{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:TDUX4B64KK7WFNIVIVFV3F4WXA","short_pith_number":"pith:TDUX4B64","canonical_record":{"source":{"id":"1511.06342","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T20:17:27Z","cross_cats_sorted":[],"title_canon_sha256":"19f5006f94e78c5954ff9c36083c3a813836158a428f72f269e8e14cbbabb4f1","abstract_canon_sha256":"b9b1fe5e573e578eda9c68655809be9ee45237ddbf63b211cee78bf6aea71a92"},"schema_version":"1.0"},"canonical_sha256":"98e97e07dc52bf62b515454b5d9796b8320f9f3b0509e4a0a0328d390c9b7e93","source":{"kind":"arxiv","id":"1511.06342","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06342","created_at":"2026-05-18T01:20:16Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06342v4","created_at":"2026-05-18T01:20:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06342","created_at":"2026-05-18T01:20:16Z"},{"alias_kind":"pith_short_12","alias_value":"TDUX4B64KK7W","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"TDUX4B64KK7WFNIV","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"TDUX4B64","created_at":"2026-05-18T12:29:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:TDUX4B64KK7WFNIVIVFV3F4WXA","target":"record","payload":{"canonical_record":{"source":{"id":"1511.06342","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T20:17:27Z","cross_cats_sorted":[],"title_canon_sha256":"19f5006f94e78c5954ff9c36083c3a813836158a428f72f269e8e14cbbabb4f1","abstract_canon_sha256":"b9b1fe5e573e578eda9c68655809be9ee45237ddbf63b211cee78bf6aea71a92"},"schema_version":"1.0"},"canonical_sha256":"98e97e07dc52bf62b515454b5d9796b8320f9f3b0509e4a0a0328d390c9b7e93","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:16.457823Z","signature_b64":"4oR7dDpAzveM1+79iARcxbd6h6RDUNWFfucELgxlBzPpIBe0JBDktBgmU8IkJL7n6xareNZhKC8bx3NvgxoLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98e97e07dc52bf62b515454b5d9796b8320f9f3b0509e4a0a0328d390c9b7e93","last_reissued_at":"2026-05-18T01:20:16.457254Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:16.457254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.06342","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:20:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZhVJUFSa48Zz0U30hRBxLx/8Ncs9veFooFX/L/XSViWrJ/UmMeoXXstxpy900C9K15CrKmCZryU+a8IJNQdICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T09:36:40.784450Z"},"content_sha256":"4fb9925f4f23a45e67b861af9fb5533a81d67b43706733f9b9c4851648296a12","schema_version":"1.0","event_id":"sha256:4fb9925f4f23a45e67b861af9fb5533a81d67b43706733f9b9c4851648296a12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:TDUX4B64KK7WFNIVIVFV3F4WXA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Emilio Parisotto, Jimmy Lei Ba, Ruslan Salakhutdinov","submitted_at":"2015-11-19T20:17:27Z","abstract_excerpt":"The ability to act in multiple environments and transfer previous knowledge to new situations can be considered a critical aspect of any intelligent agent. Towards this goal, we define a novel method of multitask and transfer learning that enables an autonomous agent to learn how to behave in multiple tasks simultaneously, and then generalize its knowledge to new domains. This method, termed \"Actor-Mimic\", exploits the use of deep reinforcement learning and model compression techniques to train a single policy network that learns how to act in a set of distinct tasks by using the guidance of s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06342","kind":"arxiv","version":4},"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":"2026-05-18T01:20:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SLADNgpUcRPEgxIFddw6539OoU9sjtNXSsFV9P3HLH0X9z6jrzxmRRA5U5hKB8qCCRKRpdtDUgus0sJKDiXbDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T09:36:40.785125Z"},"content_sha256":"561ed71dead305f231809ce8fb247b63d42c5e1eb3f64f2d077bf8f333b0503f","schema_version":"1.0","event_id":"sha256:561ed71dead305f231809ce8fb247b63d42c5e1eb3f64f2d077bf8f333b0503f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TDUX4B64KK7WFNIVIVFV3F4WXA/bundle.json","state_url":"https://pith.science/pith/TDUX4B64KK7WFNIVIVFV3