{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3O4EQJ5JHV75BVNF5TFEZTH5SB","short_pith_number":"pith:3O4EQJ5J","schema_version":"1.0","canonical_sha256":"dbb84827a93d7fd0d5a5ecca4cccfd906af440d0e04466d73c08971513ec6269","source":{"kind":"arxiv","id":"2606.25178","version":1},"attestation_state":"computed","paper":{"title":"Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bernhard Sch\\\"olkopf, Jiarui Liu, Lezhen Zhang, Yinghui He, Yongjin Yang, Zhijing Jin","submitted_at":"2026-06-23T21:10:29Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has been extended from single-domain training to multi-domain reasoning suites spanning mathematics, programming, and science. However, the training curriculum (how often each domain is sampled) is typically fixed or hand-tuned, even though reasoning skills transfer unevenly across domains. Existing learnability-based curricula adapt to where the policy is currently improving, but are blind to whether a gradient step on the selected domain benefits the remaining domains. In this paper, we propose Transfer-Aware Curriculum (TAC), a bandit-st"},"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":"2606.25178","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T21:10:29Z","cross_cats_sorted":[],"title_canon_sha256":"ec32c9fa53e386160574dd6418150f36ccb2626e3e425b1f03b120d77838a037","abstract_canon_sha256":"cc69f366d4fde14fe1f0cadee0cec8e6cccdaf8159d95177c567c653e8a49a50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:18:20.117915Z","signature_b64":"jVeAEVIt1nHUB6lKzyhLgLm9U4S2ljlXPIIUFJyf5gbZwS2Lf2cGi8LW8OiPooV/wlACwG2dEp7capUEn/bJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbb84827a93d7fd0d5a5ecca4cccfd906af440d0e04466d73c08971513ec6269","last_reissued_at":"2026-06-25T00:18:20.117554Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:18:20.117554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bernhard Sch\\\"olkopf, Jiarui Liu, Lezhen Zhang, Yinghui He, Yongjin Yang, Zhijing Jin","submitted_at":"2026-06-23T21:10:29Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has been extended from single-domain training to multi-domain reasoning suites spanning mathematics, programming, and science. However, the training curriculum (how often each domain is sampled) is typically fixed or hand-tuned, even though reasoning skills transfer unevenly across domains. Existing learnability-based curricula adapt to where the policy is currently improving, but are blind to whether a gradient step on the selected domain benefits the remaining domains. In this paper, we propose Transfer-Aware Curriculum (TAC), a bandit-st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25178","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/2606.25178/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":"2606.25178","created_at":"2026-06-25T00:18:20.117616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25178v1","created_at":"2026-06-25T00:18:20.117616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25178","created_at":"2026-06-25T00:18:20.117616+00:00"},{"alias_kind":"pith_short_12","alias_value":"3O4EQJ5JHV75","created_at":"2026-06-25T00:18:20.117616+00:00"},{"alias_kind":"pith_short_16","alias_value":"3O4EQJ5JHV75BVNF","created_at":"2026-06-25T00:18:20.117616+00:00"},{"alias_kind":"pith_short_8","alias_value":"3O4EQJ5J","created_at":"2026-06-25T00:18:20.117616+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/3O4EQJ5JHV75BVNF5TFEZTH5SB","json":"https://pith.science/pith/3O4EQJ5JHV75BVNF5TFEZTH5SB.json","graph_json":"https://pith.science/api/pith-number/3O4EQJ5JHV75BVNF5TFEZTH5SB/graph.json","events_json":"https://pith.science/api/pith-number/3O4EQJ5JHV75BVNF5TFEZTH5SB/events.json","paper":"https://pith.science/paper/3O4EQJ5J"},"agent_actions":{"view_html":"https://pith.science/pith/3O4EQJ5JHV75BVNF5TFEZTH5SB","download_json":"https://pith.science/pith/3O4EQJ5JHV75BVNF5TFEZTH5SB.json","view_paper":"https://pith.science/paper/3O4EQJ5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25178&json=true","fetch_graph":"https://pith.science/api/pith-number/3O4EQJ5JHV75BVNF5TFEZTH5SB/graph.json","fetch_events":"https://pith.science/api/pith-number/3O4EQJ5JHV75BVNF5TFEZTH5SB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3O4EQJ5JHV75BVNF5TFEZTH5SB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3O4EQJ5JHV75BVNF5TFEZTH5SB/action/storage_attestation","attest_author":"https://pith.science/pith/3O4EQJ5JHV75BVNF5TFEZTH5SB/action/author_attestation","sign_citation":"https://pith.science/pith/3O4EQJ5JHV75BVNF5TFEZTH5SB/action/citation_signature","submit_replication":"https://pith.science/pith/3O4EQJ5JHV75BVNF5TFEZTH5SB/action/replication_record"}},"created_at":"2026-06-25T00:18:20.117616+00:00","updated_at":"2026-06-25T00:18:20.117616+00:00"}