{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5JYXFN6IBUO2VTVOPJXVHU6SNA","short_pith_number":"pith:5JYXFN6I","canonical_record":{"source":{"id":"1904.09366","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-04-19T23:15:59Z","cross_cats_sorted":[],"title_canon_sha256":"f18451361c26b132e1d3f30083b7b41149415b22139557f2f714183a510c8bb9","abstract_canon_sha256":"b0f263092a4bf25552596cc677dc7ccd74852068c5587ac8d1d8791c9445bdea"},"schema_version":"1.0"},"canonical_sha256":"ea7172b7c80d1daaceae7a6f53d3d26827622410974e67e1048b4de15f5092d8","source":{"kind":"arxiv","id":"1904.09366","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09366","created_at":"2026-05-17T23:39:30Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09366v4","created_at":"2026-05-17T23:39:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09366","created_at":"2026-05-17T23:39:30Z"},{"alias_kind":"pith_short_12","alias_value":"5JYXFN6IBUO2","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5JYXFN6IBUO2VTVO","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5JYXFN6I","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5JYXFN6IBUO2VTVOPJXVHU6SNA","target":"record","payload":{"canonical_record":{"source":{"id":"1904.09366","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-04-19T23:15:59Z","cross_cats_sorted":[],"title_canon_sha256":"f18451361c26b132e1d3f30083b7b41149415b22139557f2f714183a510c8bb9","abstract_canon_sha256":"b0f263092a4bf25552596cc677dc7ccd74852068c5587ac8d1d8791c9445bdea"},"schema_version":"1.0"},"canonical_sha256":"ea7172b7c80d1daaceae7a6f53d3d26827622410974e67e1048b4de15f5092d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:30.238967Z","signature_b64":"+MDTfCm7ZLQXfXIM8W1b/hPBeema7IcLaMgtGv40Valvte2NEuWrNc2t96elnOYM6G2oQuqOnjN8i0T+ydKlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea7172b7c80d1daaceae7a6f53d3d26827622410974e67e1048b4de15f5092d8","last_reissued_at":"2026-05-17T23:39:30.238498Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:30.238498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.09366","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2hfyRDpF/ysq2B6C2vGxUSdXUgyVL2zStxoT55iNhkDIkVlHqmU9o2oN2thRmqgLJZlmf4IoqVj/9CEJ+L4xBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T23:29:29.553030Z"},"content_sha256":"3a9b83e7c821f3824acd640548813ccfa762c3db587de19149d47a289fa2d7f0","schema_version":"1.0","event_id":"sha256:3a9b83e7c821f3824acd640548813ccfa762c3db587de19149d47a289fa2d7f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5JYXFN6IBUO2VTVOPJXVHU6SNA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward Potentials for Planning with Learned Neural Network Transition Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Buser Say, Scott Sanner, Sylvie Thi\\'ebaux","submitted_at":"2019-04-19T23:15:59Z","abstract_excerpt":"Optimal planning with respect to learned neural network (NN) models in continuous action and state spaces using mixed-integer linear programming (MILP) is a challenging task for branch-and-bound solvers due to the poor linear relaxation of the underlying MILP model. For a given set of features, potential heuristics provide an efficient framework for computing bounds on cost (reward) functions. In this paper, we model the problem of finding optimal potential bounds for learned NN models as a bilevel program, and solve it using a novel finite-time constraint generation algorithm. We then strengt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09366","kind":"arxiv","version":4},"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":"2026-05-17T23:39:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/wnTFQZ+xFDCpKExqXZCsCtmCTFmXzzMw35YFOin+DPX0/XCxxBiWBwsadoocZHhCKStkoHk9mouyNyc2pACBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T23:29:29.554178Z"},"content_sha256":"3571fdffe9c50744ac3e56730855f72fe9b229f9f3442fd6a65b4f471607baed","schema_version":"1.0","event_id":"sha256:3571fdffe9c50744ac3e56730855f72fe9b229f9f3442fd6a65b4f471607baed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5JYXFN6IBUO2VTVOPJXVHU6SNA/bundle.json","state_url":"https://pith.science/pith/5JYXFN6IBUO2VTVOPJXVHU6SNA