{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WVV7KCVBZEDWGCXVQIIXK2LKRG","short_pith_number":"pith:WVV7KCVB","schema_version":"1.0","canonical_sha256":"b56bf50aa1c907630af5821175696a89ae0895fd98da6e8ca11432d9787be208","source":{"kind":"arxiv","id":"2605.19924","version":1},"attestation_state":"computed","paper":{"title":"RoHIL: Robust Human-in-the-Loop Robotic Reinforcement Learning Against Illumination Variations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Kai Liu, Ke Wang, Shuoqin Zhang, Xichuan Zhou, Xiru Gao, Yixin Xiong, Zhe Hu","submitted_at":"2026-05-19T14:47:38Z","abstract_excerpt":"Human-in-the-loop reinforcement learning systems achieve near-perfect success on the workstation where they are trained, but collapse when the same robot is moved to a workstation a few meters away due to shifts in the visual input distribution caused by new lamp positions and window light. Re-collecting demonstrations and re-running HIL on every workstation is incompatible with deployment, and naively fine-tuning on shifted-light data triggers catastrophic forgetting of the source workstation. To close this cross-domain gap, we present RoHIL, an offline fine-tuning framework that uses no extr"},"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":"2605.19924","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-19T14:47:38Z","cross_cats_sorted":[],"title_canon_sha256":"b6c1743015189a88f31685d95320c46f541e3fb6b2779e46e4244cfc39a10fe0","abstract_canon_sha256":"30fc570774712a8f327091e57205bb883ffce4602dd9fd0968b0b0f502a54d04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:05:55.524301Z","signature_b64":"hGHI3RdRM9NY2NPHfIFBEDmLKp4MbYD50hpWX9hR7g2/PHdYAyVJh81GeTGwuUxCuM/3Gvo5JrLJPtDe15CHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b56bf50aa1c907630af5821175696a89ae0895fd98da6e8ca11432d9787be208","last_reissued_at":"2026-05-20T02:05:55.523251Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:05:55.523251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoHIL: Robust Human-in-the-Loop Robotic Reinforcement Learning Against Illumination Variations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Kai Liu, Ke Wang, Shuoqin Zhang, Xichuan Zhou, Xiru Gao, Yixin Xiong, Zhe Hu","submitted_at":"2026-05-19T14:47:38Z","abstract_excerpt":"Human-in-the-loop reinforcement learning systems achieve near-perfect success on the workstation where they are trained, but collapse when the same robot is moved to a workstation a few meters away due to shifts in the visual input distribution caused by new lamp positions and window light. Re-collecting demonstrations and re-running HIL on every workstation is incompatible with deployment, and naively fine-tuning on shifted-light data triggers catastrophic forgetting of the source workstation. To close this cross-domain gap, we present RoHIL, an offline fine-tuning framework that uses no extr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19924","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/2605.19924/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":"2605.19924","created_at":"2026-05-20T02:05:55.523403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19924v1","created_at":"2026-05-20T02:05:55.523403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19924","created_at":"2026-05-20T02:05:55.523403+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVV7KCVBZEDW","created_at":"2026-05-20T02:05:55.523403+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVV7KCVBZEDWGCXV","created_at":"2026-05-20T02:05:55.523403+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVV7KCVB","created_at":"2026-05-20T02:05:55.523403+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/WVV7KCVBZEDWGCXVQIIXK2LKRG","json":"https://pith.science/pith/WVV7KCVBZEDWGCXVQIIXK2LKRG.json","graph_json":"https://pith.science/api/pith-number/WVV7KCVBZEDWGCXVQIIXK2LKRG/graph.json","events_json":"https://pith.science/api/pith-number/WVV7KCVBZEDWGCXVQIIXK2LKRG/events.json","paper":"https://pith.science/paper/WVV7KCVB"},"agent_actions":{"view_html":"https://pith.science/pith/WVV7KCVBZEDWGCXVQIIXK2LKRG","download_json":"https://pith.science/pith/WVV7KCVBZEDWGCXVQIIXK2LKRG.json","view_paper":"https://pith.science/paper/WVV7KCVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19924&json=true","fetch_graph":"https://pith.science/api/pith-number/WVV7KCVBZEDWGCXVQIIXK2LKRG/graph.json","fetch_events":"https://pith.science/api/pith-number/WVV7KCVBZEDWGCXVQIIXK2LKRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVV7KCVBZEDWGCXVQIIXK2LKRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVV7KCVBZEDWGCXVQIIXK2LKRG/action/storage_attestation","attest_author":"https://pith.science/pith/WVV7KCVBZEDWGCXVQIIXK2LKRG/action/author_attestation","sign_citation":"https://pith.science/pith/WVV7KCVBZEDWGCXVQIIXK2LKRG/action/citation_signature","submit_replication":"https://pith.science/pith/WVV7KCVBZEDWGCXVQIIXK2LKRG/action/replication_record"}},"created_at":"2026-05-20T02:05:55.523403+00:00","updated_at":"2026-05-20T02:05:55.523403+00:00"}