{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:S3ZNAO65MPNSVNHWVZE5CGYN6Z","short_pith_number":"pith:S3ZNAO65","canonical_record":{"source":{"id":"1702.05796","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-19T21:13:45Z","cross_cats_sorted":[],"title_canon_sha256":"e89800e58f83c9e36d84351f36d910d1fef18db01dbd6860cfe674b6d23893a1","abstract_canon_sha256":"a4ae25c1ec60b173b1af0c0e54237a274535c66945e437962b3d4b80624119b0"},"schema_version":"1.0"},"canonical_sha256":"96f2d03bdd63db2ab4f6ae49d11b0df6470d2ae1756047845c4f1f44de99ae9f","source":{"kind":"arxiv","id":"1702.05796","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.05796","created_at":"2026-05-18T00:50:25Z"},{"alias_kind":"arxiv_version","alias_value":"1702.05796v1","created_at":"2026-05-18T00:50:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.05796","created_at":"2026-05-18T00:50:25Z"},{"alias_kind":"pith_short_12","alias_value":"S3ZNAO65MPNS","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"S3ZNAO65MPNSVNHW","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"S3ZNAO65","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:S3ZNAO65MPNSVNHWVZE5CGYN6Z","target":"record","payload":{"canonical_record":{"source":{"id":"1702.05796","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-19T21:13:45Z","cross_cats_sorted":[],"title_canon_sha256":"e89800e58f83c9e36d84351f36d910d1fef18db01dbd6860cfe674b6d23893a1","abstract_canon_sha256":"a4ae25c1ec60b173b1af0c0e54237a274535c66945e437962b3d4b80624119b0"},"schema_version":"1.0"},"canonical_sha256":"96f2d03bdd63db2ab4f6ae49d11b0df6470d2ae1756047845c4f1f44de99ae9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:25.328140Z","signature_b64":"LLf5bNBiu2vY1ev3/AMPjyg9crfAbeI7jv4J+x/snXylwhSikO0vxQOv8PYONg+GqpR5/mrsoZmwZ6U2NFQfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96f2d03bdd63db2ab4f6ae49d11b0df6470d2ae1756047845c4f1f44de99ae9f","last_reissued_at":"2026-05-18T00:50:25.327266Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:25.327266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.05796","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":"2026-05-18T00:50:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KhPSsnUrX3Sxa8q6nUinTIvVJDhZbeMkVNNNECje7r09UfEUhncMbx7+2vG/rd9uKywo6yuLQrDX90vaqshdBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T12:25:05.150975Z"},"content_sha256":"4f7a55055a0c23c627c06ca76b485ebe6029c25a4fd9b56694b84568ee958687","schema_version":"1.0","event_id":"sha256:4f7a55055a0c23c627c06ca76b485ebe6029c25a4fd9b56694b84568ee958687"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:S3ZNAO65MPNSVNHWVZE5CGYN6Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Collaborative Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiayu Zhou, Kaixiang Lin, Shu Wang","submitted_at":"2017-02-19T21:13:45Z","abstract_excerpt":"Besides independent learning, human learning process is highly improved by summarizing what has been learned, communicating it with peers, and subsequently fusing knowledge from different sources to assist the current learning goal. This collaborative learning procedure ensures that the knowledge is shared, continuously refined, and concluded from different perspectives to construct a more profound understanding. The idea of knowledge transfer has led to many advances in machine learning and data mining, but significant challenges remain, especially when it comes to reinforcement learning, het"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.05796","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":"2026-05-18T00:50:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lrz32rcHR0rFUh+TqusFNPSK1QMgQZC6x6mIuV6FasUXBdQ321kST0FG8VJ5jieSnkAvO+i4uC6cXnhHTWD5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T12:25:05.151795Z"},"content_sha256":"b05536ecdd4304f914edd73b69fcc8a0bd6fff14cf29e1de422283f08ad12db8","schema_version":"1.0","event_id":"sha256:b05536ecdd4304f914edd73b69fcc8a0bd6fff14cf29e1de422283f08ad12db8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S3ZNAO65MPNSVNHWVZE5CGYN6Z/bundle.json","state_url":"https://pith