{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:H7WA4VXWYI5UL5PUKZIEB277U3","short_pith_number":"pith:H7WA4VXW","canonical_record":{"source":{"id":"1809.00770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-04T02:13:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"80301fd11b695bb5cad1767899299089a01cbdea169a0f2bb934720da40a944e","abstract_canon_sha256":"6d06e89fee108cbb46066ceeef783b1ae26bd809c409f5d88f9a0fe4fbe7080d"},"schema_version":"1.0"},"canonical_sha256":"3fec0e56f6c23b45f5f4565040ebffa6cd89c62ceee3a1c441052d0910e56e20","source":{"kind":"arxiv","id":"1809.00770","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.00770","created_at":"2026-05-18T00:06:32Z"},{"alias_kind":"arxiv_version","alias_value":"1809.00770v1","created_at":"2026-05-18T00:06:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.00770","created_at":"2026-05-18T00:06:32Z"},{"alias_kind":"pith_short_12","alias_value":"H7WA4VXWYI5U","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"H7WA4VXWYI5UL5PU","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"H7WA4VXW","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:H7WA4VXWYI5UL5PUKZIEB277U3","target":"record","payload":{"canonical_record":{"source":{"id":"1809.00770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-04T02:13:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"80301fd11b695bb5cad1767899299089a01cbdea169a0f2bb934720da40a944e","abstract_canon_sha256":"6d06e89fee108cbb46066ceeef783b1ae26bd809c409f5d88f9a0fe4fbe7080d"},"schema_version":"1.0"},"canonical_sha256":"3fec0e56f6c23b45f5f4565040ebffa6cd89c62ceee3a1c441052d0910e56e20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:32.545285Z","signature_b64":"2x6DMV8miSZDzq30CR/XtFe1RwCYCQjLOgj7GXv0OBYWcI9j1mjSDuH9d1V7Z88fVWq5fEyEHYf6maho2J1uDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fec0e56f6c23b45f5f4565040ebffa6cd89c62ceee3a1c441052d0910e56e20","last_reissued_at":"2026-05-18T00:06:32.544824Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:32.544824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.00770","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":"2026-05-18T00:06:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pAchg/RGiuSG+n5L80gwx8jtBDgDggYnFPURAKrH/VhKkt439nwCQ36R80AxSFBS3Xh475JSmqCCxqO4cIQnCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:53:32.695557Z"},"content_sha256":"b50cf30863b6988cde101d98c54e367b72b5d904a456064db960432559b67e8b","schema_version":"1.0","event_id":"sha256:b50cf30863b6988cde101d98c54e367b72b5d904a456064db960432559b67e8b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:H7WA4VXWYI5UL5PUKZIEB277U3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transferring Deep Reinforcement Learning with Adversarial Objective and Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bing-Yu Chen, I-Chao Shen, Shu-Hsuan Hsu","submitted_at":"2018-09-04T02:13:37Z","abstract_excerpt":"In the past few years, deep reinforcement learning has been proven to solve problems which have complex states like video games or board games. The next step of intelligent agents would be able to generalize between tasks, and using prior experience to pick up new skills more quickly. However, most reinforcement learning algorithms for now are often suffering from catastrophic forgetting even when facing a very similar target task. Our approach enables the agents to generalize knowledge from a single source task, and boost the learning progress with a semisupervised learning method when facing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.00770","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":"2026-05-18T00:06:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xzcr5GDkqnig/gL/SKPYbz9kb9Op45OLt/28cJLz7GOtS4AHOVQ8bvE0orZnr2pLeNEqDaFloghZjE9JqZ9ZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:53:32.695925Z"},"content_sha256":"3bee56d93b3f2456d82f8875141beef02fd0e706db033756182ab4573ec88900","schema_version":"1.0","event_id":"sha256:3bee56d93b3f2456d82f8875141beef02fd0e706db033756182ab4573ec88900"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H7WA4VXWYI5UL5PUKZIEB277U3/bundle.json","state_url":"https://pith.science