{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:ZPJTRYDOGBTFXFSMQX5CDU36DO","short_pith_number":"pith:ZPJTRYDO","canonical_record":{"source":{"id":"1106.0681","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-03T14:57:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"914366787b3cda9540a929cccfcc45bca28fa39e4ead3cffd2e0d269b39af394","abstract_canon_sha256":"e48e87034bb4ef48007bc2a6ee99c68f48835376797bdae9ff46951ce881ea56"},"schema_version":"1.0"},"canonical_sha256":"cbd338e06e30665b964c85fa21d37e1ba97b4348e44834ac4c79d928c2706e9b","source":{"kind":"arxiv","id":"1106.0681","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1106.0681","created_at":"2026-05-18T04:20:39Z"},{"alias_kind":"arxiv_version","alias_value":"1106.0681v1","created_at":"2026-05-18T04:20:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1106.0681","created_at":"2026-05-18T04:20:39Z"},{"alias_kind":"pith_short_12","alias_value":"ZPJTRYDOGBTF","created_at":"2026-05-18T12:26:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZPJTRYDOGBTFXFSM","created_at":"2026-05-18T12:26:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZPJTRYDO","created_at":"2026-05-18T12:26:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:ZPJTRYDOGBTFXFSMQX5CDU36DO","target":"record","payload":{"canonical_record":{"source":{"id":"1106.0681","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-03T14:57:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"914366787b3cda9540a929cccfcc45bca28fa39e4ead3cffd2e0d269b39af394","abstract_canon_sha256":"e48e87034bb4ef48007bc2a6ee99c68f48835376797bdae9ff46951ce881ea56"},"schema_version":"1.0"},"canonical_sha256":"cbd338e06e30665b964c85fa21d37e1ba97b4348e44834ac4c79d928c2706e9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:20:39.715970Z","signature_b64":"Kq/LVKm3grNPum3E5Oi4sAunMv9ravQYQVpbAZ++yl59cy6eQYvBA2g97SxDLKwjl0ALcbtkDDpcMB35gybZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbd338e06e30665b964c85fa21d37e1ba97b4348e44834ac4c79d928c2706e9b","last_reissued_at":"2026-05-18T04:20:39.715113Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:20:39.715113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1106.0681","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":"2026-05-18T04:20:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oVdmFG2iIYdJQl5zVwhf+svd67XgUtlyHgm+BS5cTKTZn9YfiH0ilvWs6vKT3gMs4uSG9l0H0hFUlx5rfUB1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T21:43:31.177801Z"},"content_sha256":"efb15c5d17660d81b8792a98dbe31a8f7c0f1e2813089d686c5e1f2ef03cc66e","schema_version":"1.0","event_id":"sha256:efb15c5d17660d81b8792a98dbe31a8f7c0f1e2813089d686c5e1f2ef03cc66e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:ZPJTRYDOGBTFXFSMQX5CDU36DO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating Reinforcement Learning through Implicit Imitation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"B. Price, C. Boutilier","submitted_at":"2011-06-03T14:57:02Z","abstract_excerpt":"Imitation can be viewed as a means of enhancing learning in multiagent environments.  It augments an agent's ability to learn useful behaviors by making intelligent use of the knowledge implicit in behaviors demonstrated by cooperative teachers or other more experienced agents.  We propose and study a formal model of implicit imitation that can accelerate reinforcement learning dramatically in certain cases.  Roughly, by observing a mentor, a reinforcement-learning agent can extract information about its own capabilities in, and the relative value of, unvisited parts of the state space.  We st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1106.0681","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":"2026-05-18T04:20:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xYLkxWJxOW5PAi67B61fj0kRSDLeo5hUr13dDsLwgNG+iiHLv52iNE56diDc8yCx+N4/xSfgH7KWRLcEOBSTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T21:43:31.178173Z"},"content_sha256":"6d7af807c416ba34fafbe2fb7cfd4fa2f720914bdb2949867ecbd65c3e6243e8","schema_version":"1.0","event_id":"sha256:6d7af807c416ba34fafbe2fb7cfd4fa2f720914bdb2949867ecbd65c3e6243e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZPJTRYDOGBTFXFSMQX5CDU36DO/bundle.json","state_url":"https://pith.science