{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:RGQ6EY5M6Z6BY64YMFQMCUU27M","short_pith_number":"pith:RGQ6EY5M","canonical_record":{"source":{"id":"1609.07088","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-22T17:59:25Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"3466a84b6703c5c2ba08fbc4aa62a7f1969f04d149cf41f0ff74158de75eaa92","abstract_canon_sha256":"bb1bf961d96b7e5f3f4760364ff09f9ef7169f9541e77da065190f2ba3fbd545"},"schema_version":"1.0"},"canonical_sha256":"89a1e263acf67c1c7b986160c1529afb3f038aa187d730a6a13d4229b5cc0eaa","source":{"kind":"arxiv","id":"1609.07088","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.07088","created_at":"2026-05-18T01:04:04Z"},{"alias_kind":"arxiv_version","alias_value":"1609.07088v1","created_at":"2026-05-18T01:04:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.07088","created_at":"2026-05-18T01:04:04Z"},{"alias_kind":"pith_short_12","alias_value":"RGQ6EY5M6Z6B","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RGQ6EY5M6Z6BY64Y","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RGQ6EY5M","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:RGQ6EY5M6Z6BY64YMFQMCUU27M","target":"record","payload":{"canonical_record":{"source":{"id":"1609.07088","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-22T17:59:25Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"3466a84b6703c5c2ba08fbc4aa62a7f1969f04d149cf41f0ff74158de75eaa92","abstract_canon_sha256":"bb1bf961d96b7e5f3f4760364ff09f9ef7169f9541e77da065190f2ba3fbd545"},"schema_version":"1.0"},"canonical_sha256":"89a1e263acf67c1c7b986160c1529afb3f038aa187d730a6a13d4229b5cc0eaa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:04.489280Z","signature_b64":"n7y/3B9aIY/STz+EJhLaZ91kiNSPuRQZrbqRbCfURI0HHJIhv1o45Bk2V0vgWkuIqz7z0OnnxfCY69trpelXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89a1e263acf67c1c7b986160c1529afb3f038aa187d730a6a13d4229b5cc0eaa","last_reissued_at":"2026-05-18T01:04:04.488918Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:04.488918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.07088","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":"2026-05-18T01:04:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6s7U/k8yTfLcMurxHiI9lg2Y3MCSyEwpk4cMOBKBpwITNTMLMxqNWAPTVeg2hW7vTRscXKeXEag0u/WxzPsPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T11:07:01.030068Z"},"content_sha256":"1021498bc2a4aa033f06407d9d212c7846a9180ad9abd3cda8a8c27f60d7cab9","schema_version":"1.0","event_id":"sha256:1021498bc2a4aa033f06407d9d212c7846a9180ad9abd3cda8a8c27f60d7cab9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:RGQ6EY5M6Z6BY64YMFQMCUU27M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Coline Devin, Pieter Abbeel, Sergey Levine, Trevor Darrell","submitted_at":"2016-09-22T17:59:25Z","abstract_excerpt":"Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep reinforcement learning to train general purpose neural network policies alleviates some of the burden of manual representation engineering by using expressive policy classes, but exacerbates the challenge of data collection, since such methods tend to be less efficient than RL with low-dimensional, hand-designed representations. Transfer learning can mitigate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.07088","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":""},"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":"2026-05-18T01:04:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C+9PELXKphQs0yarIg/XT3oGPMljB1PsNp9nGUGnknznQ7QjcbLfwFnU5hF2ikGKzZY8g3z/f1TNPrr8wm0HBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T11:07:01.030429Z"},"content_sha256":"ff4060ba8fb93c56998b1bc0c099049639779d524503d05dad1fd9e878de81f3","schema_version":"1.0","event_id":"sha256:ff4060ba8fb93c56998b1bc0c099049639779d524503d05dad1fd9e878de81f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M/bundle.json","state_url":"https://pith.science/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M/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":"2026-06-01T11:07:01Z","links":{"resolver":"https://pith.science/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M","bundle":"https://pith.science/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M/bundle.json","state":"https://pith.science/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:RGQ6EY5M6Z6BY64YMFQMCUU27M","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":"bb1bf961d96b7e5f3f4760364ff09f9ef7169f9541e77da065190f2ba3fbd545","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-22T17:59:25Z","title_canon_sha256":"3466a84b6703c5c2ba08fbc4aa62a7f1969f04d149cf41f0ff74158de75eaa92"},"schema_version":"1.0","source":{"id":"1609.07088","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.07088","created_at":"2026-05-18T01:04:04Z"},{"alias_kind":"arxiv_version","alias_value":"1609.07088v1","created_at":"2026-05-18T01:04:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.07088","created_at":"2026-05-18T01:04:04Z"},{"alias_kind":"pith_short_12","alias_value":"RGQ6EY5M6Z6B","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RGQ6EY5M6Z6BY64Y","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RGQ6EY5M","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:ff4060ba8fb93c56998b1bc0c099049639779d524503d05dad1fd9e878de81f3","target":"graph","created_at":"2026-05-18T01:04:04Z","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"},"paper":{"abstract_excerpt":"Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep reinforcement learning to train general purpose neural network policies alleviates some of the burden of manual representation engineering by using expressive policy classes, but exacerbates the challenge of data collection, since such methods tend to be less efficient than RL with low-dimensional, hand-designed representations. Transfer learning can mitigate","authors_text":"Abhishek Gupta, Coline Devin, Pieter Abbeel, Sergey Levine, Trevor Darrell","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-22T17:59:25Z","title":"Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.07088","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":"sha256:1021498bc2a4aa033f06407d9d212c7846a9180ad9abd3cda8a8c27f60d7cab9","target":"record","created_at":"2026-05-18T01:04:04Z","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":"bb1bf961d96b7e5f3f4760364ff09f9ef7169f9541e77da065190f2ba3fbd545","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-22T17:59:25Z","title_canon_sha256":"3466a84b6703c5c2ba08fbc4aa62a7f1969f04d149cf41f0ff74158de75eaa92"},"schema_version":"1.0","source":{"id":"1609.07088","kind":"arxiv","version":1}},"canonical_sha256":"89a1e263acf67c1c7b986160c1529afb3f038aa187d730a6a13d4229b5cc0eaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89a1e263acf67c1c7b986160c1529afb3f038aa187d730a6a13d4229b5cc0eaa","first_computed_at":"2026-05-18T01:04:04.488918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:04.488918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n7y/3B9aIY/STz+EJhLaZ91kiNSPuRQZrbqRbCfURI0HHJIhv1o45Bk2V0vgWkuIqz7z0OnnxfCY69trpelXDA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:04.489280Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.07088","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1021498bc2a4aa033f06407d9d212c7846a9180ad9abd3cda8a8c27f60d7cab9","sha256:ff4060ba8fb93c56998b1bc0c099049639779d524503d05dad1fd9e878de81f3"],"state_sha256":"776c8cc51f9c8af8a3112906ad4b8b806ea096eee68bf2a934b0d0c5c2e5aa57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+E6B070W554z1m69/hvR4gxr2KNHPK8d+1c4XmkLQhVbugDWOgo2INZopsPY3SG3t9kxy48HqlB6kkpE+WVwAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T11:07:01.032491Z","bundle_sha256":"f0b29e21ce3d4a396a4fc7200834216d3ecef78e07b1f3403d0be7de1e0e6f19"}}