/pith/H7WA4VXWYI5UL5PUKZIEB277U3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H7WA4VXWYI5UL5PUKZIEB277U3/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":"2026-05-31T19:53:32Z","links":{"resolver":"https://pith.science/pith/H7WA4VXWYI5UL5PUKZIEB277U3","bundle":"https://pith.science/pith/H7WA4VXWYI5UL5PUKZIEB277U3/bundle.json","state":"https://pith.science/pith/H7WA4VXWYI5UL5PUKZIEB277U3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H7WA4VXWYI5UL5PUKZIEB277U3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:H7WA4VXWYI5UL5PUKZIEB277U3","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":"6d06e89fee108cbb46066ceeef783b1ae26bd809c409f5d88f9a0fe4fbe7080d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-04T02:13:37Z","title_canon_sha256":"80301fd11b695bb5cad1767899299089a01cbdea169a0f2bb934720da40a944e"},"schema_version":"1.0","source":{"id":"1809.00770","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.00770","created_at":"2026-05-18T00:06:32Z"},{"alias_kind":"arxiv_version","alias_value":"1809.00770v1","created_at":"2026-05-18T00:06:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.00770","created_at":"2026-05-18T00:06:32Z"},{"alias_kind":"pith_short_12","alias_value":"H7WA4VXWYI5U","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"H7WA4VXWYI5UL5PU","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"H7WA4VXW","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:3bee56d93b3f2456d82f8875141beef02fd0e706db033756182ab4573ec88900","target":"graph","created_at":"2026-05-18T00:06:32Z","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":"In the past few years, deep reinforcement learning has been proven to solve problems which have complex states like video games or board games. The next step of intelligent agents would be able to generalize between tasks, and using prior experience to pick up new skills more quickly. However, most reinforcement learning algorithms for now are often suffering from catastrophic forgetting even when facing a very similar target task. Our approach enables the agents to generalize knowledge from a single source task, and boost the learning progress with a semisupervised learning method when facing","authors_text":"Bing-Yu Chen, I-Chao Shen, Shu-Hsuan Hsu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-04T02:13:37Z","title":"Transferring Deep Reinforcement Learning with Adversarial Objective and Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.00770","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:b50cf30863b6988cde101d98c54e367b72b5d904a456064db960432559b67e8b","target":"record","created_at":"2026-05-18T00:06:32Z","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":"6d06e89fee108cbb46066ceeef783b1ae26bd809c409f5d88f9a0fe4fbe7080d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-04T02:13:37Z","title_canon_sha256":"80301fd11b695bb5cad1767899299089a01cbdea169a0f2bb934720da40a944e"},"schema_version":"1.0","source":{"id":"1809.00770","kind":"arxiv","version":1}},"canonical_sha256":"3fec0e56f6c23b45f5f4565040ebffa6cd89c62ceee3a1c441052d0910e56e20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fec0e56f6c23b45f5f4565040ebffa6cd89c62ceee3a1c441052d0910e56e20","first_computed_at":"2026-05-18T00:06:32.544824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:32.544824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2x6DMV8miSZDzq30CR/XtFe1RwCYCQjLOgj7GXv0OBYWcI9j1mjSDuH9d1V7Z88fVWq5fEyEHYf6maho2J1uDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:32.545285Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.00770","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b50cf30863b6988cde101d98c54e367b72b5d904a456064db960432559b67e8b","sha256:3bee56d93b3f2456d82f8875141beef02fd0e706db033756182ab4573ec88900"],"state_sha256":"ac294b21c000a1757d8a046a91e6b943b8fb861e9cb1fd23cfe2dbe3064dcb65"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KaNK+7ta42HN8DNxY0TySB5+SZrjL0P/3axRdOdIsGUZzIFm0eyjV+d6HddqTedLb5xLikqWzY/R5lsmfz/+Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T19:53:32.699548Z","bundle_sha256":"bd4c55642c1d0a965c676948635ff4c37abe28bb479107185ebed35a7f42255a"}}