/pith/ZPJTRYDOGBTFXFSMQX5CDU36DO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZPJTRYDOGBTFXFSMQX5CDU36DO/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":"2026-06-10T21:43:31Z","links":{"resolver":"https://pith.science/pith/ZPJTRYDOGBTFXFSMQX5CDU36DO","bundle":"https://pith.science/pith/ZPJTRYDOGBTFXFSMQX5CDU36DO/bundle.json","state":"https://pith.science/pith/ZPJTRYDOGBTFXFSMQX5CDU36DO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZPJTRYDOGBTFXFSMQX5CDU36DO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:ZPJTRYDOGBTFXFSMQX5CDU36DO","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":"e48e87034bb4ef48007bc2a6ee99c68f48835376797bdae9ff46951ce881ea56","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-03T14:57:02Z","title_canon_sha256":"914366787b3cda9540a929cccfcc45bca28fa39e4ead3cffd2e0d269b39af394"},"schema_version":"1.0","source":{"id":"1106.0681","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1106.0681","created_at":"2026-05-18T04:20:39Z"},{"alias_kind":"arxiv_version","alias_value":"1106.0681v1","created_at":"2026-05-18T04:20:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1106.0681","created_at":"2026-05-18T04:20:39Z"},{"alias_kind":"pith_short_12","alias_value":"ZPJTRYDOGBTF","created_at":"2026-05-18T12:26:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZPJTRYDOGBTFXFSM","created_at":"2026-05-18T12:26:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZPJTRYDO","created_at":"2026-05-18T12:26:50Z"}],"graph_snapshots":[{"event_id":"sha256:6d7af807c416ba34fafbe2fb7cfd4fa2f720914bdb2949867ecbd65c3e6243e8","target":"graph","created_at":"2026-05-18T04:20:39Z","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":"Imitation can be viewed as a means of enhancing learning in multiagent environments.  It augments an agent's ability to learn useful behaviors by making intelligent use of the knowledge implicit in behaviors demonstrated by cooperative teachers or other more experienced agents.  We propose and study a formal model of implicit imitation that can accelerate reinforcement learning dramatically in certain cases.  Roughly, by observing a mentor, a reinforcement-learning agent can extract information about its own capabilities in, and the relative value of, unvisited parts of the state space.  We st","authors_text":"B. Price, C. Boutilier","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-03T14:57:02Z","title":"Accelerating Reinforcement Learning through Implicit Imitation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1106.0681","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:efb15c5d17660d81b8792a98dbe31a8f7c0f1e2813089d686c5e1f2ef03cc66e","target":"record","created_at":"2026-05-18T04:20:39Z","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":"e48e87034bb4ef48007bc2a6ee99c68f48835376797bdae9ff46951ce881ea56","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-03T14:57:02Z","title_canon_sha256":"914366787b3cda9540a929cccfcc45bca28fa39e4ead3cffd2e0d269b39af394"},"schema_version":"1.0","source":{"id":"1106.0681","kind":"arxiv","version":1}},"canonical_sha256":"cbd338e06e30665b964c85fa21d37e1ba97b4348e44834ac4c79d928c2706e9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbd338e06e30665b964c85fa21d37e1ba97b4348e44834ac4c79d928c2706e9b","first_computed_at":"2026-05-18T04:20:39.715113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:20:39.715113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kq/LVKm3grNPum3E5Oi4sAunMv9ravQYQVpbAZ++yl59cy6eQYvBA2g97SxDLKwjl0ALcbtkDDpcMB35gybZCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T04:20:39.715970Z","signed_message":"canonical_sha256_bytes"},"source_id":"1106.0681","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efb15c5d17660d81b8792a98dbe31a8f7c0f1e2813089d686c5e1f2ef03cc66e","sha256:6d7af807c416ba34fafbe2fb7cfd4fa2f720914bdb2949867ecbd65c3e6243e8"],"state_sha256":"ed79a2c57561be4601fe41c0e2aa886b3e6fbfb90453e66714e3a17ea8c6578a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y2/vjna5zIRg6nI+iHaGzhiEYO8JhvEne2hSucHjuGB3TGLaLLlcoebc/WTxqsfRpFF7jJpAttwfa+Mmo66fCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T21:43:31.180284Z","bundle_sha256":"bd02e3d9444e41c2967f25880fdd91197d2049fd649110c513ead7cee42ac64c"}}