{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G6MLHQV3FYXTBFEQI4QWNRGUEH","short_pith_number":"pith:G6MLHQV3","schema_version":"1.0","canonical_sha256":"3798b3c2bb2e2f309490472166c4d421e943efd939f15c2a11acd9c528f90181","source":{"kind":"arxiv","id":"2606.10025","version":1},"attestation_state":"computed","paper":{"title":"GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ben Eisner, Chuang Gan, David Held, Haotian Zhan, Haoyu Zhen, Shubham Tulsiani, Sriram Krishna, Ying Yuan","submitted_at":"2026-06-08T18:08:01Z","abstract_excerpt":"We present GHOST, a framework for learning visuomotor manipulation policies that generalize beyond the training distribution. GHOST factorizes control into (i) a high-level policy that predicts the next sub-goal as a distribution over 3D end-effector poses from multi-view RGB-D observations, and (ii) a low-level goal-conditioned controller that executes embodiment-specific actions. To condition image-based policies on 3D goals, we introduce a simple spatial interface that projects predicted goals into the image plane and represents them as end-effector heatmaps. Across a suite of manipulation "},"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":"2606.10025","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-08T18:08:01Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"d6b05b378d1e9e48124e61f9d0473959c9881c939c82a3d0c6c87e9d6e4b5147","abstract_canon_sha256":"283d16e23a24f55aef0756be4ff4e67273a5cabaf1bacfdcdec2ae523476010d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T00:08:45.080397Z","signature_b64":"PCseBISivLSKzEjs2aYYUmIPiMxk+a9o3M8TmyQysypDaOSXqKoHdC7A1ui+Fzj3Mt8lOSoeCFoAifRQsrY2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3798b3c2bb2e2f309490472166c4d421e943efd939f15c2a11acd9c528f90181","last_reissued_at":"2026-06-10T00:08:45.079496Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T00:08:45.079496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ben Eisner, Chuang Gan, David Held, Haotian Zhan, Haoyu Zhen, Shubham Tulsiani, Sriram Krishna, Ying Yuan","submitted_at":"2026-06-08T18:08:01Z","abstract_excerpt":"We present GHOST, a framework for learning visuomotor manipulation policies that generalize beyond the training distribution. GHOST factorizes control into (i) a high-level policy that predicts the next sub-goal as a distribution over 3D end-effector poses from multi-view RGB-D observations, and (ii) a low-level goal-conditioned controller that executes embodiment-specific actions. To condition image-based policies on 3D goals, we introduce a simple spatial interface that projects predicted goals into the image plane and represents them as end-effector heatmaps. Across a suite of manipulation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10025","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.10025/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2606.10025","created_at":"2026-06-10T00:08:45.079643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10025v1","created_at":"2026-06-10T00:08:45.079643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10025","created_at":"2026-06-10T00:08:45.079643+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6MLHQV3FYXT","created_at":"2026-06-10T00:08:45.079643+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6MLHQV3FYXTBFEQ","created_at":"2026-06-10T00:08:45.079643+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6MLHQV3","created_at":"2026-06-10T00:08:45.079643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6MLHQV3FYXTBFEQI4QWNRGUEH","json":"https://pith.science/pith/G6MLHQV3FYXTBFEQI4QWNRGUEH.json","graph_json":"https://pith.science/api/pith-number/G6MLHQV3FYXTBFEQI4QWNRGUEH/graph.json","events_json":"https://pith.science/api/pith-number/G6MLHQV3FYXTBFEQI4QWNRGUEH/events.json","paper":"https://pith.science/paper/G6MLHQV3"},"agent_actions":{"view_html":"https://pith.science/pith/G6MLHQV3FYXTBFEQI4QWNRGUEH","download_json":"https://pith.science/pith/G6MLHQV3FYXTBFEQI4QWNRGUEH.json","view_paper":"https://pith.science/paper/G6MLHQV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10025&json=true","fetch_graph":"https://pith.science/api/pith-number/G6MLHQV3FYXTBFEQI4QWNRGUEH/graph.json","fetch_events":"https://pith.science/api/pith-number/G6MLHQV3FYXTBFEQI4QWNRGUEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6MLHQV3FYXTBFEQI4QWNRGUEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6MLHQV3FYXTBFEQI4QWNRGUEH/action/storage_attestation","attest_author":"https://pith.science/pith/G6MLHQV3FYXTBFEQI4QWNRGUEH/action/author_attestation","sign_citation":"https://pith.science/pith/G6MLHQV3FYXTBFEQI4QWNRGUEH/action/citation_signature","submit_replication":"https://pith.science/pith/G6MLHQV3FYXTBFEQI4QWNRGUEH/action/replication_record"}},"created_at":"2026-06-10T00:08:45.079643+00:00","updated_at":"2026-06-10T00:08:45.079643+00:00"}