{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:2JKBI4LBVTGCSFH74PRWHHVF4Z","short_pith_number":"pith:2JKBI4LB","canonical_record":{"source":{"id":"1507.01273","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-05T20:54:57Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"229cef81e139b6d9adb2356e5a00113dd7048c4e9c22fa121bcf224f3651894b","abstract_canon_sha256":"de593ff9a052ea07f3ce6e02e92d82121eb16d6057918b7b2cf25352963fedbc"},"schema_version":"1.0"},"canonical_sha256":"d254147161accc2914ffe3e3639ea5e66b5b48730dfae0fd708a18fe2b18288d","source":{"kind":"arxiv","id":"1507.01273","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.01273","created_at":"2026-05-18T01:32:18Z"},{"alias_kind":"arxiv_version","alias_value":"1507.01273v2","created_at":"2026-05-18T01:32:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.01273","created_at":"2026-05-18T01:32:18Z"},{"alias_kind":"pith_short_12","alias_value":"2JKBI4LBVTGC","created_at":"2026-05-18T12:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"2JKBI4LBVTGCSFH7","created_at":"2026-05-18T12:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"2JKBI4LB","created_at":"2026-05-18T12:28:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:2JKBI4LBVTGCSFH74PRWHHVF4Z","target":"record","payload":{"canonical_record":{"source":{"id":"1507.01273","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-05T20:54:57Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"229cef81e139b6d9adb2356e5a00113dd7048c4e9c22fa121bcf224f3651894b","abstract_canon_sha256":"de593ff9a052ea07f3ce6e02e92d82121eb16d6057918b7b2cf25352963fedbc"},"schema_version":"1.0"},"canonical_sha256":"d254147161accc2914ffe3e3639ea5e66b5b48730dfae0fd708a18fe2b18288d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:32:18.367591Z","signature_b64":"uRDUz/4MIjTX1zaxLJwG1MmzPDf8bkZPCZM+PwTfEH4NHjKd/J/v94ZCvekyE48x7wtuJ83/Z6yHh/rdUPPeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d254147161accc2914ffe3e3639ea5e66b5b48730dfae0fd708a18fe2b18288d","last_reissued_at":"2026-05-18T01:32:18.366052Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:32:18.366052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.01273","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":"2026-05-18T01:32:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"McM+EteWRP5yHShT1rvRFte8Yxa2B7E2cKemrH1DA5UpNKQLYSaQcIAIB99ODT3MQ9clLUojPE7nJS+NYo61DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T05:18:36.718301Z"},"content_sha256":"e73027092cc6c4d90cf4e255f87f251b9020bfb5652d9e31b37e48615543b19f","schema_version":"1.0","event_id":"sha256:e73027092cc6c4d90cf4e255f87f251b9020bfb5652d9e31b37e48615543b19f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:2JKBI4LBVTGCSFH74PRWHHVF4Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Deep Neural Network Policies with Continuous Memory States","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Marvin Zhang, Pieter Abbeel, Sergey Levine, Zoe McCarthy","submitted_at":"2015-07-05T20:54:57Z","abstract_excerpt":"Policy learning for partially observed control tasks requires policies that can remember salient information from past observations. In this paper, we present a method for learning policies with internal memory for high-dimensional, continuous systems, such as robotic manipulators. Our approach consists of augmenting the state and action space of the system with continuous-valued memory states that the policy can read from and write to. Learning general-purpose policies with this type of memory representation directly is difficult, because the policy must automatically figure out the most