{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7SON3G77HNVK6VBEZ7EEWRRYPK","short_pith_number":"pith:7SON3G77","schema_version":"1.0","canonical_sha256":"fc9cdd9bff3b6aaf5424cfc84b46387aaaba32a2a54cf22934061f6b7a71559e","source":{"kind":"arxiv","id":"2402.15487","version":2},"attestation_state":"computed","paper":{"title":"RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Binghao Huang, Hanxiao Jiang, Hooshang Nayyeri, Ruihai Wu, Shenlong Wang, Shubham Garg, Yunzhu Li, Zhuoran Li","submitted_at":"2024-02-23T18:27:17Z","abstract_excerpt":"We introduce the novel task of interactive scene exploration, wherein robots autonomously explore environments and produce an action-conditioned scene graph (ACSG) that captures the structure of the underlying environment. The ACSG accounts for both low-level information (geometry and semantics) and high-level information (action-conditioned relationships between different entities) in the scene. To this end, we present the Robotic Exploration (RoboEXP) system, which incorporates the Large Multimodal Model (LMM) and an explicit memory design to enhance our system's capabilities. The robot reas"},"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":"2402.15487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-02-23T18:27:17Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"2c43887f95f21734756be759ca521b98fbb09ec6025c93cce6fa579cea09ca69","abstract_canon_sha256":"7fade576e12ff7887b1ddf58087b80ff9ccc8e0b97fd51e0cdffb041a624f683"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:12.038939Z","signature_b64":"xrLEgNHJGVE5D+Ol8Fymcojysi+hS6CjjJhTkesbFfmJWrG2MSFtPyKmaA0AARTbzO66Dk48N+Wmja0mxdWEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc9cdd9bff3b6aaf5424cfc84b46387aaaba32a2a54cf22934061f6b7a71559e","last_reissued_at":"2026-07-05T09:17:12.038464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:12.038464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Binghao Huang, Hanxiao Jiang, Hooshang Nayyeri, Ruihai Wu, Shenlong Wang, Shubham Garg, Yunzhu Li, Zhuoran Li","submitted_at":"2024-02-23T18:27:17Z","abstract_excerpt":"We introduce the novel task of interactive scene exploration, wherein robots autonomously explore environments and produce an action-conditioned scene graph (ACSG) that captures the structure of the underlying environment. The ACSG accounts for both low-level information (geometry and semantics) and high-level information (action-conditioned relationships between different entities) in the scene. To this end, we present the Robotic Exploration (RoboEXP) system, which incorporates the Large Multimodal Model (LMM) and an explicit memory design to enhance our system's capabilities. The robot reas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15487","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.15487/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":"2402.15487","created_at":"2026-07-05T09:17:12.038524+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15487v2","created_at":"2026-07-05T09:17:12.038524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15487","created_at":"2026-07-05T09:17:12.038524+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SON3G77HNVK","created_at":"2026-07-05T09:17:12.038524+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SON3G77HNVK6VBE","created_at":"2026-07-05T09:17:12.038524+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SON3G77","created_at":"2026-07-05T09:17:12.038524+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01072","citing_title":"Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29879","citing_title":"DGSG-Mind: Dynamic 3D Gaussian Scene Graphs for Long-Term Scene Understanding and Grounding","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18184","citing_title":"Fixed External Cameras as Common Prior Maps for Active 3D Scene Graph Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18197","citing_title":"RGB-only Active 3D Scene Graph Generation for Indoor Mobile Robots","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13428","citing_title":"SID: Sliding into Distribution for Robust Few-Demonstration Manipulation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7SON3G77HNVK6VBEZ7EEWRRYPK","json":"https://pith.science/pith/7SON3G77HNVK6VBEZ7EEWRRYPK.json","graph_json":"https://pith.science/api/pith-number/7SON3G77HNVK6VBEZ7EEWRRYPK/graph.json","events_json":"https://pith.science/api/pith-number/7SON3G77HNVK6VBEZ7EEWRRYPK/events.json","paper":"https://pith.science/paper/7SON3G77"},"agent_actions":{"view_html":"https://pith.science/pith/7SON3G77HNVK6VBEZ7EEWRRYPK","download_json":"https://pith.science/pith/7SON3G77HNVK6VBEZ7EEWRRYPK.json","view_paper":"https://pith.science/paper/7SON3G77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15487&json=true","fetch_graph":"https://pith.science/api/pith-number/7SON3G77HNVK6VBEZ7EEWRRYPK/graph.json","fetch_events":"https://pith.science/api/pith-number/7SON3G77HNVK6VBEZ7EEWRRYPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SON3G77HNVK6VBEZ7EEWRRYPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SON3G77HNVK6VBEZ7EEWRRYPK/action/storage_attestation","attest_author":"https://pith.science/pith/7SON3G77HNVK6VBEZ7EEWRRYPK/action/author_attestation","sign_citation":"https://pith.science/pith/7SON3G77HNVK6VBEZ7EEWRRYPK/action/citation_signature","submit_replication":"https://pith.science/pith/7SON3G77HNVK6VBEZ7EEWRRYPK/action/replication_record"}},"created_at":"2026-07-05T09:17:12.038524+00:00","updated_at":"2026-07-05T09:17:12.038524+00:00"}