{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OB4Q4TZANOBTGS7EXX7YKAIEZ3","short_pith_number":"pith:OB4Q4TZA","schema_version":"1.0","canonical_sha256":"70790e4f206b83334be4bdff850104cec4ff5e4a982ef6633e045e872ae55101","source":{"kind":"arxiv","id":"2608.00455","version":1},"attestation_state":"computed","paper":{"title":"AReaL-DTE: Sparse Policy-Weight Transfer for Online Agentic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Binhang Yuan, Jiawei Zhang, Ran Yan, Ruida Xu, Tongkai Yang, Wei Dong, Wenhao Zhou, Yi Gao, Yingqi Peng, Zhiqiang Ding","submitted_at":"2026-08-01T05:34:56Z","abstract_excerpt":"Online agentic reinforcement learning implemented with micro-services separates policy training from rollout generation, improving scalability and modularity while potentially making frequent policy-weight synchronization a critical systems overhead. Shared storage naturally connects these services across clusters, but vanilla dense policy weight synchronization could incur model-scale construction, transfer, and application costs. Sparse synchronization reduces transferred data, yet checkpoint-oriented approaches can still retain a previous model and materialize complete intermediates to brid"},"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":"2608.00455","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-08-01T05:34:56Z","cross_cats_sorted":[],"title_canon_sha256":"31df4a859fb0964c7ed9ad2bf91a8b3b8a53610e847f3cc4b3edbf1ab88fa77d","abstract_canon_sha256":"c4746c44d8c24eaa652c8f9682e9329576210a32aae4df673f3a52616def8e56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:36:43.174649Z","signature_b64":"iqY0lQgxDZZpx8IGMx6ZAJ6TirWoJ3g/kVXKvgGDkUIecGspihPygutwvfTsGvbhizpcRzoh0ZQfxGH0CTKvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70790e4f206b83334be4bdff850104cec4ff5e4a982ef6633e045e872ae55101","last_reissued_at":"2026-08-04T00:36:43.173227Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:36:43.173227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AReaL-DTE: Sparse Policy-Weight Transfer for Online Agentic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Binhang Yuan, Jiawei Zhang, Ran Yan, Ruida Xu, Tongkai Yang, Wei Dong, Wenhao Zhou, Yi Gao, Yingqi Peng, Zhiqiang Ding","submitted_at":"2026-08-01T05:34:56Z","abstract_excerpt":"Online agentic reinforcement learning implemented with micro-services separates policy training from rollout generation, improving scalability and modularity while potentially making frequent policy-weight synchronization a critical systems overhead. Shared storage naturally connects these services across clusters, but vanilla dense policy weight synchronization could incur model-scale construction, transfer, and application costs. Sparse synchronization reduces transferred data, yet checkpoint-oriented approaches can still retain a previous model and materialize complete intermediates to brid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00455","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/2608.00455/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":"2608.00455","created_at":"2026-08-04T00:36:43.174407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00455v1","created_at":"2026-08-04T00:36:43.174407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00455","created_at":"2026-08-04T00:36:43.174407+00:00"},{"alias_kind":"pith_short_12","alias_value":"OB4Q4TZANOBT","created_at":"2026-08-04T00:36:43.174407+00:00"},{"alias_kind":"pith_short_16","alias_value":"OB4Q4TZANOBTGS7E","created_at":"2026-08-04T00:36:43.174407+00:00"},{"alias_kind":"pith_short_8","alias_value":"OB4Q4TZA","created_at":"2026-08-04T00:36:43.174407+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/OB4Q4TZANOBTGS7EXX7YKAIEZ3","json":"https://pith.science/pith/OB4Q4TZANOBTGS7EXX7YKAIEZ3.json","graph_json":"https://pith.science/api/pith-number/OB4Q4TZANOBTGS7EXX7YKAIEZ3/graph.json","events_json":"https://pith.science/api/pith-number/OB4Q4TZANOBTGS7EXX7YKAIEZ3/events.json","paper":"https://pith.science/paper/OB4Q4TZA"},"agent_actions":{"view_html":"https://pith.science/pith/OB4Q4TZANOBTGS7EXX7YKAIEZ3","download_json":"https://pith.science/pith/OB4Q4TZANOBTGS7EXX7YKAIEZ3.json","view_paper":"https://pith.science/paper/OB4Q4TZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00455&json=true","fetch_graph":"https://pith.science/api/pith-number/OB4Q4TZANOBTGS7EXX7YKAIEZ3/graph.json","fetch_events":"https://pith.science/api/pith-number/OB4Q4TZANOBTGS7EXX7YKAIEZ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OB4Q4TZANOBTGS7EXX7YKAIEZ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OB4Q4TZANOBTGS7EXX7YKAIEZ3/action/storage_attestation","attest_author":"https://pith.science/pith/OB4Q4TZANOBTGS7EXX7YKAIEZ3/action/author_attestation","sign_citation":"https://pith.science/pith/OB4Q4TZANOBTGS7EXX7YKAIEZ3/action/citation_signature","submit_replication":"https://pith.science/pith/OB4Q4TZANOBTGS7EXX7YKAIEZ3/action/replication_record"}},"created_at":"2026-08-04T00:36:43.174407+00:00","updated_at":"2026-08-04T00:36:43.174407+00:00"}