sali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.01273","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":"2026-05-18T01:32:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+9r81yK9YTIBrRq4VJx8sdf4Cp58t4R3LljH+FWMCq1EjXia9ksnveOQjyiDkQC5FPkAU5EPYydtbUlKE3vKAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T05:18:36.718957Z"},"content_sha256":"32c95d721c85e6e6cb1206c8f2e75f08362f6dc26bb1e96f206ac25e043104c8","schema_version":"1.0","event_id":"sha256:32c95d721c85e6e6cb1206c8f2e75f08362f6dc26bb1e96f206ac25e043104c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z/bundle.json","state_url":"https://pith.science/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z/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":"2026-06-12T05:18:36Z","links":{"resolver":"https://pith.science/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z","bundle":"https://pith.science/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z/bundle.json","state":"https://pith.science/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:2JKBI4LBVTGCSFH74PRWHHVF4Z","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":"de593ff9a052ea07f3ce6e02e92d82121eb16d6057918b7b2cf25352963fedbc","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-05T20:54:57Z","title_canon_sha256":"229cef81e139b6d9adb2356e5a00113dd7048c4e9c22fa121bcf224f3651894b"},"schema_version":"1.0","source":{"id":"1507.01273","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.01273","created_at":"2026-05-18T01:32:18Z"},{"alias_kind":"arxiv_version","alias_value":"1507.01273v2","created_at":"2026-05-18T01:32:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.01273","created_at":"2026-05-18T01:32:18Z"},{"alias_kind":"pith_short_12","alias_value":"2JKBI4LBVTGC","created_at":"2026-05-18T12:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"2JKBI4LBVTGCSFH7","created_at":"2026-05-18T12:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"2JKBI4LB","created_at":"2026-05-18T12:28:59Z"}],"graph_snapshots":[{"event_id":"sha256:32c95d721c85e6e6cb1206c8f2e75f08362f6dc26bb1e96f206ac25e043104c8","target":"graph","created_at":"2026-05-18T01:32:18Z","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":"Policy learning for partially observed control tasks requires policies that can remember salient information from past observations. In this paper, we present a method for learning policies with internal memory for high-dimensional, continuous systems, such as robotic manipulators. Our approach consists of augmenting the state and action space of the system with continuous-valued memory states that the policy can read from and write to. Learning general-purpose policies with this type of memory representation directly is difficult, because the policy must automatically figure out the most sali","authors_text":"Chelsea Finn, Marvin Zhang, Pieter Abbeel, Sergey Levine, Zoe McCarthy","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-05T20:54:57Z","title":"Learning Deep Neural Network Policies with Continuous Memory States"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.01273","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:e73027092cc6c4d90cf4e255f87f251b9020bfb5652d9e31b37e48615543b19f","target":"record","created_at":"2026-05-18T01:32:18Z","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":"de593ff9a052ea07f3ce6e02e92d82121eb16d6057918b7b2cf25352963fedbc","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-05T20:54:57Z","title_canon_sha256":"229cef81e139b6d9adb2356e5a00113dd7048c4e9c22fa121bcf224f3651894b"},"schema_version":"1.0","source":{"id":"1507.01273","kind":"arxiv","version":2}},"canonical_sha256":"d254147161accc2914ffe3e3639ea5e66b5b48730dfae0fd708a18fe2b18288d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d254147161accc2914ffe3e3639ea5e66b5b48730dfae0fd708a18fe2b18288d","first_computed_at":"2026-05-18T01:32:18.366052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:32:18.366052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uRDUz/4MIjTX1zaxLJwG1MmzPDf8bkZPCZM+PwTfEH4NHjKd/J/v94ZCvekyE48x7wtuJ83/Z6yHh/rdUPPeBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:32:18.367591Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.01273","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e73027092cc6c4d90cf4e255f87f251b9020bfb5652d9e31b37e48615543b19f","sha256:32c95d721c85e6e6cb1206c8f2e75f08362f6dc26bb1e96f206ac25e043104c8"],"state_sha256":"005ea39b8b12fd845a2bcde5cf01a8c37863a545a39d8b24d1a060f677edb256"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dbK4gtXbpgp4WBsfX0kdkUXnQtNL1nDDw02ue6suwHKFcy2vAxmxmwMbgOuWJHRri1g1b1K6ruOb5X/bR0T5Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T05:18:36.722390Z","bundle_sha256":"f8e9eb960a8ec9e63a98ab9aa7b822f1de4234f6af42f087cb38ddcfdc9d7ccb"}}