{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WM5PTMFP4YXFJQ2QQPTGZ4JGVW","short_pith_number":"pith:WM5PTMFP","canonical_record":{"source":{"id":"1703.06692","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-20T11:44:00Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"b7395eb7401e4fc9aaa52cd6169f981f07241ba4741b5660b8c78d48682e800e","abstract_canon_sha256":"6083d708094c711d2d94cf17b8da6a05da4543caeb66742cedc645976f6e7fa2"},"schema_version":"1.0"},"canonical_sha256":"b33af9b0afe62e54c35083e66cf126adbe1c2b493a08f9d2a18f3372501d1500","source":{"kind":"arxiv","id":"1703.06692","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06692","created_at":"2026-05-18T00:31:28Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06692v3","created_at":"2026-05-18T00:31:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06692","created_at":"2026-05-18T00:31:28Z"},{"alias_kind":"pith_short_12","alias_value":"WM5PTMFP4YXF","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WM5PTMFP4YXFJQ2Q","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WM5PTMFP","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WM5PTMFP4YXFJQ2QQPTGZ4JGVW","target":"record","payload":{"canonical_record":{"source":{"id":"1703.06692","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-20T11:44:00Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"b7395eb7401e4fc9aaa52cd6169f981f07241ba4741b5660b8c78d48682e800e","abstract_canon_sha256":"6083d708094c711d2d94cf17b8da6a05da4543caeb66742cedc645976f6e7fa2"},"schema_version":"1.0"},"canonical_sha256":"b33af9b0afe62e54c35083e66cf126adbe1c2b493a08f9d2a18f3372501d1500","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:28.908685Z","signature_b64":"/s+JSWtct3MVbBCmDTQV2NzlTSGgMnfxHV1AHbY9AhiRRpCYumypt8dkvutsYCQgDK5rjy8cbAs9J2gOWpKgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b33af9b0afe62e54c35083e66cf126adbe1c2b493a08f9d2a18f3372501d1500","last_reissued_at":"2026-05-18T00:31:28.908069Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:28.908069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.06692","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:31:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"us7j8Dcl1asKkHS574IHFTMC63Tkvd+F5/PiM3HfNQc9Dp8OM/B9RKQbB7gFP7zZuJgeBMm5X1EQ2IyqTlbgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T10:32:30.348535Z"},"content_sha256":"5873f2826d9c8004ac461d6d2d0d3fed22f45515c3f057f2acde610d342624f0","schema_version":"1.0","event_id":"sha256:5873f2826d9c8004ac461d6d2d0d3fed22f45515c3f057f2acde610d342624f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WM5PTMFP4YXFJQ2QQPTGZ4JGVW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"QMDP-Net: Deep Learning for Planning under Partial Observability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.AI","authors_text":"David Hsu, Peter Karkus, Wee Sun Lee","submitted_at":"2017-03-20T11:44:00Z","abstract_excerpt":"This paper introduces the QMDP-net, a neural network architecture for planning under partial observability. The QMDP-net combines the strengths of model-free learning and model-based planning. It is a recurrent policy network, but it represents a policy for a parameterized set of tasks by connecting a model with a planning algorithm that solves the model, thus embedding the solution structure of planning in a network learning architecture. The QMDP-net is fully differentiable and allows for end-to-end training. We train a QMDP-net on different tasks so that it can generalize to new ones in the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06692","kind":"arxiv","version":3},"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":"2026-05-18T00:31:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IcO0VQNfzTpizB1CZ1TxSFfZ50/x6j4XScvCX+aw9mqW5x0vNVxXJDLroFbzqNAxOUD1EOgAyJo8ctt7vb/oCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T10:32:30.348916Z"},"content_sha256":"1018348b504b220e37a9edc50a47801e3e8c5aa3a14cab555719aa5f32a64a6f","schema_version":"1.0","event_id":"sha256:1018348b504b220e37a9edc50a47801e3e8c5aa3a14cab555719aa5f32a64a6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/bundle.json","state_url":"https://pith.science/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/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":"2026-05-28T10:32:30Z","links":{"resolver":"https://pith.science/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW","bundle":"https://pith.science/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/bundle.json","state":"https://pith.science/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WM5PTMFP4YXFJQ2QQPTGZ4JGVW","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":"6083d708094c711d2d94cf17b8da6a05da4543caeb66742cedc645976f6e7fa2","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-20T11:44:00Z","title_canon_sha256":"b7395eb7401e4fc9aaa52cd6169f981f07241ba4741b5660b8c78d48682e800e"},"schema_version":"1.0","source":{"id":"1703.06692","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06692","created_at":"2026-05-18T00:31:28Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06692v3","created_at":"2026-05-18T00:31:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06692","created_at":"2026-05-18T00:31:28Z"},{"alias_kind":"pith_short_12","alias_value":"WM5PTMFP4YXF","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WM5PTMFP4YXFJQ2Q","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WM5PTMFP","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:1018348b504b220e37a9edc50a47801e3e8c5aa3a14cab555719aa5f32a64a6f","target":"graph","created_at":"2026-05-18T00:31:28Z","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":"This paper introduces the QMDP-net, a neural network architecture for planning under partial observability. The QMDP-net combines the strengths of model-free learning and model-based planning. It is a recurrent policy network, but it represents a policy for a parameterized set of tasks by connecting a model with a planning algorithm that solves the model, thus embedding the solution structure of planning in a network learning architecture. The QMDP-net is fully differentiable and allows for end-to-end training. We train a QMDP-net on different tasks so that it can generalize to new ones in the","authors_text":"David Hsu, Peter Karkus, Wee Sun Lee","cross_cats":["cs.LG","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-20T11:44:00Z","title":"QMDP-Net: Deep Learning for Planning under Partial Observability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06692","kind":"arxiv","version":3},"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":"sha256:5873f2826d9c8004ac461d6d2d0d3fed22f45515c3f057f2acde610d342624f0","target":"record","created_at":"2026-05-18T00:31:28Z","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":"6083d708094c711d2d94cf17b8da6a05da4543caeb66742cedc645976f6e7fa2","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-20T11:44:00Z","title_canon_sha256":"b7395eb7401e4fc9aaa52cd6169f981f07241ba4741b5660b8c78d48682e800e"},"schema_version":"1.0","source":{"id":"1703.06692","kind":"arxiv","version":3}},"canonical_sha256":"b33af9b0afe62e54c35083e66cf126adbe1c2b493a08f9d2a18f3372501d1500","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b33af9b0afe62e54c35083e66cf126adbe1c2b493a08f9d2a18f3372501d1500","first_computed_at":"2026-05-18T00:31:28.908069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:28.908069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/s+JSWtct3MVbBCmDTQV2NzlTSGgMnfxHV1AHbY9AhiRRpCYumypt8dkvutsYCQgDK5rjy8cbAs9J2gOWpKgAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:28.908685Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.06692","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5873f2826d9c8004ac461d6d2d0d3fed22f45515c3f057f2acde610d342624f0","sha256:1018348b504b220e37a9edc50a47801e3e8c5aa3a14cab555719aa5f32a64a6f"],"state_sha256":"e86cf5617a7a7bc1f12152d8839c15860415ddb6a99f1715db977acad7265c89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1iN2oS9t2uP/ItahtJwbDF9TcXslRgKNS9j/ZEvKHzdPeaWeYUq/gpkH5WR388KUkQeCbbtPjJSDlL1ujncVDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T10:32:30.351056Z","bundle_sha256":"59c4f61f005709ffe7f42ea20fd16117cebbe54bcb345c9d355587e2ab2e75da"}}