{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2T5FR6FQPAJ6YFG7WT4PMRQ7OR","short_pith_number":"pith:2T5FR6FQ","schema_version":"1.0","canonical_sha256":"d4fa58f8b07813ec14dfb4f8f6461f7466bac806434d997dee940848fc0bae45","source":{"kind":"arxiv","id":"2407.14758","version":1},"attestation_state":"computed","paper":{"title":"DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cewu Lu, Shengcheng Luo, Xinyu Xu, Yanchao Yang, Yong-Lu Li","submitted_at":"2024-07-20T05:39:28Z","abstract_excerpt":"Building a general-purpose intelligent home-assistant agent skilled in diverse tasks by human commands is a long-term blueprint of embodied AI research, which poses requirements on task planning, environment modeling, and object interaction. In this work, we study primitive mobile manipulations for embodied agents, i.e. how to navigate and interact based on an instructed verb-noun pair. We propose DISCO, which features non-trivial advancements in contextualized scene modeling and efficient controls. In particular, DISCO incorporates differentiable scene representations of rich semantics in obj"},"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":"2407.14758","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-20T05:39:28Z","cross_cats_sorted":[],"title_canon_sha256":"6d0735c51d092613e726357a509e605442e8bcb57cf1bd57b38e7bf3b3d516b0","abstract_canon_sha256":"9253a24777bfe98a318822d2fda45f14dafafd924a0d30e826df41e460c28d4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:33.372914Z","signature_b64":"mYss4IGJAp6PKdQc6CLF3+wO3w5ZuxZ5qJygnPpNxUKsVv1J6bUQkJ2R98LnMDRklGxcpd1dT9nxotd6Kb7VAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4fa58f8b07813ec14dfb4f8f6461f7466bac806434d997dee940848fc0bae45","last_reissued_at":"2026-07-05T08:46:33.372518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:33.372518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cewu Lu, Shengcheng Luo, Xinyu Xu, Yanchao Yang, Yong-Lu Li","submitted_at":"2024-07-20T05:39:28Z","abstract_excerpt":"Building a general-purpose intelligent home-assistant agent skilled in diverse tasks by human commands is a long-term blueprint of embodied AI research, which poses requirements on task planning, environment modeling, and object interaction. In this work, we study primitive mobile manipulations for embodied agents, i.e. how to navigate and interact based on an instructed verb-noun pair. We propose DISCO, which features non-trivial advancements in contextualized scene modeling and efficient controls. In particular, DISCO incorporates differentiable scene representations of rich semantics in obj"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14758","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/2407.14758/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":"2407.14758","created_at":"2026-07-05T08:46:33.372580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14758v1","created_at":"2026-07-05T08:46:33.372580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14758","created_at":"2026-07-05T08:46:33.372580+00:00"},{"alias_kind":"pith_short_12","alias_value":"2T5FR6FQPAJ6","created_at":"2026-07-05T08:46:33.372580+00:00"},{"alias_kind":"pith_short_16","alias_value":"2T5FR6FQPAJ6YFG7","created_at":"2026-07-05T08:46:33.372580+00:00"},{"alias_kind":"pith_short_8","alias_value":"2T5FR6FQ","created_at":"2026-07-05T08:46:33.372580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17288","citing_title":"Multi-Modal Grounded Planning and Efficient Replanning For Learning Embodied Agents with A Few Examples","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2T5FR6FQPAJ6YFG7WT4PMRQ7OR","json":"https://pith.science/pith/2T5FR6FQPAJ6YFG7WT4PMRQ7OR.json","graph_json":"https://pith.science/api/pith-number/2T5FR6FQPAJ6YFG7WT4PMRQ7OR/graph.json","events_json":"https://pith.science/api/pith-number/2T5FR6FQPAJ6YFG7WT4PMRQ7OR/events.json","paper":"https://pith.science/paper/2T5FR6FQ"},"agent_actions":{"view_html":"https://pith.science/pith/2T5FR6FQPAJ6YFG7WT4PMRQ7OR","download_json":"https://pith.science/pith/2T5FR6FQPAJ6YFG7WT4PMRQ7OR.json","view_paper":"https://pith.science/paper/2T5FR6FQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14758&json=true","fetch_graph":"https://pith.science/api/pith-number/2T5FR6FQPAJ6YFG7WT4PMRQ7OR/graph.json","fetch_events":"https://pith.science/api/pith-number/2T5FR6FQPAJ6YFG7WT4PMRQ7OR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2T5FR6FQPAJ6YFG7WT4PMRQ7OR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2T5FR6FQPAJ6YFG7WT4PMRQ7OR/action/storage_attestation","attest_author":"https://pith.science/pith/2T5FR6FQPAJ6YFG7WT4PMRQ7OR/action/author_attestation","sign_citation":"https://pith.science/pith/2T5FR6FQPAJ6YFG7WT4PMRQ7OR/action/citation_signature","submit_replication":"https://pith.science/pith/2T5FR6FQPAJ6YFG7WT4PMRQ7OR/action/replication_record"}},"created_at":"2026-07-05T08:46:33.372580+00:00","updated_at":"2026-07-05T08:46:33.372580+00:00"}