{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:INQ6BMPKYPQMMLIEKRKGT55BPJ","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":"2b0df03196e7867829cfe7a5b1edfdd7408d5dc8cf3d11f05c37acd8730ae01d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-02-28T01:54:56Z","title_canon_sha256":"70b52bc7d84331f980477f07f4edbf07e42957a577f02c85d7016bf959e619b4"},"schema_version":"1.0","source":{"id":"2302.14242","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.14242","created_at":"2026-07-05T05:46:42Z"},{"alias_kind":"arxiv_version","alias_value":"2302.14242v1","created_at":"2026-07-05T05:46:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14242","created_at":"2026-07-05T05:46:42Z"},{"alias_kind":"pith_short_12","alias_value":"INQ6BMPKYPQM","created_at":"2026-07-05T05:46:42Z"},{"alias_kind":"pith_short_16","alias_value":"INQ6BMPKYPQMMLIE","created_at":"2026-07-05T05:46:42Z"},{"alias_kind":"pith_short_8","alias_value":"INQ6BMPK","created_at":"2026-07-05T05:46:42Z"}],"graph_snapshots":[{"event_id":"sha256:5060322f7467b247e62f6af99171ffcad2a9443267b597f323669ff2f01119b0","target":"graph","created_at":"2026-07-05T05:46:42Z","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/2302.14242/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in deep reinforcement learning (RL) and computer vision enables artificial agents to solve complex tasks, including locomotion, manipulation and video games from high-dimensional pixel observations. However, domain specific reward functions are often engineered to provide sufficient learning signals, requiring expert knowledge. While it is possible to train vision-based RL agents using only sparse rewards, additional challenges in exploration arise. We present a novel and efficient method to solve sparse-reward robot manipulation tasks from only image observations by utilizing ","authors_text":"Mariano Phielipp, Ruihan Zhao, Sandeep Chinchali, Ufuk Topcu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-02-28T01:54:56Z","title":"Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14242","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:c1931965df5d0d1345e13a58174d589cd10eceb541b871197daee8d119c1f263","target":"record","created_at":"2026-07-05T05:46:42Z","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":"2b0df03196e7867829cfe7a5b1edfdd7408d5dc8cf3d11f05c37acd8730ae01d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-02-28T01:54:56Z","title_canon_sha256":"70b52bc7d84331f980477f07f4edbf07e42957a577f02c85d7016bf959e619b4"},"schema_version":"1.0","source":{"id":"2302.14242","kind":"arxiv","version":1}},"canonical_sha256":"4361e0b1eac3e0c62d04545469f7a17a7bb50c8c6a74987a19d5748800598d3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4361e0b1eac3e0c62d04545469f7a17a7bb50c8c6a74987a19d5748800598d3d","first_computed_at":"2026-07-05T05:46:42.382394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:46:42.382394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5k/P5hwdvpLq9XSLUzbUhF/S3cTTWcikFK6ZnpEBXmrWWVHZ3T6rGmgyPW0AUl61emdp72dy8b784Jl8xpJUAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:46:42.382816Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.14242","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1931965df5d0d1345e13a58174d589cd10eceb541b871197daee8d119c1f263","sha256:5060322f7467b247e62f6af99171ffcad2a9443267b597f323669ff2f01119b0"],"state_sha256":"c839469faab224331f72e7cfb76679034d32754732dbd10ffcfeb07b9963e4c3"}