{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:253USWKYZU3PTREBIDDMHMSEZM","short_pith_number":"pith:253USWKY","schema_version":"1.0","canonical_sha256":"d777495958cd36f9c48140c6c3b244cb1e3de1958d1d316687bb6a2c2b878001","source":{"kind":"arxiv","id":"1705.00154","version":3},"attestation_state":"computed","paper":{"title":"Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alex Fukunaga, Masataro Asai","submitted_at":"2017-04-29T08:22:29Z","abstract_excerpt":"Current domain-independent, classical planners require symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We propose LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1705.00154","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-04-29T08:22:29Z","cross_cats_sorted":[],"title_canon_sha256":"1f7a5590f46b69d14a0600278ac8acd0814a2991a567ba0a1a02971258c89fd0","abstract_canon_sha256":"1c423c377dd8815ca943433eed5a31be541922056a6a5e9f90327c6e673109a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:01.521503Z","signature_b64":"bJBwy5xMn8or21mrcfqAXHKu+rbTQtx23KQ0FfWua4y9Yoz1r/WnR9VvfugHECKg51To01jvloC0EnCLm0fwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d777495958cd36f9c48140c6c3b244cb1e3de1958d1d316687bb6a2c2b878001","last_reissued_at":"2026-05-18T00:29:01.521114Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:01.521114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alex Fukunaga, Masataro Asai","submitted_at":"2017-04-29T08:22:29Z","abstract_excerpt":"Current domain-independent, classical planners require symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We propose LatPlan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), and a pair of i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.00154","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1705.00154","created_at":"2026-05-18T00:29:01.521179+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.00154v3","created_at":"2026-05-18T00:29:01.521179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.00154","created_at":"2026-05-18T00:29:01.521179+00:00"},{"alias_kind":"pith_short_12","alias_value":"253USWKYZU3P","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"253USWKYZU3PTREB","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"253USWKY","created_at":"2026-05-18T12:30:55.937587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2010.03768","citing_title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/253USWKYZU3PTREBIDDMHMSEZM","json":"https://pith.science/pith/253USWKYZU3PTREBIDDMHMSEZM.json","graph_json":"https://pith.science/api/pith-number/253USWKYZU3PTREBIDDMHMSEZM/graph.json","events_json":"https://pith.science/api/pith-number/253USWKYZU3PTREBIDDMHMSEZM/events.json","paper":"https://pith.science/paper/253USWKY"},"agent_actions":{"view_html":"https://pith.science/pith/253USWKYZU3PTREBIDDMHMSEZM","download_json":"https://pith.science/pith/253USWKYZU3PTREBIDDMHMSEZM.json","view_paper":"https://pith.science/paper/253USWKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.00154&json=true","fetch_graph":"https://pith.science/api/pith-number/253USWKYZU3PTREBIDDMHMSEZM/graph.json","fetch_events":"https://pith.science/api/pith-number/253USWKYZU3PTREBIDDMHMSEZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/253USWKYZU3PTREBIDDMHMSEZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/253USWKYZU3PTREBIDDMHMSEZM/action/storage_attestation","attest_author":"https://pith.science/pith/253USWKYZU3PTREBIDDMHMSEZM/action/author_attestation","sign_citation":"https://pith.science/pith/253USWKYZU3PTREBIDDMHMSEZM/action/citation_signature","submit_replication":"https://pith.science/pith/253USWKYZU3PTREBIDDMHMSEZM/action/replication_record"}},"created_at":"2026-05-18T00:29:01.521179+00:00","updated_at":"2026-05-18T00:29:01.521179+00:00"}