{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ULFHOEQMSTY3LDVQLJMO2RD3B4","short_pith_number":"pith:ULFHOEQM","canonical_record":{"source":{"id":"2303.01488","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-02T18:51:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"68bec472d5a2d765ae2fb282150929afbeb3a99b8483d47a718e6dfe97b1ab59","abstract_canon_sha256":"67a3143a7ff1f03b57042abad1ee54c3bba98ec0eddec80545859a70851e0ea6"},"schema_version":"1.0"},"canonical_sha256":"a2ca77120c94f1b58eb05a58ed447b0f05369f62b6148b61cfb5ba1b8fd8b79e","source":{"kind":"arxiv","id":"2303.01488","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.01488","created_at":"2026-07-05T05:47:31Z"},{"alias_kind":"arxiv_version","alias_value":"2303.01488v1","created_at":"2026-07-05T05:47:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01488","created_at":"2026-07-05T05:47:31Z"},{"alias_kind":"pith_short_12","alias_value":"ULFHOEQMSTY3","created_at":"2026-07-05T05:47:31Z"},{"alias_kind":"pith_short_16","alias_value":"ULFHOEQMSTY3LDVQ","created_at":"2026-07-05T05:47:31Z"},{"alias_kind":"pith_short_8","alias_value":"ULFHOEQM","created_at":"2026-07-05T05:47:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ULFHOEQMSTY3LDVQLJMO2RD3B4","target":"record","payload":{"canonical_record":{"source":{"id":"2303.01488","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-02T18:51:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"68bec472d5a2d765ae2fb282150929afbeb3a99b8483d47a718e6dfe97b1ab59","abstract_canon_sha256":"67a3143a7ff1f03b57042abad1ee54c3bba98ec0eddec80545859a70851e0ea6"},"schema_version":"1.0"},"canonical_sha256":"a2ca77120c94f1b58eb05a58ed447b0f05369f62b6148b61cfb5ba1b8fd8b79e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:31.596465Z","signature_b64":"6DzmrGSbisOEOdRq9AQT0cuuDOCHYhb/ZJaVA9J4QATUjPTSys1zokx6XUakW8pUSUVFniVYcjtWpRtNHORhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2ca77120c94f1b58eb05a58ed447b0f05369f62b6148b61cfb5ba1b8fd8b79e","last_reissued_at":"2026-07-05T05:47:31.596035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:31.596035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.01488","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":"2026-07-05T05:47:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gx+I+Vn779Lf9InSV0QC3CUtbiLWKNozZ6LbqZmAcQeJCFcPghClKqpoPLcZBQvWrNrhnZtY2MKvO8eGDqggDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:38:03.782949Z"},"content_sha256":"f5c2cfb46282df8bd48b50374cf0a87943a0569f819f68c85890643a033f45ed","schema_version":"1.0","event_id":"sha256:f5c2cfb46282df8bd48b50374cf0a87943a0569f819f68c85890643a033f45ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ULFHOEQMSTY3LDVQLJMO2RD3B4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ahmed M. Ahmed, Archit Sharma, Chelsea Finn, Rehaan Ahmad","submitted_at":"2023-03-02T18:51:38Z","abstract_excerpt":"In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on. An aspirational goal is to construct self-improving robots: robots that can learn and improve on their own, from autonomous interaction with minimal human supervision or oversight. Such robots could collect and train on much larger datasets, and thus learn more robust and performant policies. While reinforcement learning offers a framework for such autonomous learning via trial-and-error, practical realizations end up requiring extensive human supervision for reward f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01488","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/2303.01488/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":"2026-07-05T05:47:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lCk+gR+6M9VQtLmjsqoC5HebLzFwneVDjdqnwUy9H2cTkPJz73pPWD6OzHav9FIzh6BdKCKb6+i5arWtrYlFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:38:03.783357Z"},"content_sha256":"f0b90a7617ef6d5bac4c7ed005b671de643877f51616bfcb2e627aab11789c70","schema_version":"1.0","event_id":"sha256:f0b90a7617ef6d5bac4c7ed005b671de643877f51616bfcb2e627aab11789c70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ULFHOEQMSTY3LDVQLJMO2RD3B4/bundle.json","state_url":"https://