{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BJWLOCZC3W345LAUQBMDCUZVMW","short_pith_number":"pith:BJWLOCZC","schema_version":"1.0","canonical_sha256":"0a6cb70b22ddb7ceac1480583153356590d5173cac9e5f14448a0da324869aeb","source":{"kind":"arxiv","id":"2507.05707","version":2},"attestation_state":"computed","paper":{"title":"Agentic-R1: Distilled Dual-Strategy Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Pranjal Aggarwal, Sean Welleck, Weihua Du, Yiming Yang","submitted_at":"2025-07-08T06:35:16Z","abstract_excerpt":"Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic via code execution, but often falter on complex logical tasks. We introduce a fine-tuning framework, DualDistill, that distills complementary reasoning strategies from multiple teachers into a unified student model. Using this approach, we train Agentic-R1, which dynamically selects the optimal strategy for each query, invoking tools for arithmetic and algorithmic problems, and using text-based reasoning for abstract "},"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":"2507.05707","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T06:35:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e059d17180a8b00abf1467a796c56e3087ce59b35a697fba52c3643d9b3fa3db","abstract_canon_sha256":"de6304c113ea4068acc8e0eb14a46c5796880514850fddf7251564ede4683379"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:03.278655Z","signature_b64":"PAR0TnXP3pMMoV5LJwRkKnuMq8+5U1gqJajvbb62pcFv2dUw9ZaPS3D/KWpDWWmUyxImEJzTFPtFNiKtfVTAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a6cb70b22ddb7ceac1480583153356590d5173cac9e5f14448a0da324869aeb","last_reissued_at":"2026-07-05T12:02:03.278215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:03.278215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agentic-R1: Distilled Dual-Strategy Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Pranjal Aggarwal, Sean Welleck, Weihua Du, Yiming Yang","submitted_at":"2025-07-08T06:35:16Z","abstract_excerpt":"Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic via code execution, but often falter on complex logical tasks. We introduce a fine-tuning framework, DualDistill, that distills complementary reasoning strategies from multiple teachers into a unified student model. Using this approach, we train Agentic-R1, which dynamically selects the optimal strategy for each query, invoking tools for arithmetic and algorithmic problems, and using text-based reasoning for abstract "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05707","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/2507.05707/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":"2507.05707","created_at":"2026-07-05T12:02:03.278272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05707v2","created_at":"2026-07-05T12:02:03.278272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05707","created_at":"2026-07-05T12:02:03.278272+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJWLOCZC3W34","created_at":"2026-07-05T12:02:03.278272+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJWLOCZC3W345LAU","created_at":"2026-07-05T12:02:03.278272+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJWLOCZC","created_at":"2026-07-05T12:02:03.278272+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/BJWLOCZC3W345LAUQBMDCUZVMW","json":"https://pith.science/pith/BJWLOCZC3W345LAUQBMDCUZVMW.json","graph_json":"https://pith.science/api/pith-number/BJWLOCZC3W345LAUQBMDCUZVMW/graph.json","events_json":"https://pith.science/api/pith-number/BJWLOCZC3W345LAUQBMDCUZVMW/events.json","paper":"https://pith.science/paper/BJWLOCZC"},"agent_actions":{"view_html":"https://pith.science/pith/BJWLOCZC3W345LAUQBMDCUZVMW","download_json":"https://pith.science/pith/BJWLOCZC3W345LAUQBMDCUZVMW.json","view_paper":"https://pith.science/paper/BJWLOCZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05707&json=true","fetch_graph":"https://pith.science/api/pith-number/BJWLOCZC3W345LAUQBMDCUZVMW/graph.json","fetch_events":"https://pith.science/api/pith-number/BJWLOCZC3W345LAUQBMDCUZVMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJWLOCZC3W345LAUQBMDCUZVMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJWLOCZC3W345LAUQBMDCUZVMW/action/storage_attestation","attest_author":"https://pith.science/pith/BJWLOCZC3W345LAUQBMDCUZVMW/action/author_attestation","sign_citation":"https://pith.science/pith/BJWLOCZC3W345LAUQBMDCUZVMW/action/citation_signature","submit_replication":"https://pith.science/pith/BJWLOCZC3W345LAUQBMDCUZVMW/action/replication_record"}},"created_at":"2026-07-05T12:02:03.278272+00:00","updated_at":"2026-07-05T12:02:03.278272+00:00"}