{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NCLZQBTRBLMOTBOMCPDDLWSCYD","short_pith_number":"pith:NCLZQBTR","schema_version":"1.0","canonical_sha256":"68979806710ad8e985cc13c635da42c0c08747fd0166bff41a8ea12aa8e65cc7","source":{"kind":"arxiv","id":"2506.01600","version":1},"attestation_state":"computed","paper":{"title":"WoMAP: World Models For Embodied Open-Vocabulary Object Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Anirudha Majumdar, Emily Zhou, Jeremy Bao, Lihan Zha, Miyu Yamane, Ola Shorinwa, Tao Sun, Tenny Yin, Zhiting Mei","submitted_at":"2025-06-02T12:35:14Z","abstract_excerpt":"Language-instructed active object localization is a critical challenge for robots, requiring efficient exploration of partially observable environments. However, state-of-the-art approaches either struggle to generalize beyond demonstration datasets (e.g., imitation learning methods) or fail to generate physically grounded actions (e.g., VLMs). To address these limitations, we introduce WoMAP (World Models for Active Perception): a recipe for training open-vocabulary object localization policies that: (i) uses a Gaussian Splatting-based real-to-sim-to-real pipeline for scalable data generation"},"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":"2506.01600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-02T12:35:14Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"8f7a2aa0b6021d5f3a561bff421f252466feb388759e18fc92fd78b79eb89b56","abstract_canon_sha256":"4c7f020c7720a3f84ed4bcf994eac315a3a76a9470ba8184f9207449fae50cc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:16.527954Z","signature_b64":"aM+iW1REMc/w4hYzJqwKHL3neFh6qg259jlaG8YI4iIuk0dWIGeqOLQBBYeSSHpaEKGMNilKmQbyJjaZoaxfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68979806710ad8e985cc13c635da42c0c08747fd0166bff41a8ea12aa8e65cc7","last_reissued_at":"2026-07-05T11:14:16.527498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:16.527498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WoMAP: World Models For Embodied Open-Vocabulary Object Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Anirudha Majumdar, Emily Zhou, Jeremy Bao, Lihan Zha, Miyu Yamane, Ola Shorinwa, Tao Sun, Tenny Yin, Zhiting Mei","submitted_at":"2025-06-02T12:35:14Z","abstract_excerpt":"Language-instructed active object localization is a critical challenge for robots, requiring efficient exploration of partially observable environments. However, state-of-the-art approaches either struggle to generalize beyond demonstration datasets (e.g., imitation learning methods) or fail to generate physically grounded actions (e.g., VLMs). To address these limitations, we introduce WoMAP (World Models for Active Perception): a recipe for training open-vocabulary object localization policies that: (i) uses a Gaussian Splatting-based real-to-sim-to-real pipeline for scalable data generation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01600","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/2506.01600/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":"2506.01600","created_at":"2026-07-05T11:14:16.527557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01600v1","created_at":"2026-07-05T11:14:16.527557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01600","created_at":"2026-07-05T11:14:16.527557+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCLZQBTRBLMO","created_at":"2026-07-05T11:14:16.527557+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCLZQBTRBLMOTBOM","created_at":"2026-07-05T11:14:16.527557+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCLZQBTR","created_at":"2026-07-05T11:14:16.527557+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00836","citing_title":"From World Models to World Action Models: A Concise Tutorial for Robotics","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00836","citing_title":"From World Models to World Action Models: A Concise Tutorial for Robotics","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NCLZQBTRBLMOTBOMCPDDLWSCYD","json":"https://pith.science/pith/NCLZQBTRBLMOTBOMCPDDLWSCYD.json","graph_json":"https://pith.science/api/pith-number/NCLZQBTRBLMOTBOMCPDDLWSCYD/graph.json","events_json":"https://pith.science/api/pith-number/NCLZQBTRBLMOTBOMCPDDLWSCYD/events.json","paper":"https://pith.science/paper/NCLZQBTR"},"agent_actions":{"view_html":"https://pith.science/pith/NCLZQBTRBLMOTBOMCPDDLWSCYD","download_json":"https://pith.science/pith/NCLZQBTRBLMOTBOMCPDDLWSCYD.json","view_paper":"https://pith.science/paper/NCLZQBTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01600&json=true","fetch_graph":"https://pith.science/api/pith-number/NCLZQBTRBLMOTBOMCPDDLWSCYD/graph.json","fetch_events":"https://pith.science/api/pith-number/NCLZQBTRBLMOTBOMCPDDLWSCYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCLZQBTRBLMOTBOMCPDDLWSCYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCLZQBTRBLMOTBOMCPDDLWSCYD/action/storage_attestation","attest_author":"https://pith.science/pith/NCLZQBTRBLMOTBOMCPDDLWSCYD/action/author_attestation","sign_citation":"https://pith.science/pith/NCLZQBTRBLMOTBOMCPDDLWSCYD/action/citation_signature","submit_replication":"https://pith.science/pith/NCLZQBTRBLMOTBOMCPDDLWSCYD/action/replication_record"}},"created_at":"2026-07-05T11:14:16.527557+00:00","updated_at":"2026-07-05T11:14:16.527557+00:00"}