{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:X2OBTUN3FERCXRG4YEGWPLS32V","short_pith_number":"pith:X2OBTUN3","canonical_record":{"source":{"id":"1905.07866","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-05-20T04:17:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ed0da2336aaccc6050027fcde9cea23ddc0ee62175a4fb0f71239e69f7ba1c36","abstract_canon_sha256":"e8a5df416aff4d003a1f0863abe81ea5dad2567275249a349b7097723ca79e73"},"schema_version":"1.0"},"canonical_sha256":"be9c19d1bb29222bc4dcc10d67ae5bd57968e23dd0630be6c410ab052b56ccc1","source":{"kind":"arxiv","id":"1905.07866","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07866","created_at":"2026-05-17T23:40:38Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07866v2","created_at":"2026-05-17T23:40:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07866","created_at":"2026-05-17T23:40:38Z"},{"alias_kind":"pith_short_12","alias_value":"X2OBTUN3FERC","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"X2OBTUN3FERCXRG4","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"X2OBTUN3","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:X2OBTUN3FERCXRG4YEGWPLS32V","target":"record","payload":{"canonical_record":{"source":{"id":"1905.07866","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-05-20T04:17:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ed0da2336aaccc6050027fcde9cea23ddc0ee62175a4fb0f71239e69f7ba1c36","abstract_canon_sha256":"e8a5df416aff4d003a1f0863abe81ea5dad2567275249a349b7097723ca79e73"},"schema_version":"1.0"},"canonical_sha256":"be9c19d1bb29222bc4dcc10d67ae5bd57968e23dd0630be6c410ab052b56ccc1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:38.746617Z","signature_b64":"bZDFqR3+rlb2r3zuRJhCGSUCoJykyh/nGHTJSwOv7ugGrt5YxdtpqxZ+5Kw5UDT5BLl99bdQzMDu11vPca+pDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be9c19d1bb29222bc4dcc10d67ae5bd57968e23dd0630be6c410ab052b56ccc1","last_reissued_at":"2026-05-17T23:40:38.745630Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:38.745630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.07866","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:40:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VLsdeiZcnsplABPdTNx5JKSTn8Dxq+Wude01OdcKqgJXbpLos69/6CMHSdaVPpx1VSsia+US5o6bULbQrFi+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T14:22:22.552746Z"},"content_sha256":"c5cf1345b5d2d75ce5a9f12c4928da91c32442418f0818687c6d1780f318c975","schema_version":"1.0","event_id":"sha256:c5cf1345b5d2d75ce5a9f12c4928da91c32442418f0818687c6d1780f318c975"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:X2OBTUN3FERCXRG4YEGWPLS32V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning without Ground-Truth State","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"David Held, Harjatin Singh Baweja, Xingyu Lin","submitted_at":"2019-05-20T04:17:03Z","abstract_excerpt":"To perform robot manipulation tasks, a low-dimensional state of the environment typically needs to be estimated. However, designing a state estimator can sometimes be difficult, especially in environments with deformable objects. An alternative is to learn an end-to-end policy that maps directly from high-dimensional sensor inputs to actions. However, if this policy is trained with reinforcement learning, then without a state estimator, it is hard to specify a reward function based on high-dimensional observations. To meet this challenge, we propose a simple indicator reward function for goal-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07866","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:40:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TMPMuliIhBn6dAJ+6wadvEVRSi1zv9rwAuzkn0NkK1xH2KzKTl0xzmbRKamCQSP/bVRAFa472OKrs7PPtULLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T14:22:22.553107Z"},"content_sha256":"5fa48c2232106b367af53ed57e5bd90a8ba8e1ddf10d367cd7767e7c797dd0ab","schema_version":"1.0","event_id":"sha256:5fa48c2232106b367af53ed57e5bd90a8ba8e1ddf10d367cd7767e7c797dd0ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X2OBTUN3FERCXRG4YEGWPLS32V/bundle.json","state_url":"https://pith.science/pith/X2OBTUN3FERCXRG4YEGWPLS32V