{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SXF6V2ESHFJFOFVQKGZ7YXSJ5D","short_pith_number":"pith:SXF6V2ES","canonical_record":{"source":{"id":"1904.02435","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-04T09:52:18Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"06795c53445fa323763cb5917bf476c64a6885d82247beafe0d13e0dd262869e","abstract_canon_sha256":"4ea13fa73017f6f61175f8601f69559f03adb0598c58db50698a7a7911207cf3"},"schema_version":"1.0"},"canonical_sha256":"95cbeae89239525716b051b3fc5e49e8c609e79879d65dc3d5d208e801bf88e5","source":{"kind":"arxiv","id":"1904.02435","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.02435","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"1904.02435v2","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02435","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"SXF6V2ESHFJF","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SXF6V2ESHFJFOFVQ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SXF6V2ES","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SXF6V2ESHFJFOFVQKGZ7YXSJ5D","target":"record","payload":{"canonical_record":{"source":{"id":"1904.02435","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-04T09:52:18Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"06795c53445fa323763cb5917bf476c64a6885d82247beafe0d13e0dd262869e","abstract_canon_sha256":"4ea13fa73017f6f61175f8601f69559f03adb0598c58db50698a7a7911207cf3"},"schema_version":"1.0"},"canonical_sha256":"95cbeae89239525716b051b3fc5e49e8c609e79879d65dc3d5d208e801bf88e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:08.912075Z","signature_b64":"LO9ql2RcUMsLP6QTuIiAEiB2l13Ut3iGZUZZW8F/2Taelnto/zr7WsMZkwNW6ubyMNDrURm6QIIUQPH0vdPwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95cbeae89239525716b051b3fc5e49e8c609e79879d65dc3d5d208e801bf88e5","last_reissued_at":"2026-05-17T23:46:08.911496Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:08.911496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.02435","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":"2026-05-17T23:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QlnQdZRxnXKsQimfiRdfb8Onin2heCQ/YnZ0Ojm6JM9Wu9vSJur7A7nLXCBiOVrBSfm8E14AiXQ7LZr6JMwyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:10:01.451714Z"},"content_sha256":"588ff0fda9ae589eaee5cebb43d1f5a31839e08210643c932570cb04e3d04d6f","schema_version":"1.0","event_id":"sha256:588ff0fda9ae589eaee5cebb43d1f5a31839e08210643c932570cb04e3d04d6f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SXF6V2ESHFJFOFVQKGZ7YXSJ5D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Adapting Goals Allow Transfer of Predictive Models to New Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jim Torresen, Kai Olav Ellefsen","submitted_at":"2019-04-04T09:52:18Z","abstract_excerpt":"A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the challenge of learning accurate models of an environment. If such a model is inaccurate, the agent's plans and actions will likely be sub-optimal, and likely lead to the wrong outcomes. Recent progress in model-based reinforcement learning has improved the ability for agents to learn and use predictive models. In this paper, we extend a recent deep learning arch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02435","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":"2026-05-17T23:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tWtC6ezftWX2ss2D//RSHjQzfFIMal1YI5GjRZLLLoMnJ6xvxK/lRGltxq1avF+PT6934Y3IImuxY1MUxPuSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:10:01.452068Z"},"content_sha256":"01ec40ab0f99c0cd3e6b352fb7a69da33ab7877502ceac80497a8774a2d45ed7","schema_version":"1.0","event_id":"sha256:01ec40ab0f99c0cd3e6b352fb7a69da33ab7877502ceac80497a8774a2d45ed7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/bundle.json","state_url":"https://pith.science/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/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":"2026-06-02T11:10:01Z","links":{"resolver":"https://pith.science/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D","bundle":"https://pith.science/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/bundle.json","state":"https://pith.science/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SXF6V2ESHFJFOFVQKGZ7YXSJ5D","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":"4ea13fa73017f6f61175f8601f69559f03adb0598c58db50698a7a7911207cf3","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-04T09:52:18Z","title_canon_sha256":"06795c53445fa323763cb5917bf476c64a6885d82247beafe0d13e0dd262869e"},"schema_version":"1.0","source":{"id":"1904.02435","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.02435","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"1904.02435v2","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02435","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"SXF6V2ESHFJF","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SXF6V2ESHFJFOFVQ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SXF6V2ES","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:01ec40ab0f99c0cd3e6b352fb7a69da33ab7877502ceac80497a8774a2d45ed7","target":"graph","created_at":"2026-05-17T23:46:08Z","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":"A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the challenge of learning accurate models of an environment. If such a model is inaccurate, the agent's plans and actions will likely be sub-optimal, and likely lead to the wrong outcomes. Recent progress in model-based reinforcement learning has improved the ability for agents to learn and use predictive models. In this paper, we extend a recent deep learning arch","authors_text":"Jim Torresen, Kai Olav Ellefsen","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-04T09:52:18Z","title":"Self-Adapting Goals Allow Transfer of Predictive Models to New Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02435","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":"sha256:588ff0fda9ae589eaee5cebb43d1f5a31839e08210643c932570cb04e3d04d6f","target":"record","created_at":"2026-05-17T23:46:08Z","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":"4ea13fa73017f6f61175f8601f69559f03adb0598c58db50698a7a7911207cf3","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-04T09:52:18Z","title_canon_sha256":"06795c53445fa323763cb5917bf476c64a6885d82247beafe0d13e0dd262869e"},"schema_version":"1.0","source":{"id":"1904.02435","kind":"arxiv","version":2}},"canonical_sha256":"95cbeae89239525716b051b3fc5e49e8c609e79879d65dc3d5d208e801bf88e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95cbeae89239525716b051b3fc5e49e8c609e79879d65dc3d5d208e801bf88e5","first_computed_at":"2026-05-17T23:46:08.911496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:08.911496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LO9ql2RcUMsLP6QTuIiAEiB2l13Ut3iGZUZZW8F/2Taelnto/zr7WsMZkwNW6ubyMNDrURm6QIIUQPH0vdPwBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:08.912075Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.02435","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:588ff0fda9ae589eaee5cebb43d1f5a31839e08210643c932570cb04e3d04d6f","sha256:01ec40ab0f99c0cd3e6b352fb7a69da33ab7877502ceac80497a8774a2d45ed7"],"state_sha256":"c36cf1acd56a85134dc9e83b46f4f66cf399655c3287936ea4d57ee84035dad4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rgy6WVkguZLEmmnCR3QeLPJvFBxF5XnahtXrwyPbBBEvrgsxsJtQWSNPBGf+QoRS/tvT8cZTDjVpZ1Nq3HTuBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T11:10:01.454107Z","bundle_sha256":"65db8ab70407b236a8e214cfb5c44734bf841cf5713fabf807eddd498d440341"}}