{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C67NY6TOQFVL5OAUEBAGARMHHY","short_pith_number":"pith:C67NY6TO","schema_version":"1.0","canonical_sha256":"17bedc7a6e816abeb81420406045873e1a8c1cf5367f35933ae45b4feafffd75","source":{"kind":"arxiv","id":"2310.05086","version":2},"attestation_state":"computed","paper":{"title":"Learning Generalizable Agents via Saliency-Guided Features Decorrelation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Yang, Hechang Chen, Jifeng Hu, Lichao Sun, Sili Huang, Siyuan Guo, Yanchao Sun, Yi Chang","submitted_at":"2023-10-08T09:24:43Z","abstract_excerpt":"In visual-based Reinforcement Learning (RL), agents often struggle to generalize well to environmental variations in the state space that were not observed during training. The variations can arise in both task-irrelevant features, such as background noise, and task-relevant features, such as robot configurations, that are related to the optimal decisions. To achieve generalization in both situations, agents are required to accurately understand the impact of changed features on the decisions, i.e., establishing the true associations between changed features and decisions in the policy model. "},"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":"2310.05086","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-08T09:24:43Z","cross_cats_sorted":[],"title_canon_sha256":"7d0349e7f861f897ac25bddc6b613356944aab578bace26d6f8155bda793900e","abstract_canon_sha256":"28b755870e510a2683a02d89a2892a9786b581cae592df778d9820a95d40f426"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:08.648572Z","signature_b64":"hk16SwUyaf1fpR4nLq+1LIBPyLoYhsy2yn9+oMn3C3JHpD7rLYAsFjpIpKwoantrymcgNkkBj9IKSkvT1Lc0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17bedc7a6e816abeb81420406045873e1a8c1cf5367f35933ae45b4feafffd75","last_reissued_at":"2026-07-05T07:27:08.648123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:08.648123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Generalizable Agents via Saliency-Guided Features Decorrelation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Yang, Hechang Chen, Jifeng Hu, Lichao Sun, Sili Huang, Siyuan Guo, Yanchao Sun, Yi Chang","submitted_at":"2023-10-08T09:24:43Z","abstract_excerpt":"In visual-based Reinforcement Learning (RL), agents often struggle to generalize well to environmental variations in the state space that were not observed during training. The variations can arise in both task-irrelevant features, such as background noise, and task-relevant features, such as robot configurations, that are related to the optimal decisions. To achieve generalization in both situations, agents are required to accurately understand the impact of changed features on the decisions, i.e., establishing the true associations between changed features and decisions in the policy model. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05086","kind":"arxiv","version":2},"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/2310.05086/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":"2310.05086","created_at":"2026-07-05T07:27:08.648189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.05086v2","created_at":"2026-07-05T07:27:08.648189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05086","created_at":"2026-07-05T07:27:08.648189+00:00"},{"alias_kind":"pith_short_12","alias_value":"C67NY6TOQFVL","created_at":"2026-07-05T07:27:08.648189+00:00"},{"alias_kind":"pith_short_16","alias_value":"C67NY6TOQFVL5OAU","created_at":"2026-07-05T07:27:08.648189+00:00"},{"alias_kind":"pith_short_8","alias_value":"C67NY6TO","created_at":"2026-07-05T07:27:08.648189+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06337","citing_title":"Decorrelated feature importance from local sample weighting","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C67NY6TOQFVL5OAUEBAGARMHHY","json":"https://pith.science/pith/C67NY6TOQFVL5OAUEBAGARMHHY.json","graph_json":"https://pith.science/api/pith-number/C67NY6TOQFVL5OAUEBAGARMHHY/graph.json","events_json":"https://pith.science/api/pith-number/C67NY6TOQFVL5OAUEBAGARMHHY/events.json","paper":"https://pith.science/paper/C67NY6TO"},"agent_actions":{"view_html":"https://pith.science/pith/C67NY6TOQFVL5OAUEBAGARMHHY","download_json":"https://pith.science/pith/C67NY6TOQFVL5OAUEBAGARMHHY.json","view_paper":"https://pith.science/paper/C67NY6TO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.05086&json=true","fetch_graph":"https://pith.science/api/pith-number/C67NY6TOQFVL5OAUEBAGARMHHY/graph.json","fetch_events":"https://pith.science/api/pith-number/C67NY6TOQFVL5OAUEBAGARMHHY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C67NY6TOQFVL5OAUEBAGARMHHY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C67NY6TOQFVL5OAUEBAGARMHHY/action/storage_attestation","attest_author":"https://pith.science/pith/C67NY6TOQFVL5OAUEBAGARMHHY/action/author_attestation","sign_citation":"https://pith.science/pith/C67NY6TOQFVL5OAUEBAGARMHHY/action/citation_signature","submit_replication":"https://pith.science/pith/C67NY6TOQFVL5OAUEBAGARMHHY/action/replication_record"}},"created_at":"2026-07-05T07:27:08.648189+00:00","updated_at":"2026-07-05T07:27:08.648189+00:00"}