{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SIKMDX4OR4NDZIEBMECS6KRYBB","short_pith_number":"pith:SIKMDX4O","schema_version":"1.0","canonical_sha256":"9214c1df8e8f1a3ca08161052f2a38086232e5c9c4f1eedf99cc06deac5ca018","source":{"kind":"arxiv","id":"2304.03696","version":3},"attestation_state":"computed","paper":{"title":"MOPA: Modular Object Navigation with PointGoal Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Angel X. Chang, Manolis Savva, Sonia Raychaudhuri, Tommaso Campari, Unnat Jain","submitted_at":"2023-04-07T15:32:16Z","abstract_excerpt":"We propose a simple but effective modular approach MOPA (Modular ObjectNav with PointGoal agents) to systematically investigate the inherent modularity of the object navigation task in Embodied AI. MOPA consists of four modules: (a) an object detection module trained to identify objects from RGB images, (b) a map building module to build a semantic map of the observed objects, (c) an exploration module enabling the agent to explore the environment, and (d) a navigation module to move to identified target objects. We show that we can effectively reuse a pretrained PointGoal agent as the navigat"},"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":"2304.03696","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-04-07T15:32:16Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"cfea81f131deb6fcbd0db6dc3c01f3a462ec7831a9bfb963a093b68385e3f770","abstract_canon_sha256":"ac9ba96fc51faa4944a7aa0393505dfa26d3663b394136b57e907dd645a69433"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:26.682436Z","signature_b64":"ZlU/IKloCg+ZjtyKCWz1c67fFWRMELYKAEcJ82qlxvV3Yu0PRSAHCK4rBGvno6yaE45n8LikVtUW7hXE1i0NCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9214c1df8e8f1a3ca08161052f2a38086232e5c9c4f1eedf99cc06deac5ca018","last_reissued_at":"2026-07-05T07:38:26.681632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:26.681632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOPA: Modular Object Navigation with PointGoal Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Angel X. Chang, Manolis Savva, Sonia Raychaudhuri, Tommaso Campari, Unnat Jain","submitted_at":"2023-04-07T15:32:16Z","abstract_excerpt":"We propose a simple but effective modular approach MOPA (Modular ObjectNav with PointGoal agents) to systematically investigate the inherent modularity of the object navigation task in Embodied AI. MOPA consists of four modules: (a) an object detection module trained to identify objects from RGB images, (b) a map building module to build a semantic map of the observed objects, (c) an exploration module enabling the agent to explore the environment, and (d) a navigation module to move to identified target objects. We show that we can effectively reuse a pretrained PointGoal agent as the navigat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03696","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.03696/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":"2304.03696","created_at":"2026-07-05T07:38:26.681693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03696v3","created_at":"2026-07-05T07:38:26.681693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03696","created_at":"2026-07-05T07:38:26.681693+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIKMDX4OR4ND","created_at":"2026-07-05T07:38:26.681693+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIKMDX4OR4NDZIEB","created_at":"2026-07-05T07:38:26.681693+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIKMDX4O","created_at":"2026-07-05T07:38:26.681693+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22409","citing_title":"SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2412.07160","citing_title":"Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22409","citing_title":"SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIKMDX4OR4NDZIEBMECS6KRYBB","json":"https://pith.science/pith/SIKMDX4OR4NDZIEBMECS6KRYBB.json","graph_json":"https://pith.science/api/pith-number/SIKMDX4OR4NDZIEBMECS6KRYBB/graph.json","events_json":"https://pith.science/api/pith-number/SIKMDX4OR4NDZIEBMECS6KRYBB/events.json","paper":"https://pith.science/paper/SIKMDX4O"},"agent_actions":{"view_html":"https://pith.science/pith/SIKMDX4OR4NDZIEBMECS6KRYBB","download_json":"https://pith.science/pith/SIKMDX4OR4NDZIEBMECS6KRYBB.json","view_paper":"https://pith.science/paper/SIKMDX4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03696&json=true","fetch_graph":"https://pith.science/api/pith-number/SIKMDX4OR4NDZIEBMECS6KRYBB/graph.json","fetch_events":"https://pith.science/api/pith-number/SIKMDX4OR4NDZIEBMECS6KRYBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIKMDX4OR4NDZIEBMECS6KRYBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIKMDX4OR4NDZIEBMECS6KRYBB/action/storage_attestation","attest_author":"https://pith.science/pith/SIKMDX4OR4NDZIEBMECS6KRYBB/action/author_attestation","sign_citation":"https://pith.science/pith/SIKMDX4OR4NDZIEBMECS6KRYBB/action/citation_signature","submit_replication":"https://pith.science/pith/SIKMDX4OR4NDZIEBMECS6KRYBB/action/replication_record"}},"created_at":"2026-07-05T07:38:26.681693+00:00","updated_at":"2026-07-05T07:38:26.681693+00:00"}