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X2OBTUN3FERCXRG4YEGWPLS32V/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":"2026-06-04T14:22:22Z","links":{"resolver":"https://pith.science/pith/X2OBTUN3FERCXRG4YEGWPLS32V","bundle":"https://pith.science/pith/X2OBTUN3FERCXRG4YEGWPLS32V/bundle.json","state":"https://pith.science/pith/X2OBTUN3FERCXRG4YEGWPLS32V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X2OBTUN3FERCXRG4YEGWPLS32V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:X2OBTUN3FERCXRG4YEGWPLS32V","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":"e8a5df416aff4d003a1f0863abe81ea5dad2567275249a349b7097723ca79e73","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-05-20T04:17:03Z","title_canon_sha256":"ed0da2336aaccc6050027fcde9cea23ddc0ee62175a4fb0f71239e69f7ba1c36"},"schema_version":"1.0","source":{"id":"1905.07866","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07866","created_at":"2026-05-17T23:40:38Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07866v2","created_at":"2026-05-17T23:40:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07866","created_at":"2026-05-17T23:40:38Z"},{"alias_kind":"pith_short_12","alias_value":"X2OBTUN3FERC","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"X2OBTUN3FERCXRG4","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"X2OBTUN3","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:5fa48c2232106b367af53ed57e5bd90a8ba8e1ddf10d367cd7767e7c797dd0ab","target":"graph","created_at":"2026-05-17T23:40:38Z","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"},"paper":{"abstract_excerpt":"To perform robot manipulation tasks, a low-dimensional state of the environment typically needs to be estimated. However, designing a state estimator can sometimes be difficult, especially in environments with deformable objects. An alternative is to learn an end-to-end policy that maps directly from high-dimensional sensor inputs to actions. However, if this policy is trained with reinforcement learning, then without a state estimator, it is hard to specify a reward function based on high-dimensional observations. To meet this challenge, we propose a simple indicator reward function for goal-","authors_text":"David Held, Harjatin Singh Baweja, Xingyu Lin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-05-20T04:17:03Z","title":"Reinforcement Learning without Ground-Truth State"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07866","kind":"arxiv","version":2},"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:c5cf1345b5d2d75ce5a9f12c4928da91c32442418f0818687c6d1780f318c975","target":"record","created_at":"2026-05-17T23:40:38Z","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":"e8a5df416aff4d003a1f0863abe81ea5dad2567275249a349b7097723ca79e73","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-05-20T04:17:03Z","title_canon_sha256":"ed0da2336aaccc6050027fcde9cea23ddc0ee62175a4fb0f71239e69f7ba1c36"},"schema_version":"1.0","source":{"id":"1905.07866","kind":"arxiv","version":2}},"canonical_sha256":"be9c19d1bb29222bc4dcc10d67ae5bd57968e23dd0630be6c410ab052b56ccc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be9c19d1bb29222bc4dcc10d67ae5bd57968e23dd0630be6c410ab052b56ccc1","first_computed_at":"2026-05-17T23:40:38.745630Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:38.745630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bZDFqR3+rlb2r3zuRJhCGSUCoJykyh/nGHTJSwOv7ugGrt5YxdtpqxZ+5Kw5UDT5BLl99bdQzMDu11vPca+pDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:38.746617Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.07866","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5cf1345b5d2d75ce5a9f12c4928da91c32442418f0818687c6d1780f318c975","sha256:5fa48c2232106b367af53ed57e5bd90a8ba8e1ddf10d367cd7767e7c797dd0ab"],"state_sha256":"35ff74da2cfd5d61186d38ceadfbe49271da6413ab0130ad6010790a4998338c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L8ezonV8h/ZIhxY9+wKlDuEF6M7txaqf+q8AHPk5M7ibhAxeQq/hEa4M9a8TjE0UUJgJ/oi7Hb1QuAEbMdlFDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T14:22:22.555195Z","bundle_sha256":"954d5926b54ea1b92f66ae10a004e6d3bc81308a431235b9ebbebc92d1676a60"}}