{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GELUCV62VP2WG7Y3JK2PZQH5QP","short_pith_number":"pith:GELUCV62","canonical_record":{"source":{"id":"2509.04970","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-05T09:52:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"72eedc7d621b9c3190a2e5cce3650d18816a3f5b537849b619184cd466d219ec","abstract_canon_sha256":"fd2979d7fab859f34dd44427cd75e1ed64e0de59ff98cb3c9dbc41badc93ddc5"},"schema_version":"1.0"},"canonical_sha256":"31174157daabf5637f1b4ab4fcc0fd83c672cfef242fb71b738e7c63c32601f7","source":{"kind":"arxiv","id":"2509.04970","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04970","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04970v1","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04970","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"GELUCV62VP2W","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"GELUCV62VP2WG7Y3","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"GELUCV62","created_at":"2026-07-05T12:05:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GELUCV62VP2WG7Y3JK2PZQH5QP","target":"record","payload":{"canonical_record":{"source":{"id":"2509.04970","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-05T09:52:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"72eedc7d621b9c3190a2e5cce3650d18816a3f5b537849b619184cd466d219ec","abstract_canon_sha256":"fd2979d7fab859f34dd44427cd75e1ed64e0de59ff98cb3c9dbc41badc93ddc5"},"schema_version":"1.0"},"canonical_sha256":"31174157daabf5637f1b4ab4fcc0fd83c672cfef242fb71b738e7c63c32601f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:33.611153Z","signature_b64":"2eaORGky0jdnzUj5I6Y0nfEjptcMJTWHL7lQdyqzUSWwj+PzjgkNFJ2mi8uT+Qd2+KssB/Yo0Xu2Oa+NEogYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31174157daabf5637f1b4ab4fcc0fd83c672cfef242fb71b738e7c63c32601f7","last_reissued_at":"2026-07-05T12:05:33.610708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:33.610708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.04970","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:05:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7HdmEGD8YEFnDAwbET5v0nkI1TD8KrNHw8kDTJECDO0XUK6vsOMXSoNDk6KeZ/Njrf1aPsKVjy/ZFioD9JA3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:09:40.273967Z"},"content_sha256":"b2e76ec5fcde45d167812cf294e78b2028f20742ebc06af9e2c8dbe483afb3c6","schema_version":"1.0","event_id":"sha256:b2e76ec5fcde45d167812cf294e78b2028f20742ebc06af9e2c8dbe483afb3c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GELUCV62VP2WG7Y3JK2PZQH5QP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeGuV: Depth-Guided Visual Reinforcement Learning for Generalization and Interpretability in Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Angelo Cangelosi, Khang Nguyen, Manfred Huber, Tien Pham, Xinyun Chi","submitted_at":"2025-09-05T09:52:08Z","abstract_excerpt":"Reinforcement learning (RL) agents can learn to solve complex tasks from visual inputs, but generalizing these learned skills to new environments remains a major challenge in RL application, especially robotics. While data augmentation can improve generalization, it often compromises sample efficiency and training stability. This paper introduces DeGuV, an RL framework that enhances both generalization and sample efficiency. In specific, we leverage a learnable masker network that produces a mask from the depth input, preserving only critical visual information while discarding irrelevant pixe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04970","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/2509.04970/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:05:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PDE+doQ2lZuDGkTZCqMfINd2ZidfjuQ+sQ54LQ63yD8U0Ct0hWJ6bDtfltF8rYGsSigNwSQcdu8RUiqQaHFnAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:09:40.274502Z"},"content_sha256":"5c6e7ed6bba193901d0ae9bc254bd633da3f18d898425f05a529b2595af13d53","schema_version":"1.0","event_id":"sha256:5c6e7ed6bba193901d0ae9bc254bd633da3f18d898425f05a529b2595af13d53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GELUCV62VP2WG7Y3JK2PZQH5QP/bundle.json","state