{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4IQONJASR3HB56LSVAWUI2PUY3","short_pith_number":"pith:4IQONJAS","canonical_record":{"source":{"id":"2312.15339","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-23T20:11:05Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"5735d9f01a8a6911680170130bcee887e0d9a53d59945fd829a8e10f09518099","abstract_canon_sha256":"a1099469876a7bf76cf1839f0533935d4c45a8f774cbad03600266a37a9efea7"},"schema_version":"1.0"},"canonical_sha256":"e220e6a4128ece1ef972a82d4469f4c6c6778c0ddad6fe131dca0b7512e19028","source":{"kind":"arxiv","id":"2312.15339","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15339","created_at":"2026-07-05T07:27:33Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15339v1","created_at":"2026-07-05T07:27:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15339","created_at":"2026-07-05T07:27:33Z"},{"alias_kind":"pith_short_12","alias_value":"4IQONJASR3HB","created_at":"2026-07-05T07:27:33Z"},{"alias_kind":"pith_short_16","alias_value":"4IQONJASR3HB56LS","created_at":"2026-07-05T07:27:33Z"},{"alias_kind":"pith_short_8","alias_value":"4IQONJAS","created_at":"2026-07-05T07:27:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4IQONJASR3HB56LSVAWUI2PUY3","target":"record","payload":{"canonical_record":{"source":{"id":"2312.15339","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-23T20:11:05Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"5735d9f01a8a6911680170130bcee887e0d9a53d59945fd829a8e10f09518099","abstract_canon_sha256":"a1099469876a7bf76cf1839f0533935d4c45a8f774cbad03600266a37a9efea7"},"schema_version":"1.0"},"canonical_sha256":"e220e6a4128ece1ef972a82d4469f4c6c6778c0ddad6fe131dca0b7512e19028","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:33.874871Z","signature_b64":"t71EsIQJ6F49IyMu6eZRuVh/54D3RQis4Daqktx4j1nZthg3ZVZgTKJC10pPmB4SFvPG89v1mEH9abNt1zrXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e220e6a4128ece1ef972a82d4469f4c6c6778c0ddad6fe131dca0b7512e19028","last_reissued_at":"2026-07-05T07:27:33.874375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:33.874375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.15339","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":"2026-07-05T07:27:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rde3A0PFghhO5oaLog6d+v+SQ9YwUgnZgbC/70USC2ziF7Vb136IUSvFVRvmgLUdpZxMkCvtvbprbZopI9jiCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:29:35.683167Z"},"content_sha256":"d3a4b821d0fa5953e89a731b01a28ba79e57de9bf318f312dd819e779eebcf1e","schema_version":"1.0","event_id":"sha256:d3a4b821d0fa5953e89a731b01a28ba79e57de9bf318f312dd819e779eebcf1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4IQONJASR3HB56LSVAWUI2PUY3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"A. Rupam Mahmood, Bram Grooten, Decebal Constantin Mocanu, Gautham Vasan, Matthew E. Taylor, Meng Fang, Mykola Pechenizkiy, Tristan Tomilin","submitted_at":"2023-12-23T20:11:05Z","abstract_excerpt":"The visual world provides an abundance of information, but many input pixels received by agents often contain distracting stimuli. Autonomous agents need the ability to distinguish useful information from task-irrelevant perceptions, enabling them to generalize to unseen environments with new distractions. Existing works approach this problem using data augmentation or large auxiliary networks with additional loss functions. We introduce MaDi, a novel algorithm that learns to mask distractions by the reward signal only. In MaDi, the conventional actor-critic structure of deep reinforcement lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15339","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/2312.15339/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":"2026-07-05T07:27:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wfg17Uxt8zyA1p4X+FwvXQxKL6xIwmGU0C8hSgzTDgooOiKkQnikZXbrF6yO68x5Bm2wvJQmUKcSiNDdcZL1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:29:35.683547Z"},"content_sha256":"95fd1262c5d78be471808948e1be8257ba0d920e5d69049c7ea0a7fb811bea4d","schema_version":"1.0","event_id":"sha256:95fd1262c5d78be471808948e1be8257ba0d920e5d69049c7ea0a7fb811bea4d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4IQONJASR3HB56LSVAWUI2PUY3/bundle.json","state_url":"https://pith.science/pith/4IQONJASR3HB56LSVAWUI2PUY3