{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KJZSTJM6U6PEUH55MOCVECWL7E","short_pith_number":"pith:KJZSTJM6","schema_version":"1.0","canonical_sha256":"527329a59ea79e4a1fbd6385520acbf92b9cf9ad2119dfed655f6a36aad78034","source":{"kind":"arxiv","id":"2507.17512","version":1},"attestation_state":"computed","paper":{"title":"Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Conghui He, Honglin Lin, Lijun Wu, Mengyuan Sun, Yu Li, Zhuoshi Pan","submitted_at":"2025-07-23T13:51:04Z","abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of LLMs. Existing research has predominantly concentrated on isolated reasoning domains such as mathematical problem-solving, coding tasks, or logical reasoning. However, real world reasoning scenarios inherently demand an integrated application of multiple cognitive skills. Despite this, the interplay among these reasoning skills under reinforcement learning remains poorly understood. To bridge this gap, we present a systematic investigation of multi-domain reasoni"},"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":"2507.17512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-23T13:51:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3047d493cbc28c1a9dc78dfdbab9f68b17271fcc695f882e7aa5638189b78d51","abstract_canon_sha256":"62412a73f36ec7a766a44b86d5e0fa73aa04cfbee996859a3382de1807e5c270"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:09.153459Z","signature_b64":"XDeqben7amQM/0QX2hb57l2gVpYm7vWoW04vt+pj+kHTO8kN/8YmNe5ukJqZ1xr1o3bVRhcDs3DUPC/b097SDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"527329a59ea79e4a1fbd6385520acbf92b9cf9ad2119dfed655f6a36aad78034","last_reissued_at":"2026-07-05T11:42:09.152950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:09.152950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Conghui He, Honglin Lin, Lijun Wu, Mengyuan Sun, Yu Li, Zhuoshi Pan","submitted_at":"2025-07-23T13:51:04Z","abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of LLMs. Existing research has predominantly concentrated on isolated reasoning domains such as mathematical problem-solving, coding tasks, or logical reasoning. However, real world reasoning scenarios inherently demand an integrated application of multiple cognitive skills. Despite this, the interplay among these reasoning skills under reinforcement learning remains poorly understood. To bridge this gap, we present a systematic investigation of multi-domain reasoni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17512","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/2507.17512/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":"2507.17512","created_at":"2026-07-05T11:42:09.153010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17512v1","created_at":"2026-07-05T11:42:09.153010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17512","created_at":"2026-07-05T11:42:09.153010+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJZSTJM6U6PE","created_at":"2026-07-05T11:42:09.153010+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJZSTJM6U6PEUH55","created_at":"2026-07-05T11:42:09.153010+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJZSTJM6","created_at":"2026-07-05T11:42:09.153010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25178","citing_title":"Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17682","citing_title":"From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11052","citing_title":"Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25178","citing_title":"Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23964","citing_title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","ref_index":205,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10480","citing_title":"Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJZSTJM6U6PEUH55MOCVECWL7E","json":"https://pith.science/pith/KJZSTJM6U6PEUH55MOCVECWL7E.json","graph_json":"https://pith.science/api/pith-number/KJZSTJM6U6PEUH55MOCVECWL7E/graph.json","events_json":"https://pith.science/api/pith-number/KJZSTJM6U6PEUH55MOCVECWL7E/events.json","paper":"https://pith.science/paper/KJZSTJM6"},"agent_actions":{"view_html":"https://pith.science/pith/KJZSTJM6U6PEUH55MOCVECWL7E","download_json":"https://pith.science/pith/KJZSTJM6U6PEUH55MOCVECWL7E.json","view_paper":"https://pith.science/paper/KJZSTJM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17512&json=true","fetch_graph":"https://pith.science/api/pith-number/KJZSTJM6U6PEUH55MOCVECWL7E/graph.json","fetch_events":"https://pith.science/api/pith-number/KJZSTJM6U6PEUH55MOCVECWL7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJZSTJM6U6PEUH55MOCVECWL7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJZSTJM6U6PEUH55MOCVECWL7E/action/storage_attestation","attest_author":"https://pith.science/pith/KJZSTJM6U6PEUH55MOCVECWL7E/action/author_attestation","sign_citation":"https://pith.science/pith/KJZSTJM6U6PEUH55MOCVECWL7E/action/citation_signature","submit_replication":"https://pith.science/pith/KJZSTJM6U6PEUH55MOCVECWL7E/action/replication_record"}},"created_at":"2026-07-05T11:42:09.153010+00:00","updated_at":"2026-07-05T11:42:09.153010+00:00"}