_url":"https://pith.science/pith/GELUCV62VP2WG7Y3JK2PZQH5QP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GELUCV62VP2WG7Y3JK2PZQH5QP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T14:09:40Z","links":{"resolver":"https://pith.science/pith/GELUCV62VP2WG7Y3JK2PZQH5QP","bundle":"https://pith.science/pith/GELUCV62VP2WG7Y3JK2PZQH5QP/bundle.json","state":"https://pith.science/pith/GELUCV62VP2WG7Y3JK2PZQH5QP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GELUCV62VP2WG7Y3JK2PZQH5QP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GELUCV62VP2WG7Y3JK2PZQH5QP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fd2979d7fab859f34dd44427cd75e1ed64e0de59ff98cb3c9dbc41badc93ddc5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-05T09:52:08Z","title_canon_sha256":"72eedc7d621b9c3190a2e5cce3650d18816a3f5b537849b619184cd466d219ec"},"schema_version":"1.0","source":{"id":"2509.04970","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04970","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04970v1","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04970","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"GELUCV62VP2W","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"GELUCV62VP2WG7Y3","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"GELUCV62","created_at":"2026-07-05T12:05:33Z"}],"graph_snapshots":[{"event_id":"sha256:5c6e7ed6bba193901d0ae9bc254bd633da3f18d898425f05a529b2595af13d53","target":"graph","created_at":"2026-07-05T12:05:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.04970/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) agents can learn to solve complex tasks from visual inputs, but generalizing these learned skills to new environments remains a major challenge in RL application, especially robotics. While data augmentation can improve generalization, it often compromises sample efficiency and training stability. This paper introduces DeGuV, an RL framework that enhances both generalization and sample efficiency. In specific, we leverage a learnable masker network that produces a mask from the depth input, preserving only critical visual information while discarding irrelevant pixe","authors_text":"Angelo Cangelosi, Khang Nguyen, Manfred Huber, Tien Pham, Xinyun Chi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-05T09:52:08Z","title":"DeGuV: Depth-Guided Visual Reinforcement Learning for Generalization and Interpretability in Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04970","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b2e76ec5fcde45d167812cf294e78b2028f20742ebc06af9e2c8dbe483afb3c6","target":"record","created_at":"2026-07-05T12:05:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fd2979d7fab859f34dd44427cd75e1ed64e0de59ff98cb3c9dbc41badc93ddc5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-05T09:52:08Z","title_canon_sha256":"72eedc7d621b9c3190a2e5cce3650d18816a3f5b537849b619184cd466d219ec"},"schema_version":"1.0","source":{"id":"2509.04970","kind":"arxiv","version":1}},"canonical_sha256":"31174157daabf5637f1b4ab4fcc0fd83c672cfef242fb71b738e7c63c32601f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31174157daabf5637f1b4ab4fcc0fd83c672cfef242fb71b738e7c63c32601f7","first_computed_at":"2026-07-05T12:05:33.610708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:33.610708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2eaORGky0jdnzUj5I6Y0nfEjptcMJTWHL7lQdyqzUSWwj+PzjgkNFJ2mi8uT+Qd2+KssB/Yo0Xu2Oa+NEogYDA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:33.611153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.04970","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2e76ec5fcde45d167812cf294e78b2028f20742ebc06af9e2c8dbe483afb3c6","sha256:5c6e7ed6bba193901d0ae9bc254bd633da3f18d898425f05a529b2595af13d53"],"state_sha256":"263a078149f8b0dd3e598b599891a88ffb810536641604d811f6886ee2759ebe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uIZmGqMDtZ3hWSLfclUZU4kJXeWe+CPPxYTGwl5z5fruXJ4BJ0b4C1TeMSsD+OBPh6M39DBjeoAMWO8eMqr1Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T14:09:40.281177Z","bundle_sha256":"1249502c109ec6c6e94b1a6cda7cdac851c659daa571fe5f43b202123b303746"}}