{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4HK7HXV5WEFPEQCZ2QNCIPCK3Z","short_pith_number":"pith:4HK7HXV5","schema_version":"1.0","canonical_sha256":"e1d5f3debdb10af24059d41a243c4ade73e4d61263c9b60d69d1fc73df0e955f","source":{"kind":"arxiv","id":"2603.22570","version":2},"attestation_state":"computed","paper":{"title":"CanViT: Toward Active-Vision Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Audrey Durand, B. Suresh Krishna, Sabrina Du, Yoha\\\"i-Eliel Berreby","submitted_at":"2026-03-23T21:05:21Z","abstract_excerpt":"Active computer vision promises efficient, biologically plausible perception through sequential, localized glimpses, but lacks scalable general-purpose architectures and pretraining pipelines, leaving Active-Vision Foundation Models (AVFMs) underexplored. We introduce CanViT, the first task- and policy-agnostic AVFM. CanViT uses scene-relative RoPE to bind a retinotopic Vision Transformer backbone and a spatiotopic scene-wide latent workspace, the canvas. Efficient interaction with this high-capacity working memory is supported by Canvas Attention, a novel asymmetric cross-attention mechanism."},"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":"2603.22570","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-23T21:05:21Z","cross_cats_sorted":[],"title_canon_sha256":"c560076a56d0a7b481897abdf6cb63e37943dac413446ad248154750bd8dfa11","abstract_canon_sha256":"071e756fc8c5eb19c7ad9e7e4f3ae17ed7353b8f604e0b6107c83949045fffc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:09.132085Z","signature_b64":"dzHxzNQ6UjAqC3U1PGycjDqYEzJQ7w/7nkWMPoRuVDuAxch6GaScTSuLnnuTqZS4iqTIlDoQOXZizrRrkC+jAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1d5f3debdb10af24059d41a243c4ade73e4d61263c9b60d69d1fc73df0e955f","last_reissued_at":"2026-05-20T00:03:09.131194Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:09.131194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CanViT: Toward Active-Vision Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Audrey Durand, B. Suresh Krishna, Sabrina Du, Yoha\\\"i-Eliel Berreby","submitted_at":"2026-03-23T21:05:21Z","abstract_excerpt":"Active computer vision promises efficient, biologically plausible perception through sequential, localized glimpses, but lacks scalable general-purpose architectures and pretraining pipelines, leaving Active-Vision Foundation Models (AVFMs) underexplored. We introduce CanViT, the first task- and policy-agnostic AVFM. CanViT uses scene-relative RoPE to bind a retinotopic Vision Transformer backbone and a spatiotopic scene-wide latent workspace, the canvas. Efficient interaction with this high-capacity working memory is supported by Canvas Attention, a novel asymmetric cross-attention mechanism."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.22570","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/2603.22570/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":"2603.22570","created_at":"2026-05-20T00:03:09.131340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.22570v2","created_at":"2026-05-20T00:03:09.131340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.22570","created_at":"2026-05-20T00:03:09.131340+00:00"},{"alias_kind":"pith_short_12","alias_value":"4HK7HXV5WEFP","created_at":"2026-05-20T00:03:09.131340+00:00"},{"alias_kind":"pith_short_16","alias_value":"4HK7HXV5WEFPEQCZ","created_at":"2026-05-20T00:03:09.131340+00:00"},{"alias_kind":"pith_short_8","alias_value":"4HK7HXV5","created_at":"2026-05-20T00:03:09.131340+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/4HK7HXV5WEFPEQCZ2QNCIPCK3Z","json":"https://pith.science/pith/4HK7HXV5WEFPEQCZ2QNCIPCK3Z.json","graph_json":"https://pith.science/api/pith-number/4HK7HXV5WEFPEQCZ2QNCIPCK3Z/graph.json","events_json":"https://pith.science/api/pith-number/4HK7HXV5WEFPEQCZ2QNCIPCK3Z/events.json","paper":"https://pith.science/paper/4HK7HXV5"},"agent_actions":{"view_html":"https://pith.science/pith/4HK7HXV5WEFPEQCZ2QNCIPCK3Z","download_json":"https://pith.science/pith/4HK7HXV5WEFPEQCZ2QNCIPCK3Z.json","view_paper":"https://pith.science/paper/4HK7HXV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.22570&json=true","fetch_graph":"https://pith.science/api/pith-number/4HK7HXV5WEFPEQCZ2QNCIPCK3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/4HK7HXV5WEFPEQCZ2QNCIPCK3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4HK7HXV5WEFPEQCZ2QNCIPCK3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4HK7HXV5WEFPEQCZ2QNCIPCK3Z/action/storage_attestation","attest_author":"https://pith.science/pith/4HK7HXV5WEFPEQCZ2QNCIPCK3Z/action/author_attestation","sign_citation":"https://pith.science/pith/4HK7HXV5WEFPEQCZ2QNCIPCK3Z/action/citation_signature","submit_replication":"https://pith.science/pith/4HK7HXV5WEFPEQCZ2QNCIPCK3Z/action/replication_record"}},"created_at":"2026-05-20T00:03:09.131340+00:00","updated_at":"2026-05-20T00:03:09.131340+00:00"}