{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PHXSKWZVEGCG6XDEOOWIMGL3TA","short_pith_number":"pith:PHXSKWZV","canonical_record":{"source":{"id":"1810.09923","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-23T15:44:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"301dbd14c34f11c6792799bcfa278b1875de357b5ce5d7c7049c1eb4723c7292","abstract_canon_sha256":"f1e12d64e81b28b3ce6140452f645ce02944d9dc8647e59d7d2b3f7707a9a107"},"schema_version":"1.0"},"canonical_sha256":"79ef255b3521846f5c6473ac86197b9812502c056799b05806d4e40aa8dab6b3","source":{"kind":"arxiv","id":"1810.09923","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.09923","created_at":"2026-05-17T23:48:50Z"},{"alias_kind":"arxiv_version","alias_value":"1810.09923v2","created_at":"2026-05-17T23:48:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09923","created_at":"2026-05-17T23:48:50Z"},{"alias_kind":"pith_short_12","alias_value":"PHXSKWZVEGCG","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PHXSKWZVEGCG6XDE","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PHXSKWZV","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PHXSKWZVEGCG6XDEOOWIMGL3TA","target":"record","payload":{"canonical_record":{"source":{"id":"1810.09923","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-23T15:44:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"301dbd14c34f11c6792799bcfa278b1875de357b5ce5d7c7049c1eb4723c7292","abstract_canon_sha256":"f1e12d64e81b28b3ce6140452f645ce02944d9dc8647e59d7d2b3f7707a9a107"},"schema_version":"1.0"},"canonical_sha256":"79ef255b3521846f5c6473ac86197b9812502c056799b05806d4e40aa8dab6b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:50.644657Z","signature_b64":"FEvv6FQHrhu9C5BpwNtSsgTWklDENGKh22dE/IDS4AyqPPBv97srMVxXjoKSQm27djHCftNfgXxl7p5cSNVoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79ef255b3521846f5c6473ac86197b9812502c056799b05806d4e40aa8dab6b3","last_reissued_at":"2026-05-17T23:48:50.644099Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:50.644099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.09923","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":"2026-05-17T23:48:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zg5urVoXV/l3dSHQxkxh53r09tbY98l2EZOQEIe8spFd/0XcYwEiXe7W7kqXcaI75Ic9cHRQxWgcwjduxCBcDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T14:56:36.796206Z"},"content_sha256":"1ab9779bca9114d09b2628aca051ad895a19d5ee929979bb37ee43cbc9b5773a","schema_version":"1.0","event_id":"sha256:1ab9779bca9114d09b2628aca051ad895a19d5ee929979bb37ee43cbc9b5773a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PHXSKWZVEGCG6XDEOOWIMGL3TA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Classical Planning Strategies with Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alessandra Russo, Dalal Alrajeh, Pawel Gomoluch","submitted_at":"2018-10-23T15:44:44Z","abstract_excerpt":"A common paradigm in classical planning is heuristic forward search. Forward search planners often rely on simple best-first search which remains fixed throughout the search process. In this paper, we introduce a novel search framework capable of alternating between several forward search approaches while solving a particular planning problem. Selection of the approach is performed using a trainable stochastic policy, mapping the state of the search to a probability distribution over the approaches. This enables using policy gradient to learn search strategies tailored to a specific distributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09923","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":"2026-05-17T23:48:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z6El6BAo7e6dTL1rIXqictKwQifoL7Eyj9HYpls1iouSd9eKm8/IHOXs2sPdfAyKlT3bM66vULC2n818s/ZGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T14:56:36.796877Z"},"content_sha256":"86192265d8e92e4f49665794e72d680b8c41026dbc95043de8cc200b84a44ef2","schema_version":"1.0","event_id":"sha256:86192265d8e92e4f49665794e72d680b8c41026dbc95043de8cc200b84a44ef2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA/bundle.json","state_url":"https://pith.science/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA/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":"2026-05-29T14:56:36Z","links":{"resolver":"https://pith.science/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA","bundle":"https://pith.science/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA/bundle.json","state":"https://pith.science/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PHXSKWZVEGCG6XDEOOWIMGL3TA","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":"f1e12d64e81b28b3ce6140452f645ce02944d9dc8647e59d7d2b3f7707a9a107","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-23T15:44:44Z","title_canon_sha256":"301dbd14c34f11c6792799bcfa278b1875de357b5ce5d7c7049c1eb4723c7292"},"schema_version":"1.0","source":{"id":"1810.09923","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.09923","created_at":"2026-05-17T23:48:50Z"},{"alias_kind":"arxiv_version","alias_value":"1810.09923v2","created_at":"2026-05-17T23:48:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09923","created_at":"2026-05-17T23:48:50Z"},{"alias_kind":"pith_short_12","alias_value":"PHXSKWZVEGCG","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PHXSKWZVEGCG6XDE","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PHXSKWZV","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:86192265d8e92e4f49665794e72d680b8c41026dbc95043de8cc200b84a44ef2","target":"graph","created_at":"2026-05-17T23:48:50Z","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":"A common paradigm in classical planning is heuristic forward search. Forward search planners often rely on simple best-first search which remains fixed throughout the search process. In this paper, we introduce a novel search framework capable of alternating between several forward search approaches while solving a particular planning problem. Selection of the approach is performed using a trainable stochastic policy, mapping the state of the search to a probability distribution over the approaches. This enables using policy gradient to learn search strategies tailored to a specific distributi","authors_text":"Alessandra Russo, Dalal Alrajeh, Pawel Gomoluch","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-23T15:44:44Z","title":"Learning Classical Planning Strategies with Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09923","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":"sha256:1ab9779bca9114d09b2628aca051ad895a19d5ee929979bb37ee43cbc9b5773a","target":"record","created_at":"2026-05-17T23:48:50Z","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":"f1e12d64e81b28b3ce6140452f645ce02944d9dc8647e59d7d2b3f7707a9a107","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-23T15:44:44Z","title_canon_sha256":"301dbd14c34f11c6792799bcfa278b1875de357b5ce5d7c7049c1eb4723c7292"},"schema_version":"1.0","source":{"id":"1810.09923","kind":"arxiv","version":2}},"canonical_sha256":"79ef255b3521846f5c6473ac86197b9812502c056799b05806d4e40aa8dab6b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79ef255b3521846f5c6473ac86197b9812502c056799b05806d4e40aa8dab6b3","first_computed_at":"2026-05-17T23:48:50.644099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:50.644099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FEvv6FQHrhu9C5BpwNtSsgTWklDENGKh22dE/IDS4AyqPPBv97srMVxXjoKSQm27djHCftNfgXxl7p5cSNVoCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:50.644657Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.09923","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ab9779bca9114d09b2628aca051ad895a19d5ee929979bb37ee43cbc9b5773a","sha256:86192265d8e92e4f49665794e72d680b8c41026dbc95043de8cc200b84a44ef2"],"state_sha256":"3685a183e0f134f6318d7f99da2b984fabcbec00c2f5e496f13e44473f0ad23e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DWK2Dg+48hOjS2RBbi3UWIHId6WMXsgdwerKqzWQ/2j5oY2K+pBHGbLNUB/4i+1oa3DEDdnP2c0mo+BT6XZhCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T14:56:36.800590Z","bundle_sha256":"cda4e75bc2ac2f572f31c69dc96a13a209d2ecf921932a91964598728bd8278a"}}