{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BGZNADIV3WRHICLR2SFOP2KWPX","short_pith_number":"pith:BGZNADIV","schema_version":"1.0","canonical_sha256":"09b2d00d15dda2740971d48ae7e9567dde3a8c18a98f723adaca64e1353a21ae","source":{"kind":"arxiv","id":"2409.20154","version":7},"attestation_state":"computed","paper":{"title":"GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jieqi Shi, Jing Huo, Junhui Yin, Pinzhuo Tian, Yang Gao, Yangtao Chen, Zixuan Chen","submitted_at":"2024-09-30T10:02:42Z","abstract_excerpt":"Robots' ability to follow language instructions and execute diverse 3D manipulation tasks is vital in robot learning. Traditional imitation learning-based methods perform well on seen tasks but struggle with novel, unseen ones due to variability. Recent approaches leverage large foundation models to assist in understanding novel tasks, thereby mitigating this issue. However, these methods lack a task-specific learning process, which is essential for an accurate understanding of 3D environments, often leading to execution failures. In this paper, we introduce GravMAD, a sub-goal-driven, languag"},"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":"2409.20154","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-30T10:02:42Z","cross_cats_sorted":[],"title_canon_sha256":"d59746e1e9208fc193f4637af7757f975c5f89d26447f46cbbf40c5ef7206c96","abstract_canon_sha256":"7a99cf213d646d0ab924eaa4349939bd748d1233ae546d56a0d7f032c8ebcda5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:47.499546Z","signature_b64":"3drwlWL6jeelrKvcuYqVsVQtbQZ22EB/qRZqaBuWwtlyW8N0RehlcmBAwSHE7rSoQ2X4zU9S+wcohwYZ5xOvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09b2d00d15dda2740971d48ae7e9567dde3a8c18a98f723adaca64e1353a21ae","last_reissued_at":"2026-07-05T10:31:47.498876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:47.498876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jieqi Shi, Jing Huo, Junhui Yin, Pinzhuo Tian, Yang Gao, Yangtao Chen, Zixuan Chen","submitted_at":"2024-09-30T10:02:42Z","abstract_excerpt":"Robots' ability to follow language instructions and execute diverse 3D manipulation tasks is vital in robot learning. Traditional imitation learning-based methods perform well on seen tasks but struggle with novel, unseen ones due to variability. Recent approaches leverage large foundation models to assist in understanding novel tasks, thereby mitigating this issue. However, these methods lack a task-specific learning process, which is essential for an accurate understanding of 3D environments, often leading to execution failures. In this paper, we introduce GravMAD, a sub-goal-driven, languag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20154","kind":"arxiv","version":7},"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/2409.20154/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":"2409.20154","created_at":"2026-07-05T10:31:47.498959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.20154v7","created_at":"2026-07-05T10:31:47.498959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20154","created_at":"2026-07-05T10:31:47.498959+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGZNADIV3WRH","created_at":"2026-07-05T10:31:47.498959+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGZNADIV3WRHICLR","created_at":"2026-07-05T10:31:47.498959+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGZNADIV","created_at":"2026-07-05T10:31:47.498959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06605","citing_title":"RoboHorizon: An LLM-Assisted Multi-View World Model for Long-Horizon Robotic Manipulation","ref_index":4622,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGZNADIV3WRHICLR2SFOP2KWPX","json":"https://pith.science/pith/BGZNADIV3WRHICLR2SFOP2KWPX.json","graph_json":"https://pith.science/api/pith-number/BGZNADIV3WRHICLR2SFOP2KWPX/graph.json","events_json":"https://pith.science/api/pith-number/BGZNADIV3WRHICLR2SFOP2KWPX/events.json","paper":"https://pith.science/paper/BGZNADIV"},"agent_actions":{"view_html":"https://pith.science/pith/BGZNADIV3WRHICLR2SFOP2KWPX","download_json":"https://pith.science/pith/BGZNADIV3WRHICLR2SFOP2KWPX.json","view_paper":"https://pith.science/paper/BGZNADIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.20154&json=true","fetch_graph":"https://pith.science/api/pith-number/BGZNADIV3WRHICLR2SFOP2KWPX/graph.json","fetch_events":"https://pith.science/api/pith-number/BGZNADIV3WRHICLR2SFOP2KWPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGZNADIV3WRHICLR2SFOP2KWPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGZNADIV3WRHICLR2SFOP2KWPX/action/storage_attestation","attest_author":"https://pith.science/pith/BGZNADIV3WRHICLR2SFOP2KWPX/action/author_attestation","sign_citation":"https://pith.science/pith/BGZNADIV3WRHICLR2SFOP2KWPX/action/citation_signature","submit_replication":"https://pith.science/pith/BGZNADIV3WRHICLR2SFOP2KWPX/action/replication_record"}},"created_at":"2026-07-05T10:31:47.498959+00:00","updated_at":"2026-07-05T10:31:47.498959+00:00"}