F4WXA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TDUX4B64KK7WFNIVIVFV3F4WXA/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":"2026-06-10T09:36:40Z","links":{"resolver":"https://pith.science/pith/TDUX4B64KK7WFNIVIVFV3F4WXA","bundle":"https://pith.science/pith/TDUX4B64KK7WFNIVIVFV3F4WXA/bundle.json","state":"https://pith.science/pith/TDUX4B64KK7WFNIVIVFV3F4WXA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TDUX4B64KK7WFNIVIVFV3F4WXA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:TDUX4B64KK7WFNIVIVFV3F4WXA","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":"b9b1fe5e573e578eda9c68655809be9ee45237ddbf63b211cee78bf6aea71a92","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T20:17:27Z","title_canon_sha256":"19f5006f94e78c5954ff9c36083c3a813836158a428f72f269e8e14cbbabb4f1"},"schema_version":"1.0","source":{"id":"1511.06342","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06342","created_at":"2026-05-18T01:20:16Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06342v4","created_at":"2026-05-18T01:20:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06342","created_at":"2026-05-18T01:20:16Z"},{"alias_kind":"pith_short_12","alias_value":"TDUX4B64KK7W","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"TDUX4B64KK7WFNIV","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"TDUX4B64","created_at":"2026-05-18T12:29:42Z"}],"graph_snapshots":[{"event_id":"sha256:561ed71dead305f231809ce8fb247b63d42c5e1eb3f64f2d077bf8f333b0503f","target":"graph","created_at":"2026-05-18T01:20:16Z","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":"The ability to act in multiple environments and transfer previous knowledge to new situations can be considered a critical aspect of any intelligent agent. Towards this goal, we define a novel method of multitask and transfer learning that enables an autonomous agent to learn how to behave in multiple tasks simultaneously, and then generalize its knowledge to new domains. This method, termed \"Actor-Mimic\", exploits the use of deep reinforcement learning and model compression techniques to train a single policy network that learns how to act in a set of distinct tasks by using the guidance of s","authors_text":"Emilio Parisotto, Jimmy Lei Ba, Ruslan Salakhutdinov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T20:17:27Z","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06342","kind":"arxiv","version":4},"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":"sha256:4fb9925f4f23a45e67b861af9fb5533a81d67b43706733f9b9c4851648296a12","target":"record","created_at":"2026-05-18T01:20:16Z","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":"b9b1fe5e573e578eda9c68655809be9ee45237ddbf63b211cee78bf6aea71a92","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T20:17:27Z","title_canon_sha256":"19f5006f94e78c5954ff9c36083c3a813836158a428f72f269e8e14cbbabb4f1"},"schema_version":"1.0","source":{"id":"1511.06342","kind":"arxiv","version":4}},"canonical_sha256":"98e97e07dc52bf62b515454b5d9796b8320f9f3b0509e4a0a0328d390c9b7e93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98e97e07dc52bf62b515454b5d9796b8320f9f3b0509e4a0a0328d390c9b7e93","first_computed_at":"2026-05-18T01:20:16.457254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:20:16.457254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4oR7dDpAzveM1+79iARcxbd6h6RDUNWFfucELgxlBzPpIBe0JBDktBgmU8IkJL7n6xareNZhKC8bx3NvgxoLCg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:20:16.457823Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.06342","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fb9925f4f23a45e67b861af9fb5533a81d67b43706733f9b9c4851648296a12","sha256:561ed71dead305f231809ce8fb247b63d42c5e1eb3f64f2d077bf8f333b0503f"],"state_sha256":"0e0f51f32d2d034943cf341b51e71c2cdbf1e97c42e05d959714ea61382f2a12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Opto+WOlzCbZTvFUKIghDPIXS4df6Xluj2AfFFXf5msddDDpsbF1nkGK/g4TlKO9VKJRYfwnze7LAbN6emSJDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T09:36:40.789533Z","bundle_sha256":"6a979015f46f4f9757670432397ee129b70b1f7812647db9e6c9ab8360dc3002"}}