pith.science/pith/ULFHOEQMSTY3LDVQLJMO2RD3B4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ULFHOEQMSTY3LDVQLJMO2RD3B4/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":"2026-08-07T18:38:03Z","links":{"resolver":"https://pith.science/pith/ULFHOEQMSTY3LDVQLJMO2RD3B4","bundle":"https://pith.science/pith/ULFHOEQMSTY3LDVQLJMO2RD3B4/bundle.json","state":"https://pith.science/pith/ULFHOEQMSTY3LDVQLJMO2RD3B4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ULFHOEQMSTY3LDVQLJMO2RD3B4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ULFHOEQMSTY3LDVQLJMO2RD3B4","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":"67a3143a7ff1f03b57042abad1ee54c3bba98ec0eddec80545859a70851e0ea6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-02T18:51:38Z","title_canon_sha256":"68bec472d5a2d765ae2fb282150929afbeb3a99b8483d47a718e6dfe97b1ab59"},"schema_version":"1.0","source":{"id":"2303.01488","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.01488","created_at":"2026-07-05T05:47:31Z"},{"alias_kind":"arxiv_version","alias_value":"2303.01488v1","created_at":"2026-07-05T05:47:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01488","created_at":"2026-07-05T05:47:31Z"},{"alias_kind":"pith_short_12","alias_value":"ULFHOEQMSTY3","created_at":"2026-07-05T05:47:31Z"},{"alias_kind":"pith_short_16","alias_value":"ULFHOEQMSTY3LDVQ","created_at":"2026-07-05T05:47:31Z"},{"alias_kind":"pith_short_8","alias_value":"ULFHOEQM","created_at":"2026-07-05T05:47:31Z"}],"graph_snapshots":[{"event_id":"sha256:f0b90a7617ef6d5bac4c7ed005b671de643877f51616bfcb2e627aab11789c70","target":"graph","created_at":"2026-07-05T05:47:31Z","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/2303.01488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on. An aspirational goal is to construct self-improving robots: robots that can learn and improve on their own, from autonomous interaction with minimal human supervision or oversight. Such robots could collect and train on much larger datasets, and thus learn more robust and performant policies. While reinforcement learning offers a framework for such autonomous learning via trial-and-error, practical realizations end up requiring extensive human supervision for reward f","authors_text":"Ahmed M. Ahmed, Archit Sharma, Chelsea Finn, Rehaan Ahmad","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-02T18:51:38Z","title":"Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01488","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:f5c2cfb46282df8bd48b50374cf0a87943a0569f819f68c85890643a033f45ed","target":"record","created_at":"2026-07-05T05:47:31Z","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":"67a3143a7ff1f03b57042abad1ee54c3bba98ec0eddec80545859a70851e0ea6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-02T18:51:38Z","title_canon_sha256":"68bec472d5a2d765ae2fb282150929afbeb3a99b8483d47a718e6dfe97b1ab59"},"schema_version":"1.0","source":{"id":"2303.01488","kind":"arxiv","version":1}},"canonical_sha256":"a2ca77120c94f1b58eb05a58ed447b0f05369f62b6148b61cfb5ba1b8fd8b79e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2ca77120c94f1b58eb05a58ed447b0f05369f62b6148b61cfb5ba1b8fd8b79e","first_computed_at":"2026-07-05T05:47:31.596035Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:31.596035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6DzmrGSbisOEOdRq9AQT0cuuDOCHYhb/ZJaVA9J4QATUjPTSys1zokx6XUakW8pUSUVFniVYcjtWpRtNHORhAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:31.596465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.01488","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5c2cfb46282df8bd48b50374cf0a87943a0569f819f68c85890643a033f45ed","sha256:f0b90a7617ef6d5bac4c7ed005b671de643877f51616bfcb2e627aab11789c70"],"state_sha256":"7a4ee069b7969349afdcb4836887f0817a771440803f8ee0205bb444909c91bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tQiVRB2U0VBo4BEv1Z/uX8qzDkoWA3hWBFN8sgf3HrjqbJxBrfsN/0jtO8LhdLnBsf2iTc7xZZ7S1UJL56BTCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:38:03.786119Z","bundle_sha256":"ade1ad70398e212667e80d6ca318cfab276079c6ec0ba90cfc28a450d13f13ed"}}