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5JYXFN6IBUO2VTVOPJXVHU6SNA/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":"2026-06-04T23:29:29Z","links":{"resolver":"https://pith.science/pith/5JYXFN6IBUO2VTVOPJXVHU6SNA","bundle":"https://pith.science/pith/5JYXFN6IBUO2VTVOPJXVHU6SNA/bundle.json","state":"https://pith.science/pith/5JYXFN6IBUO2VTVOPJXVHU6SNA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5JYXFN6IBUO2VTVOPJXVHU6SNA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5JYXFN6IBUO2VTVOPJXVHU6SNA","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":"b0f263092a4bf25552596cc677dc7ccd74852068c5587ac8d1d8791c9445bdea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-04-19T23:15:59Z","title_canon_sha256":"f18451361c26b132e1d3f30083b7b41149415b22139557f2f714183a510c8bb9"},"schema_version":"1.0","source":{"id":"1904.09366","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09366","created_at":"2026-05-17T23:39:30Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09366v4","created_at":"2026-05-17T23:39:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09366","created_at":"2026-05-17T23:39:30Z"},{"alias_kind":"pith_short_12","alias_value":"5JYXFN6IBUO2","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5JYXFN6IBUO2VTVO","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5JYXFN6I","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:3571fdffe9c50744ac3e56730855f72fe9b229f9f3442fd6a65b4f471607baed","target":"graph","created_at":"2026-05-17T23:39:30Z","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":"Optimal planning with respect to learned neural network (NN) models in continuous action and state spaces using mixed-integer linear programming (MILP) is a challenging task for branch-and-bound solvers due to the poor linear relaxation of the underlying MILP model. For a given set of features, potential heuristics provide an efficient framework for computing bounds on cost (reward) functions. In this paper, we model the problem of finding optimal potential bounds for learned NN models as a bilevel program, and solve it using a novel finite-time constraint generation algorithm. We then strengt","authors_text":"Buser Say, Scott Sanner, Sylvie Thi\\'ebaux","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-04-19T23:15:59Z","title":"Reward Potentials for Planning with Learned Neural Network Transition Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09366","kind":"arxiv","version":4},"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":"sha256:3a9b83e7c821f3824acd640548813ccfa762c3db587de19149d47a289fa2d7f0","target":"record","created_at":"2026-05-17T23:39:30Z","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":"b0f263092a4bf25552596cc677dc7ccd74852068c5587ac8d1d8791c9445bdea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-04-19T23:15:59Z","title_canon_sha256":"f18451361c26b132e1d3f30083b7b41149415b22139557f2f714183a510c8bb9"},"schema_version":"1.0","source":{"id":"1904.09366","kind":"arxiv","version":4}},"canonical_sha256":"ea7172b7c80d1daaceae7a6f53d3d26827622410974e67e1048b4de15f5092d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea7172b7c80d1daaceae7a6f53d3d26827622410974e67e1048b4de15f5092d8","first_computed_at":"2026-05-17T23:39:30.238498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:30.238498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+MDTfCm7ZLQXfXIM8W1b/hPBeema7IcLaMgtGv40Valvte2NEuWrNc2t96elnOYM6G2oQuqOnjN8i0T+ydKlDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:30.238967Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.09366","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a9b83e7c821f3824acd640548813ccfa762c3db587de19149d47a289fa2d7f0","sha256:3571fdffe9c50744ac3e56730855f72fe9b229f9f3442fd6a65b4f471607baed"],"state_sha256":"3bb688059b47708c074305a2d0a46815a8839270281b33449a98a0fd18a19425"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zX6yUE73MEFlRxAoy/R7c3jwpxvheVvhHyEzS7/Txg7IjUwAAVGoIEjg0aPE7h3mBY3+xbP3LLb1GsDjvTxuDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T23:29:29.559211Z","bundle_sha256":"b19920cf888f14d973492e0f52b202a3d280074e9f1e720ac14890ae66eb7c4c"}}