{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RD6JSM3PMMC2YUE7EAIRRSHHV5","short_pith_number":"pith:RD6JSM3P","canonical_record":{"source":{"id":"2403.10940","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-16T14:52:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"99f7024fe32ccbb7ca0d15a416fe2f5cb1c1001ebccbc3cff484896d8ff0815b","abstract_canon_sha256":"798a682a9666bf4f83ae40779fdb5842f00a8733c84aa1f8b343c9a22dfce46e"},"schema_version":"1.0"},"canonical_sha256":"88fc99336f6305ac509f201118c8e7af43fb4545ef444202a45773e18e3560fa","source":{"kind":"arxiv","id":"2403.10940","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10940","created_at":"2026-07-05T09:23:04Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10940v3","created_at":"2026-07-05T09:23:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10940","created_at":"2026-07-05T09:23:04Z"},{"alias_kind":"pith_short_12","alias_value":"RD6JSM3PMMC2","created_at":"2026-07-05T09:23:04Z"},{"alias_kind":"pith_short_16","alias_value":"RD6JSM3PMMC2YUE7","created_at":"2026-07-05T09:23:04Z"},{"alias_kind":"pith_short_8","alias_value":"RD6JSM3P","created_at":"2026-07-05T09:23:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RD6JSM3PMMC2YUE7EAIRRSHHV5","target":"record","payload":{"canonical_record":{"source":{"id":"2403.10940","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-16T14:52:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"99f7024fe32ccbb7ca0d15a416fe2f5cb1c1001ebccbc3cff484896d8ff0815b","abstract_canon_sha256":"798a682a9666bf4f83ae40779fdb5842f00a8733c84aa1f8b343c9a22dfce46e"},"schema_version":"1.0"},"canonical_sha256":"88fc99336f6305ac509f201118c8e7af43fb4545ef444202a45773e18e3560fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:04.280146Z","signature_b64":"Nyr2uBjTmiRjyftbk2onZvup3FR1yqavpjAQ5Wty5sCZvXlOcr6tOWzIAqLrA4VvavEWJX47oFlHwOWEUchnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88fc99336f6305ac509f201118c8e7af43fb4545ef444202a45773e18e3560fa","last_reissued_at":"2026-07-05T09:23:04.279693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:04.279693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.10940","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:23:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"agq1YQt1t7qJKrtGSVAo18kmvuWqiIB33AHrAHrryykDMmWlIWp0kKoAMg+pf9HjAc8f+Ot58U6toCj7r3eeCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:24:08.283390Z"},"content_sha256":"718905d05fcb08329d76cec8a73fcc117ef3e7c53352e955c01d72dc4d94b863","schema_version":"1.0","event_id":"sha256:718905d05fcb08329d76cec8a73fcc117ef3e7c53352e955c01d72dc4d94b863"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RD6JSM3PMMC2YUE7EAIRRSHHV5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ViSaRL: Visual Reinforcement Learning Guided by Human Saliency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Anthony Liang, Erdem B{\\i}y{\\i}k, Jesse Thomason","submitted_at":"2024-03-16T14:52:26Z","abstract_excerpt":"Training robots to perform complex control tasks from high-dimensional pixel input using reinforcement learning (RL) is sample-inefficient, because image observations are comprised primarily of task-irrelevant information. By contrast, humans are able to visually attend to task-relevant objects and areas. Based on this insight, we introduce Visual Saliency-Guided Reinforcement Learning (ViSaRL). Using ViSaRL to learn visual representations significantly improves the success rate, sample efficiency, and generalization of an RL agent on diverse tasks including DeepMind Control benchmark, robot m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10940","kind":"arxiv","version":3},"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/2403.10940/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":"2026-07-05T09:23:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tgoh2pZ1ZEn7OybXOrKT9tF1LjJRlAw2Fhlb4a5FLWdDMe9/EaY2j4a5gelGLNTxwUDC9z7PWDGziho5kDOiCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:24:08.283879Z"},"content_sha256":"b4e27f4f5645003dc2cb4e221d9eb0eaf0388d834cc45c7ce23d170197aab0fe","schema_version":"1.0","event_id":"sha256:b4e27f4f5645003dc2cb4e221d9eb0eaf0388d834cc45c7ce23d170197aab0fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RD6JSM3PMMC2YUE7EAIRRSHHV5/bundle.json","state_url":"https://pith.science/