{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UXIPHJ3XCC4WAMBK6ZPVQSZ4CQ","short_pith_number":"pith:UXIPHJ3X","schema_version":"1.0","canonical_sha256":"a5d0f3a77710b960302af65f584b3c142942cdc604bfeafa52e3d3c9b7ecf9c0","source":{"kind":"arxiv","id":"2607.00796","version":1},"attestation_state":"computed","paper":{"title":"Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinwen Wang, Kai Lv, Qian Xu, Shuo Wang, Xiaobo Hu, Youfang Lin, Zhuo Chen","submitted_at":"2026-07-01T11:26:25Z","abstract_excerpt":"Visual Reinforcement Learning (VRL) has achieved considerable success in solving control tasks. However, generalizing learned policies to new environments remains a major challenge, as agents often overfit to task-irrelevant features in the training environment. To solve this problem, we introduce the concept of decoupling observations into task-relevant and task-irrelevant representations. Building on this idea, we propose a self-supervised Task-Relevant Representation Decoupling (T2RD) algorithm for VRL. This algorithm consists of three components: task-relevant representation consistency, c"},"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":"2607.00796","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T11:26:25Z","cross_cats_sorted":[],"title_canon_sha256":"346f625babe593e0331802f0043d701b270dad1d7e232effe740cfdf9fb9e70a","abstract_canon_sha256":"09a5432e1d835575728aed809b4e84a2456a0d43f23917eb352e00cee11524d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:55.588151Z","signature_b64":"kSH3KAjjnWAMUsRjvLqsdK44CbqBV4xhSVV+eGRniQxFckvlK+VdSpW5idPv4Ltiu3Iq9EaA32WcC874YzjHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5d0f3a77710b960302af65f584b3c142942cdc604bfeafa52e3d3c9b7ecf9c0","last_reissued_at":"2026-07-02T01:17:55.587761Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:55.587761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinwen Wang, Kai Lv, Qian Xu, Shuo Wang, Xiaobo Hu, Youfang Lin, Zhuo Chen","submitted_at":"2026-07-01T11:26:25Z","abstract_excerpt":"Visual Reinforcement Learning (VRL) has achieved considerable success in solving control tasks. However, generalizing learned policies to new environments remains a major challenge, as agents often overfit to task-irrelevant features in the training environment. To solve this problem, we introduce the concept of decoupling observations into task-relevant and task-irrelevant representations. Building on this idea, we propose a self-supervised Task-Relevant Representation Decoupling (T2RD) algorithm for VRL. This algorithm consists of three components: task-relevant representation consistency, c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00796","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/2607.00796/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":"2607.00796","created_at":"2026-07-02T01:17:55.587818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00796v1","created_at":"2026-07-02T01:17:55.587818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00796","created_at":"2026-07-02T01:17:55.587818+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXIPHJ3XCC4W","created_at":"2026-07-02T01:17:55.587818+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXIPHJ3XCC4WAMBK","created_at":"2026-07-02T01:17:55.587818+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXIPHJ3X","created_at":"2026-07-02T01:17:55.587818+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/UXIPHJ3XCC4WAMBK6ZPVQSZ4CQ","json":"https://pith.science/pith/UXIPHJ3XCC4WAMBK6ZPVQSZ4CQ.json","graph_json":"https://pith.science/api/pith-number/UXIPHJ3XCC4WAMBK6ZPVQSZ4CQ/graph.json","events_json":"https://pith.science/api/pith-number/UXIPHJ3XCC4WAMBK6ZPVQSZ4CQ/events.json","paper":"https://pith.science/paper/UXIPHJ3X"},"agent_actions":{"view_html":"https://pith.science/pith/UXIPHJ3XCC4WAMBK6ZPVQSZ4CQ","download_json":"https://pith.science/pith/UXIPHJ3XCC4WAMBK6ZPVQSZ4CQ.json","view_paper":"https://pith.science/paper/UXIPHJ3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00796&json=true","fetch_graph":"https://pith.science/api/pith-number/UXIPHJ3XCC4WAMBK6ZPVQSZ4CQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UXIPHJ3XCC4WAMBK6ZPVQSZ4CQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXIPHJ3XCC4WAMBK6ZPVQSZ4CQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXIPHJ3XCC4WAMBK6ZPVQSZ4CQ/action/storage_attestation","attest_author":"https://pith.science/pith/UXIPHJ3XCC4WAMBK6ZPVQSZ4CQ/action/author_attestation","sign_citation":"https://pith.science/pith/UXIPHJ3XCC4WAMBK6ZPVQSZ4CQ/action/citation_signature","submit_replication":"https://pith.science/pith/UXIPHJ3XCC4WAMBK6ZPVQSZ4CQ/action/replication_record"}},"created_at":"2026-07-02T01:17:55.587818+00:00","updated_at":"2026-07-02T01:17:55.587818+00:00"}