{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UQOFNDQ43F6S46GMQAFD35XQ3G","short_pith_number":"pith:UQOFNDQ4","schema_version":"1.0","canonical_sha256":"a41c568e1cd97d2e78cc800a3df6f0d99773b0ac14e659fc1217b9cd908141e4","source":{"kind":"arxiv","id":"2606.01247","version":1},"attestation_state":"computed","paper":{"title":"Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Hao Chen, Hengyu Zhao, Ke Liu, Linhao Zhong, Liyang Li, Muzhi Zhu, Zhiyue Zhao","submitted_at":"2026-05-31T14:00:10Z","abstract_excerpt":"Humans can reproduce the viewpoint specified by a target image through active head and body motion, yet spatial intelligence in foundation models has largely been studied as passive understanding of pre-collected observations. We introduce Target Viewpoint Reproduction (TVR) -- an active task where an agent adjusts its viewpoint in a 3D environment until its observation matches a given target image -- and TVRBench, an indoor-simulation benchmark spanning scene scale and target-view visual richness. TVR is far from solved: on the evaluation split, the strongest open-source and closed-source mod"},"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":"2606.01247","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T14:00:10Z","cross_cats_sorted":[],"title_canon_sha256":"050f784a098761bc7940c829ee7b1417b60a129239924c68482ca656f7245606","abstract_canon_sha256":"c5e7b544757a2aa50f987650644a214488add20786341e53ed85d3070250a324"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:27.884516Z","signature_b64":"kdsMqexJfPsjgV34hZyAMQnD0THY0SeLRNTX5sexznCceXW3sDGO+H5BnxkmQIBr5bn1VZfV90h5mXQBfphSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a41c568e1cd97d2e78cc800a3df6f0d99773b0ac14e659fc1217b9cd908141e4","last_reissued_at":"2026-06-02T02:04:27.884065Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:27.884065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Hao Chen, Hengyu Zhao, Ke Liu, Linhao Zhong, Liyang Li, Muzhi Zhu, Zhiyue Zhao","submitted_at":"2026-05-31T14:00:10Z","abstract_excerpt":"Humans can reproduce the viewpoint specified by a target image through active head and body motion, yet spatial intelligence in foundation models has largely been studied as passive understanding of pre-collected observations. We introduce Target Viewpoint Reproduction (TVR) -- an active task where an agent adjusts its viewpoint in a 3D environment until its observation matches a given target image -- and TVRBench, an indoor-simulation benchmark spanning scene scale and target-view visual richness. TVR is far from solved: on the evaluation split, the strongest open-source and closed-source mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01247","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/2606.01247/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":"2606.01247","created_at":"2026-06-02T02:04:27.884142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01247v1","created_at":"2026-06-02T02:04:27.884142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01247","created_at":"2026-06-02T02:04:27.884142+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQOFNDQ43F6S","created_at":"2026-06-02T02:04:27.884142+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQOFNDQ43F6S46GM","created_at":"2026-06-02T02:04:27.884142+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQOFNDQ4","created_at":"2026-06-02T02:04:27.884142+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UQOFNDQ43F6S46GMQAFD35XQ3G","json":"https://pith.science/pith/UQOFNDQ43F6S46GMQAFD35XQ3G.json","graph_json":"https://pith.science/api/pith-number/UQOFNDQ43F6S46GMQAFD35XQ3G/graph.json","events_json":"https://pith.science/api/pith-number/UQOFNDQ43F6S46GMQAFD35XQ3G/events.json","paper":"https://pith.science/paper/UQOFNDQ4"},"agent_actions":{"view_html":"https://pith.science/pith/UQOFNDQ43F6S46GMQAFD35XQ3G","download_json":"https://pith.science/pith/UQOFNDQ43F6S46GMQAFD35XQ3G.json","view_paper":"https://pith.science/paper/UQOFNDQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01247&json=true","fetch_graph":"https://pith.science/api/pith-number/UQOFNDQ43F6S46GMQAFD35XQ3G/graph.json","fetch_events":"https://pith.science/api/pith-number/UQOFNDQ43F6S46GMQAFD35XQ3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQOFNDQ43F6S46GMQAFD35XQ3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQOFNDQ43F6S46GMQAFD35XQ3G/action/storage_attestation","attest_author":"https://pith.science/pith/UQOFNDQ43F6S46GMQAFD35XQ3G/action/author_attestation","sign_citation":"https://pith.science/pith/UQOFNDQ43F6S46GMQAFD35XQ3G/action/citation_signature","submit_replication":"https://pith.science/pith/UQOFNDQ43F6S46GMQAFD35XQ3G/action/replication_record"}},"created_at":"2026-06-02T02:04:27.884142+00:00","updated_at":"2026-06-02T02:04:27.884142+00:00"}