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4IQONJASR3HB56LSVAWUI2PUY3/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":"2026-08-14T22:29:35Z","links":{"resolver":"https://pith.science/pith/4IQONJASR3HB56LSVAWUI2PUY3","bundle":"https://pith.science/pith/4IQONJASR3HB56LSVAWUI2PUY3/bundle.json","state":"https://pith.science/pith/4IQONJASR3HB56LSVAWUI2PUY3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4IQONJASR3HB56LSVAWUI2PUY3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4IQONJASR3HB56LSVAWUI2PUY3","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":"a1099469876a7bf76cf1839f0533935d4c45a8f774cbad03600266a37a9efea7","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-23T20:11:05Z","title_canon_sha256":"5735d9f01a8a6911680170130bcee887e0d9a53d59945fd829a8e10f09518099"},"schema_version":"1.0","source":{"id":"2312.15339","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15339","created_at":"2026-07-05T07:27:33Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15339v1","created_at":"2026-07-05T07:27:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15339","created_at":"2026-07-05T07:27:33Z"},{"alias_kind":"pith_short_12","alias_value":"4IQONJASR3HB","created_at":"2026-07-05T07:27:33Z"},{"alias_kind":"pith_short_16","alias_value":"4IQONJASR3HB56LS","created_at":"2026-07-05T07:27:33Z"},{"alias_kind":"pith_short_8","alias_value":"4IQONJAS","created_at":"2026-07-05T07:27:33Z"}],"graph_snapshots":[{"event_id":"sha256:95fd1262c5d78be471808948e1be8257ba0d920e5d69049c7ea0a7fb811bea4d","target":"graph","created_at":"2026-07-05T07:27:33Z","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/2312.15339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The visual world provides an abundance of information, but many input pixels received by agents often contain distracting stimuli. Autonomous agents need the ability to distinguish useful information from task-irrelevant perceptions, enabling them to generalize to unseen environments with new distractions. Existing works approach this problem using data augmentation or large auxiliary networks with additional loss functions. We introduce MaDi, a novel algorithm that learns to mask distractions by the reward signal only. In MaDi, the conventional actor-critic structure of deep reinforcement lea","authors_text":"A. Rupam Mahmood, Bram Grooten, Decebal Constantin Mocanu, Gautham Vasan, Matthew E. Taylor, Meng Fang, Mykola Pechenizkiy, Tristan Tomilin","cross_cats":["cs.AI","cs.CV","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-23T20:11:05Z","title":"MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15339","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:d3a4b821d0fa5953e89a731b01a28ba79e57de9bf318f312dd819e779eebcf1e","target":"record","created_at":"2026-07-05T07:27:33Z","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":"a1099469876a7bf76cf1839f0533935d4c45a8f774cbad03600266a37a9efea7","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-23T20:11:05Z","title_canon_sha256":"5735d9f01a8a6911680170130bcee887e0d9a53d59945fd829a8e10f09518099"},"schema_version":"1.0","source":{"id":"2312.15339","kind":"arxiv","version":1}},"canonical_sha256":"e220e6a4128ece1ef972a82d4469f4c6c6778c0ddad6fe131dca0b7512e19028","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e220e6a4128ece1ef972a82d4469f4c6c6778c0ddad6fe131dca0b7512e19028","first_computed_at":"2026-07-05T07:27:33.874375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:33.874375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t71EsIQJ6F49IyMu6eZRuVh/54D3RQis4Daqktx4j1nZthg3ZVZgTKJC10pPmB4SFvPG89v1mEH9abNt1zrXAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:33.874871Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.15339","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3a4b821d0fa5953e89a731b01a28ba79e57de9bf318f312dd819e779eebcf1e","sha256:95fd1262c5d78be471808948e1be8257ba0d920e5d69049c7ea0a7fb811bea4d"],"state_sha256":"29e06d7a5adcd3f4145e081bcedb83249218fdf5ef3551eeb92a2a9865a8fbbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SA6OfVx1wVBVd2yEM7c32xD9HYj9Kjz5W/C9P9onT5qpnCu84c90BbxN/m5IoMfZJDLyekxphOYoBwY0P1MRBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T22:29:35.687385Z","bundle_sha256":"f3fd8724734a74793c1eeff4906fed7ced3c00569ee0354a961922dbd91a025f"}}