pith/RD6JSM3PMMC2YUE7EAIRRSHHV5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RD6JSM3PMMC2YUE7EAIRRSHHV5/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":"2026-08-14T22:24:08Z","links":{"resolver":"https://pith.science/pith/RD6JSM3PMMC2YUE7EAIRRSHHV5","bundle":"https://pith.science/pith/RD6JSM3PMMC2YUE7EAIRRSHHV5/bundle.json","state":"https://pith.science/pith/RD6JSM3PMMC2YUE7EAIRRSHHV5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RD6JSM3PMMC2YUE7EAIRRSHHV5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RD6JSM3PMMC2YUE7EAIRRSHHV5","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":"798a682a9666bf4f83ae40779fdb5842f00a8733c84aa1f8b343c9a22dfce46e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-16T14:52:26Z","title_canon_sha256":"99f7024fe32ccbb7ca0d15a416fe2f5cb1c1001ebccbc3cff484896d8ff0815b"},"schema_version":"1.0","source":{"id":"2403.10940","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10940","created_at":"2026-07-05T09:23:04Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10940v3","created_at":"2026-07-05T09:23:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10940","created_at":"2026-07-05T09:23:04Z"},{"alias_kind":"pith_short_12","alias_value":"RD6JSM3PMMC2","created_at":"2026-07-05T09:23:04Z"},{"alias_kind":"pith_short_16","alias_value":"RD6JSM3PMMC2YUE7","created_at":"2026-07-05T09:23:04Z"},{"alias_kind":"pith_short_8","alias_value":"RD6JSM3P","created_at":"2026-07-05T09:23:04Z"}],"graph_snapshots":[{"event_id":"sha256:b4e27f4f5645003dc2cb4e221d9eb0eaf0388d834cc45c7ce23d170197aab0fe","target":"graph","created_at":"2026-07-05T09:23:04Z","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/2403.10940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training robots to perform complex control tasks from high-dimensional pixel input using reinforcement learning (RL) is sample-inefficient, because image observations are comprised primarily of task-irrelevant information. By contrast, humans are able to visually attend to task-relevant objects and areas. Based on this insight, we introduce Visual Saliency-Guided Reinforcement Learning (ViSaRL). Using ViSaRL to learn visual representations significantly improves the success rate, sample efficiency, and generalization of an RL agent on diverse tasks including DeepMind Control benchmark, robot m","authors_text":"Anthony Liang, Erdem B{\\i}y{\\i}k, Jesse Thomason","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-16T14:52:26Z","title":"ViSaRL: Visual Reinforcement Learning Guided by Human Saliency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10940","kind":"arxiv","version":3},"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":"sha256:718905d05fcb08329d76cec8a73fcc117ef3e7c53352e955c01d72dc4d94b863","target":"record","created_at":"2026-07-05T09:23:04Z","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":"798a682a9666bf4f83ae40779fdb5842f00a8733c84aa1f8b343c9a22dfce46e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-16T14:52:26Z","title_canon_sha256":"99f7024fe32ccbb7ca0d15a416fe2f5cb1c1001ebccbc3cff484896d8ff0815b"},"schema_version":"1.0","source":{"id":"2403.10940","kind":"arxiv","version":3}},"canonical_sha256":"88fc99336f6305ac509f201118c8e7af43fb4545ef444202a45773e18e3560fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88fc99336f6305ac509f201118c8e7af43fb4545ef444202a45773e18e3560fa","first_computed_at":"2026-07-05T09:23:04.279693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:04.279693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nyr2uBjTmiRjyftbk2onZvup3FR1yqavpjAQ5Wty5sCZvXlOcr6tOWzIAqLrA4VvavEWJX47oFlHwOWEUchnAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:04.280146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.10940","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:718905d05fcb08329d76cec8a73fcc117ef3e7c53352e955c01d72dc4d94b863","sha256:b4e27f4f5645003dc2cb4e221d9eb0eaf0388d834cc45c7ce23d170197aab0fe"],"state_sha256":"822e49cac2b5ea674675247dbda26a1b3cf14e1d50b5d8cb5eeec64d7f75615e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"scbm0uUVrqNct30nQx72K5KG7jIp1gI+QitnZK32QnL0KAvXhrPPX9p27HOUFNxLOqFOIbc1o85mw+yj+5oMCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T22:24:08.287087Z","bundle_sha256":"96aa40b0f1a3360c192f9d7ecdfa2b2dacfd4e01ec53949cb4ef8e18996a15f1"}}