.science/pith/S3ZNAO65MPNSVNHWVZE5CGYN6Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S3ZNAO65MPNSVNHWVZE5CGYN6Z/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":"2026-05-31T12:25:05Z","links":{"resolver":"https://pith.science/pith/S3ZNAO65MPNSVNHWVZE5CGYN6Z","bundle":"https://pith.science/pith/S3ZNAO65MPNSVNHWVZE5CGYN6Z/bundle.json","state":"https://pith.science/pith/S3ZNAO65MPNSVNHWVZE5CGYN6Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S3ZNAO65MPNSVNHWVZE5CGYN6Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:S3ZNAO65MPNSVNHWVZE5CGYN6Z","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":"a4ae25c1ec60b173b1af0c0e54237a274535c66945e437962b3d4b80624119b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-19T21:13:45Z","title_canon_sha256":"e89800e58f83c9e36d84351f36d910d1fef18db01dbd6860cfe674b6d23893a1"},"schema_version":"1.0","source":{"id":"1702.05796","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.05796","created_at":"2026-05-18T00:50:25Z"},{"alias_kind":"arxiv_version","alias_value":"1702.05796v1","created_at":"2026-05-18T00:50:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.05796","created_at":"2026-05-18T00:50:25Z"},{"alias_kind":"pith_short_12","alias_value":"S3ZNAO65MPNS","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"S3ZNAO65MPNSVNHW","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"S3ZNAO65","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:b05536ecdd4304f914edd73b69fcc8a0bd6fff14cf29e1de422283f08ad12db8","target":"graph","created_at":"2026-05-18T00:50:25Z","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":"Besides independent learning, human learning process is highly improved by summarizing what has been learned, communicating it with peers, and subsequently fusing knowledge from different sources to assist the current learning goal. This collaborative learning procedure ensures that the knowledge is shared, continuously refined, and concluded from different perspectives to construct a more profound understanding. The idea of knowledge transfer has led to many advances in machine learning and data mining, but significant challenges remain, especially when it comes to reinforcement learning, het","authors_text":"Jiayu Zhou, Kaixiang Lin, Shu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-19T21:13:45Z","title":"Collaborative Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.05796","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":"sha256:4f7a55055a0c23c627c06ca76b485ebe6029c25a4fd9b56694b84568ee958687","target":"record","created_at":"2026-05-18T00:50:25Z","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":"a4ae25c1ec60b173b1af0c0e54237a274535c66945e437962b3d4b80624119b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-19T21:13:45Z","title_canon_sha256":"e89800e58f83c9e36d84351f36d910d1fef18db01dbd6860cfe674b6d23893a1"},"schema_version":"1.0","source":{"id":"1702.05796","kind":"arxiv","version":1}},"canonical_sha256":"96f2d03bdd63db2ab4f6ae49d11b0df6470d2ae1756047845c4f1f44de99ae9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96f2d03bdd63db2ab4f6ae49d11b0df6470d2ae1756047845c4f1f44de99ae9f","first_computed_at":"2026-05-18T00:50:25.327266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:25.327266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LLf5bNBiu2vY1ev3/AMPjyg9crfAbeI7jv4J+x/snXylwhSikO0vxQOv8PYONg+GqpR5/mrsoZmwZ6U2NFQfDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:25.328140Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.05796","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f7a55055a0c23c627c06ca76b485ebe6029c25a4fd9b56694b84568ee958687","sha256:b05536ecdd4304f914edd73b69fcc8a0bd6fff14cf29e1de422283f08ad12db8"],"state_sha256":"989078cce84b9d04693f641e734ce40d3c2b3223108c27b544ffa608ced7c8c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kyFUWc7ZyRSz2MUiwhacu7pODhRe4NcMyCxmomWF4wcDU88KjVKUe8SoAh0gxSZuU/4hdPwnQT6Pu7ip0DPuAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T12:25:05.156580Z","bundle_sha256":"c867d996c0c5c5c5e2ed4cf6b9b21fc2519faf53f7a106c8a2736e771d2430b4"}}