{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OUZC76F3MKJX6WKE22W73DIPHR","short_pith_number":"pith:OUZC76F3","schema_version":"1.0","canonical_sha256":"75322ff8bb62937f5944d6adfd8d0f3c75422b7310c7f468c45947beb58161b1","source":{"kind":"arxiv","id":"2605.19577","version":1},"attestation_state":"computed","paper":{"title":"GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Li, Jian Liang, Junmin Chen, Minxuan Lv, Ruiming Tang, Ruotong Pan, Tanlong Du, Tiehua Mei, Zhennan Wu, Zhenpeng Su, Ziqi Wang, Ziyang Chen","submitted_at":"2026-05-19T09:21:09Z","abstract_excerpt":"We present GoLongRL, a fully open-source, capability-oriented post-training recipe for long-context reinforcement learning with verifiable rewards (RLVR). Existing long-context RL methods often treat data construction as a matter of designing increasingly complex retrieval paths, leading to homogeneous task coverage and reward formulations that inadequately reflect practical long-context requirements. Our work offers two contributions. (1) Capability-oriented data construction with full open release. We openly release a dataset of 23K RLVR samples, the complete construction pipeline, and all t"},"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":"2605.19577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T09:21:09Z","cross_cats_sorted":[],"title_canon_sha256":"af9b635262493bfdb8b3b8b5c27c782c75159280cd6d84a8d4f698a43db582d4","abstract_canon_sha256":"2f1b2fad20e212e6a29269cff5881230aac64e50bc2dc7f96cc58e18747e6430"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:52.639152Z","signature_b64":"fVv5X0VCNC89mWOFSUbQUp2GAL5YgrmezSxRjU1zUqdF8JaZmy4BOJxD/5iu6P5P2NAAqiNWzSbSAblRigy3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75322ff8bb62937f5944d6adfd8d0f3c75422b7310c7f468c45947beb58161b1","last_reissued_at":"2026-05-20T01:05:52.638424Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:52.638424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Li, Jian Liang, Junmin Chen, Minxuan Lv, Ruiming Tang, Ruotong Pan, Tanlong Du, Tiehua Mei, Zhennan Wu, Zhenpeng Su, Ziqi Wang, Ziyang Chen","submitted_at":"2026-05-19T09:21:09Z","abstract_excerpt":"We present GoLongRL, a fully open-source, capability-oriented post-training recipe for long-context reinforcement learning with verifiable rewards (RLVR). Existing long-context RL methods often treat data construction as a matter of designing increasingly complex retrieval paths, leading to homogeneous task coverage and reward formulations that inadequately reflect practical long-context requirements. Our work offers two contributions. (1) Capability-oriented data construction with full open release. We openly release a dataset of 23K RLVR samples, the complete construction pipeline, and all t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19577","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/2605.19577/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":"2605.19577","created_at":"2026-05-20T01:05:52.638546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19577v1","created_at":"2026-05-20T01:05:52.638546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19577","created_at":"2026-05-20T01:05:52.638546+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUZC76F3MKJX","created_at":"2026-05-20T01:05:52.638546+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUZC76F3MKJX6WKE","created_at":"2026-05-20T01:05:52.638546+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUZC76F3","created_at":"2026-05-20T01:05:52.638546+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/OUZC76F3MKJX6WKE22W73DIPHR","json":"https://pith.science/pith/OUZC76F3MKJX6WKE22W73DIPHR.json","graph_json":"https://pith.science/api/pith-number/OUZC76F3MKJX6WKE22W73DIPHR/graph.json","events_json":"https://pith.science/api/pith-number/OUZC76F3MKJX6WKE22W73DIPHR/events.json","paper":"https://pith.science/paper/OUZC76F3"},"agent_actions":{"view_html":"https://pith.science/pith/OUZC76F3MKJX6WKE22W73DIPHR","download_json":"https://pith.science/pith/OUZC76F3MKJX6WKE22W73DIPHR.json","view_paper":"https://pith.science/paper/OUZC76F3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19577&json=true","fetch_graph":"https://pith.science/api/pith-number/OUZC76F3MKJX6WKE22W73DIPHR/graph.json","fetch_events":"https://pith.science/api/pith-number/OUZC76F3MKJX6WKE22W73DIPHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUZC76F3MKJX6WKE22W73DIPHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUZC76F3MKJX6WKE22W73DIPHR/action/storage_attestation","attest_author":"https://pith.science/pith/OUZC76F3MKJX6WKE22W73DIPHR/action/author_attestation","sign_citation":"https://pith.science/pith/OUZC76F3MKJX6WKE22W73DIPHR/action/citation_signature","submit_replication":"https://pith.science/pith/OUZC76F3MKJX6WKE22W73DIPHR/action/replication_record"}},"created_at":"2026-05-20T01:05:52.638546+00:00","updated_at":"2026-05-20T01:05:52.638546+00:00"}