{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H5MLURJXNKPJ3LLPQHQ3ZYIVWG","short_pith_number":"pith:H5MLURJX","schema_version":"1.0","canonical_sha256":"3f58ba45376a9e9dad6f81e1bce115b186e33ea17732b48b31420b416542c5bf","source":{"kind":"arxiv","id":"2409.17641","version":2},"attestation_state":"computed","paper":{"title":"Scene Exploration by Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Amir Ghalamzan, Frank Guerin, Samuel Carter, Venkatesh Sripada","submitted_at":"2024-09-26T08:44:49Z","abstract_excerpt":"Active perception enables robots to dynamically gather information by adjusting their viewpoints, a crucial capability for interacting with complex, partially observable environments. In this paper, we present AP-VLM, a novel framework that combines active perception with a Vision-Language Model (VLM) to guide robotic exploration and answer semantic queries. Using a 3D virtual grid overlaid on the scene and orientation adjustments, AP-VLM allows a robotic manipulator to intelligently select optimal viewpoints and orientations to resolve challenging tasks, such as identifying objects in occlude"},"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":"2409.17641","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-26T08:44:49Z","cross_cats_sorted":[],"title_canon_sha256":"b241cc9e5f01e1ac60274b3b6f628f99ff45ac18a5daf6bd5bd3741412ae25c0","abstract_canon_sha256":"e0a14244dc89033708ca33fa66db1b6ec15d61650bdf0fabb33f6f3175a74e9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:14.275864Z","signature_b64":"3EsMYS76L/+tG4bNcgY+uvOTqfrWAZHCCkgnCkZAGlh9px0vzCeXlF+gf5LB+F1NLPcMEiqHYtT4tf3ScAZ4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f58ba45376a9e9dad6f81e1bce115b186e33ea17732b48b31420b416542c5bf","last_reissued_at":"2026-07-05T11:18:14.275354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:14.275354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scene Exploration by Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Amir Ghalamzan, Frank Guerin, Samuel Carter, Venkatesh Sripada","submitted_at":"2024-09-26T08:44:49Z","abstract_excerpt":"Active perception enables robots to dynamically gather information by adjusting their viewpoints, a crucial capability for interacting with complex, partially observable environments. In this paper, we present AP-VLM, a novel framework that combines active perception with a Vision-Language Model (VLM) to guide robotic exploration and answer semantic queries. Using a 3D virtual grid overlaid on the scene and orientation adjustments, AP-VLM allows a robotic manipulator to intelligently select optimal viewpoints and orientations to resolve challenging tasks, such as identifying objects in occlude"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17641","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/2409.17641/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":"2409.17641","created_at":"2026-07-05T11:18:14.275423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.17641v2","created_at":"2026-07-05T11:18:14.275423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17641","created_at":"2026-07-05T11:18:14.275423+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5MLURJXNKPJ","created_at":"2026-07-05T11:18:14.275423+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5MLURJXNKPJ3LLP","created_at":"2026-07-05T11:18:14.275423+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5MLURJX","created_at":"2026-07-05T11:18:14.275423+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.20323","citing_title":"PhysMem: Scaling Test-Time Memory for Embodied Physical Reasoning","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5MLURJXNKPJ3LLPQHQ3ZYIVWG","json":"https://pith.science/pith/H5MLURJXNKPJ3LLPQHQ3ZYIVWG.json","graph_json":"https://pith.science/api/pith-number/H5MLURJXNKPJ3LLPQHQ3ZYIVWG/graph.json","events_json":"https://pith.science/api/pith-number/H5MLURJXNKPJ3LLPQHQ3ZYIVWG/events.json","paper":"https://pith.science/paper/H5MLURJX"},"agent_actions":{"view_html":"https://pith.science/pith/H5MLURJXNKPJ3LLPQHQ3ZYIVWG","download_json":"https://pith.science/pith/H5MLURJXNKPJ3LLPQHQ3ZYIVWG.json","view_paper":"https://pith.science/paper/H5MLURJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.17641&json=true","fetch_graph":"https://pith.science/api/pith-number/H5MLURJXNKPJ3LLPQHQ3ZYIVWG/graph.json","fetch_events":"https://pith.science/api/pith-number/H5MLURJXNKPJ3LLPQHQ3ZYIVWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5MLURJXNKPJ3LLPQHQ3ZYIVWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5MLURJXNKPJ3LLPQHQ3ZYIVWG/action/storage_attestation","attest_author":"https://pith.science/pith/H5MLURJXNKPJ3LLPQHQ3ZYIVWG/action/author_attestation","sign_citation":"https://pith.science/pith/H5MLURJXNKPJ3LLPQHQ3ZYIVWG/action/citation_signature","submit_replication":"https://pith.science/pith/H5MLURJXNKPJ3LLPQHQ3ZYIVWG/action/replication_record"}},"created_at":"2026-07-05T11:18:14.275423+00:00","updated_at":"2026-07-05T11:18:14.275423+00:00"}