{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:RQJMWSYCLWHHAQHKRJX2CP2GFJ","short_pith_number":"pith:RQJMWSYC","canonical_record":{"source":{"id":"1206.4655","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-18T15:25:58Z","cross_cats_sorted":[],"title_canon_sha256":"85f466050f4f47f8abf3fc40a77c29cf7342725e705372641019a98601f39c03","abstract_canon_sha256":"8220abcc0c45bff5f53005ddf73fa844eace3297787044e857e058861c15f5d6"},"schema_version":"1.0"},"canonical_sha256":"8c12cb4b025d8e7040ea8a6fa13f462a47727ad4c5e84acc85f88caed763af90","source":{"kind":"arxiv","id":"1206.4655","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.4655","created_at":"2026-05-18T03:53:04Z"},{"alias_kind":"arxiv_version","alias_value":"1206.4655v1","created_at":"2026-05-18T03:53:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.4655","created_at":"2026-05-18T03:53:04Z"},{"alias_kind":"pith_short_12","alias_value":"RQJMWSYCLWHH","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"RQJMWSYCLWHHAQHK","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"RQJMWSYC","created_at":"2026-05-18T12:27:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:RQJMWSYCLWHHAQHKRJX2CP2GFJ","target":"record","payload":{"canonical_record":{"source":{"id":"1206.4655","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-18T15:25:58Z","cross_cats_sorted":[],"title_canon_sha256":"85f466050f4f47f8abf3fc40a77c29cf7342725e705372641019a98601f39c03","abstract_canon_sha256":"8220abcc0c45bff5f53005ddf73fa844eace3297787044e857e058861c15f5d6"},"schema_version":"1.0"},"canonical_sha256":"8c12cb4b025d8e7040ea8a6fa13f462a47727ad4c5e84acc85f88caed763af90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:53:04.253861Z","signature_b64":"+q80Iv818kIKNJ1elCZlBJki+ex0u4trxFx+Oyzat9xfFnjhyVQnTrsyQsz+2YcUBTY/jwkZ3EaUYuUyf+VkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c12cb4b025d8e7040ea8a6fa13f462a47727ad4c5e84acc85f88caed763af90","last_reissued_at":"2026-05-18T03:53:04.253094Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:53:04.253094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1206.4655","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":"2026-05-18T03:53:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kdBcQWYf1VprFjm6q0k9S5T2VZYaN4pJs8bHu1sXaLOv3KcjU06bGg+BBRrMau3UoFBcz8uBKPozTpzXv0I7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T15:51:10.443184Z"},"content_sha256":"e788950d83d354d68d1ce7da7d4596d9114c5cbb00d84a12a12b8127049129b3","schema_version":"1.0","event_id":"sha256:e788950d83d354d68d1ce7da7d4596d9114c5cbb00d84a12a12b8127049129b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:RQJMWSYCLWHHAQHKRJX2CP2GFJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modelling transition dynamics in MDPs with RKHS embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arthur Gretton (MPI for Intelligent Systems), Guy Lever (University College London), Luca Baldassarre (University College London), Massi Pontil (University College London), Steffen Grunewalder (University College London)","submitted_at":"2012-06-18T15:25:58Z","abstract_excerpt":"We propose a new, nonparametric approach to learning and representing transition dynamics in Markov decision processes (MDPs), which can be combined easily with dynamic programming methods for policy optimisation and value estimation. This approach makes use of a recently developed representation of conditional distributions as \\emph{embeddings} in a reproducing kernel Hilbert space (RKHS). Such representations bypass the need for estimating transition probabilities or densities, and apply to any domain on which kernels can be defined. This avoids the need to calculate intractable integrals, s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.4655","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":"2026-05-18T03:53:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nEAjjqPJxUI6WEsS0xUJl8P1HGm6tiavJhpnIAYYYTpe6x3ajo/bFW2EZzcj15feMGK2LzBdZ7yWrQos7ypIBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T15:51:10.443554Z"},"content_sha256":"7f26050ad678ebf120fd6ae159c5c013c82ac1c11c9de30089ad459979c4a6c7","schema_version":"1.0","event_id":"sha256:7f26050ad678ebf120fd6ae159c5c013c82ac1c11c9de30089ad459979c4a6c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RQJMWSYCLWHHAQHKRJX2CP2GFJ/bundle.json","state_url":"https://pith.science/pith/RQJMWSYCLWHHAQHKRJX2CP2GFJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RQJMWSYCLWHHAQHKRJX2CP2GFJ/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":"2026-07-04T15:51:10Z","links":{"resolver":"https://pith.science/pith/RQJMWSYCLWHHAQHKRJX2CP2GFJ","bundle":"https://pith.science/pith/RQJMWSYCLWHHAQHKRJX2CP2GFJ/bundle.json","state":"https://pith.science/pith/RQJMWSYCLWHHAQHKRJX2CP2GFJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RQJMWSYCLWHHAQHKRJX2CP2GFJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:RQJMWSYCLWHHAQHKRJX2CP2GFJ","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":"8220abcc0c45bff5f53005ddf73fa844eace3297787044e857e058861c15f5d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-18T15:25:58Z","title_canon_sha256":"85f466050f4f47f8abf3fc40a77c29cf7342725e705372641019a98601f39c03"},"schema_version":"1.0","source":{"id":"1206.4655","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.4655","created_at":"2026-05-18T03:53:04Z"},{"alias_kind":"arxiv_version","alias_value":"1206.4655v1","created_at":"2026-05-18T03:53:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.4655","created_at":"2026-05-18T03:53:04Z"},{"alias_kind":"pith_short_12","alias_value":"RQJMWSYCLWHH","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"RQJMWSYCLWHHAQHK","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"RQJMWSYC","created_at":"2026-05-18T12:27:20Z"}],"graph_snapshots":[{"event_id":"sha256:7f26050ad678ebf120fd6ae159c5c013c82ac1c11c9de30089ad459979c4a6c7","target":"graph","created_at":"2026-05-18T03:53:04Z","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":"We propose a new, nonparametric approach to learning and representing transition dynamics in Markov decision processes (MDPs), which can be combined easily with dynamic programming methods for policy optimisation and value estimation. This approach makes use of a recently developed representation of conditional distributions as \\emph{embeddings} in a reproducing kernel Hilbert space (RKHS). Such representations bypass the need for estimating transition probabilities or densities, and apply to any domain on which kernels can be defined. This avoids the need to calculate intractable integrals, s","authors_text":"Arthur Gretton (MPI for Intelligent Systems), Guy Lever (University College London), Luca Baldassarre (University College London), Massi Pontil (University College London), Steffen Grunewalder (University College London)","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-18T15:25:58Z","title":"Modelling transition dynamics in MDPs with RKHS embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.4655","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:e788950d83d354d68d1ce7da7d4596d9114c5cbb00d84a12a12b8127049129b3","target":"record","created_at":"2026-05-18T03:53:04Z","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":"8220abcc0c45bff5f53005ddf73fa844eace3297787044e857e058861c15f5d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-18T15:25:58Z","title_canon_sha256":"85f466050f4f47f8abf3fc40a77c29cf7342725e705372641019a98601f39c03"},"schema_version":"1.0","source":{"id":"1206.4655","kind":"arxiv","version":1}},"canonical_sha256":"8c12cb4b025d8e7040ea8a6fa13f462a47727ad4c5e84acc85f88caed763af90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c12cb4b025d8e7040ea8a6fa13f462a47727ad4c5e84acc85f88caed763af90","first_computed_at":"2026-05-18T03:53:04.253094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:53:04.253094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+q80Iv818kIKNJ1elCZlBJki+ex0u4trxFx+Oyzat9xfFnjhyVQnTrsyQsz+2YcUBTY/jwkZ3EaUYuUyf+VkDA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:53:04.253861Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.4655","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e788950d83d354d68d1ce7da7d4596d9114c5cbb00d84a12a12b8127049129b3","sha256:7f26050ad678ebf120fd6ae159c5c013c82ac1c11c9de30089ad459979c4a6c7"],"state_sha256":"56d781368e9e203e05b537fc20beb551ca8ad8f6711a1094a66a0275ac7cd456"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mJKquGl7JUUSKwmNhqcEBX6aS3eTGF2gASdWZHkF6gzSx6jkU0Lr80tMpJe3q64TRbKF/TgSLvTnP7HhSgY5Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T15:51:10.445697Z","bundle_sha256":"35feeb18b561c44581e597eec1cf745a83de927aa32456de5d6d77b02808f333"}}