{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:INVXC2YHEGJMGFRY4URUSFCDLW","short_pith_number":"pith:INVXC2YH","canonical_record":{"source":{"id":"1806.01265","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-01T21:54:18Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ec2ccf810a0e0eaddee84cddb8516eff69457ef313127ebd5bdeddb82c373208","abstract_canon_sha256":"1cb5fce260fa176a1a2fd185d4e380ab417ffecc1785e804942306ca57140639"},"schema_version":"1.0"},"canonical_sha256":"436b716b072192c31638e5234914435dbe93ab7f4ecf9046126573c8e2bb5f39","source":{"kind":"arxiv","id":"1806.01265","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.01265","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"1806.01265v2","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01265","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"INVXC2YHEGJM","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"INVXC2YHEGJMGFRY","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"INVXC2YH","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:INVXC2YHEGJMGFRY4URUSFCDLW","target":"record","payload":{"canonical_record":{"source":{"id":"1806.01265","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-01T21:54:18Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ec2ccf810a0e0eaddee84cddb8516eff69457ef313127ebd5bdeddb82c373208","abstract_canon_sha256":"1cb5fce260fa176a1a2fd185d4e380ab417ffecc1785e804942306ca57140639"},"schema_version":"1.0"},"canonical_sha256":"436b716b072192c31638e5234914435dbe93ab7f4ecf9046126573c8e2bb5f39","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:17.256668Z","signature_b64":"ow0jThKltcbwAKrIozh+sYhK1i7M+afxhHgRWw81tOXeEXgd/aLd9LICxGNEoQd3HYRxTKtSB2ynhNLBQ04vAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"436b716b072192c31638e5234914435dbe93ab7f4ecf9046126573c8e2bb5f39","last_reissued_at":"2026-05-18T00:11:17.255892Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:17.255892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.01265","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":"2026-05-18T00:11:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TK63TQi8nEhaBH0FijMoKuRpQ1REbCeT7TaeAzbvIU7sKEc8iWVuexKJfGb5CvEnvST2rK/SHOcjE9n/LR/FBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T13:23:02.650500Z"},"content_sha256":"72ed8e4bee9ceeeee15eae51b8a6f55b20a2cd38689be98e83a06d7f917b2808","schema_version":"1.0","event_id":"sha256:72ed8e4bee9ceeeee15eae51b8a6f55b20a2cd38689be98e83a06d7f917b2808"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:INVXC2YHEGJMGFRY4URUSFCDLW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Equivalence Between Wasserstein and Value-Aware Loss for Model-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dipendra Misra, Evan Cater, Kavosh Asadi, Michael L. Littman","submitted_at":"2018-06-01T21:54:18Z","abstract_excerpt":"Learning a generative model is a key component of model-based reinforcement learning. Though learning a good model in the tabular setting is a simple task, learning a useful model in the approximate setting is challenging. In this context, an important question is the loss function used for model learning as varying the loss function can have a remarkable impact on effectiveness of planning. Recently Farahmand et al. (2017) proposed a value-aware model learning (VAML) objective that captures the structure of value function during model learning. Using tools from Asadi et al. (2018), we show th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01265","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":"2026-05-18T00:11:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HU759z+e9FDQkBjUQBM8QeuRa7oVKC0QZ5eoIH9uB1bYeuivP6615AKDGDETai1nv8Pzz6IFAmojWNa37XAsAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T13:23:02.651170Z"},"content_sha256":"1f2865362cddd9f4b7084bf74e37f21d88b15b33d054ec46dade03e5b7cdaf09","schema_version":"1.0","event_id":"sha256:1f2865362cddd9f4b7084bf74e37f21d88b15b33d054ec46dade03e5b7cdaf09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/INVXC2YHEGJMGFRY4URUSFCDLW/bundle.json","state_url":"https://pith.science/pith/INVXC2YHEGJMGFRY4URUSFCDLW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/INVXC2YHEGJMGFRY4URUSFCDLW/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":"2026-06-10T13:23:02Z","links":{"resolver":"https://pith.science/pith/INVXC2YHEGJMGFRY4URUSFCDLW","bundle":"https://pith.science/pith/INVXC2YHEGJMGFRY4URUSFCDLW/bundle.json","state":"https://pith.science/pith/INVXC2YHEGJMGFRY4URUSFCDLW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/INVXC2YHEGJMGFRY4URUSFCDLW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:INVXC2YHEGJMGFRY4URUSFCDLW","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":"1cb5fce260fa176a1a2fd185d4e380ab417ffecc1785e804942306ca57140639","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-01T21:54:18Z","title_canon_sha256":"ec2ccf810a0e0eaddee84cddb8516eff69457ef313127ebd5bdeddb82c373208"},"schema_version":"1.0","source":{"id":"1806.01265","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.01265","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"1806.01265v2","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01265","created_at":"2026-05-18T00:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"INVXC2YHEGJM","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"INVXC2YHEGJMGFRY","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"INVXC2YH","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:1f2865362cddd9f4b7084bf74e37f21d88b15b33d054ec46dade03e5b7cdaf09","target":"graph","created_at":"2026-05-18T00:11:17Z","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":"Learning a generative model is a key component of model-based reinforcement learning. Though learning a good model in the tabular setting is a simple task, learning a useful model in the approximate setting is challenging. In this context, an important question is the loss function used for model learning as varying the loss function can have a remarkable impact on effectiveness of planning. Recently Farahmand et al. (2017) proposed a value-aware model learning (VAML) objective that captures the structure of value function during model learning. Using tools from Asadi et al. (2018), we show th","authors_text":"Dipendra Misra, Evan Cater, Kavosh Asadi, Michael L. Littman","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-01T21:54:18Z","title":"Equivalence Between Wasserstein and Value-Aware Loss for Model-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01265","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":"sha256:72ed8e4bee9ceeeee15eae51b8a6f55b20a2cd38689be98e83a06d7f917b2808","target":"record","created_at":"2026-05-18T00:11:17Z","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":"1cb5fce260fa176a1a2fd185d4e380ab417ffecc1785e804942306ca57140639","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-01T21:54:18Z","title_canon_sha256":"ec2ccf810a0e0eaddee84cddb8516eff69457ef313127ebd5bdeddb82c373208"},"schema_version":"1.0","source":{"id":"1806.01265","kind":"arxiv","version":2}},"canonical_sha256":"436b716b072192c31638e5234914435dbe93ab7f4ecf9046126573c8e2bb5f39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"436b716b072192c31638e5234914435dbe93ab7f4ecf9046126573c8e2bb5f39","first_computed_at":"2026-05-18T00:11:17.255892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:17.255892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ow0jThKltcbwAKrIozh+sYhK1i7M+afxhHgRWw81tOXeEXgd/aLd9LICxGNEoQd3HYRxTKtSB2ynhNLBQ04vAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:17.256668Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.01265","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72ed8e4bee9ceeeee15eae51b8a6f55b20a2cd38689be98e83a06d7f917b2808","sha256:1f2865362cddd9f4b7084bf74e37f21d88b15b33d054ec46dade03e5b7cdaf09"],"state_sha256":"b51f9a1b5b47721adf64087ca9e9b1919dac9f064b42549c4a763888184d665e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rVBBe63rLxHzyQAA5xE3BhZ/7B7YJxRCg7YSKtS6QEAQNhhUX8odsB/PrTPSw6rob2XqoKcALhrRplnwAAY+CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T13:23:02.655626Z","bundle_sha256":"de002534899164fdb414c90f0e2967f256acfe27c378daad2e978dc88ac23ad1"}}