"https://pith.science/api/pith-number/6O2EWFNBIDXIJKS33G7BBNOGZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6O2EWFNBIDXIJKS33G7BBNOGZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6O2EWFNBIDXIJKS33G7BBNOGZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6O2EWFNBIDXIJKS33G7BBNOGZJ/action/storage_attestation","attest_author":"https://pith.science/pith/6O2EWFNBIDXIJKS33G7BBNOGZJ/action/author_attestation","sign_citation":"https://pith.science/pith/6O2EWFNBIDXIJKS33G7BBNOGZJ/action/citation_signature","submit_replication":"https://pith.science/pith/6O2EWFNBIDXIJKS33G7BBNOGZJ/action/replication_record"}},"created_at":"2026-07-05T11:06:31.297683+00:00","updated_at":"2026-07-05T11:06:31.297683+00:00"}