{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JS7DRHU4LWHEZU5BIJ22YVNFHN","short_pith_number":"pith:JS7DRHU4","schema_version":"1.0","canonical_sha256":"4cbe389e9c5d8e4cd3a14275ac55a53b58fcd7640d8e92a47db80bf71cc3af26","source":{"kind":"arxiv","id":"2605.18603","version":1},"attestation_state":"computed","paper":{"title":"Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wei, Fangzhen Lin, Haozhe Wang, Wenhu Chen, Yuhuan Wu","submitted_at":"2026-05-18T16:13:09Z","abstract_excerpt":"Vision-Language Models (VLMs) deployed as situated agents in high-resolution visual environments require active perception -- the ability to dynamically decide where to look through operations like zooming, cropping, and panning. However, current training paradigms produce models that mimic the surface form of such operations without functionally depending on their outputs, a phenomenon we term lazy perception. We trace this to a fundamental learning asymmetry: when coarse global views combined with language priors suffice for moderate accuracy, the model has no incentive to learn harder multi"},"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":"2605.18603","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T16:13:09Z","cross_cats_sorted":[],"title_canon_sha256":"fa92389bdb5e577c9079ccc59e34c15550b7291e1276202af6bad989a674e672","abstract_canon_sha256":"dc6a973876c5f83903f458a6e2bac6a9621f4d7e8f596ed29aa1ae0df14cb504"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:10.434270Z","signature_b64":"VaB3jC396lctL5j/f+7uC2T+MoqcJ3FREyQ5mQKw94dZhkjJ80MD6r81EHrnG601zG/B301evzcxHAPKzMLoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cbe389e9c5d8e4cd3a14275ac55a53b58fcd7640d8e92a47db80bf71cc3af26","last_reissued_at":"2026-05-20T00:06:10.433333Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:10.433333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wei, Fangzhen Lin, Haozhe Wang, Wenhu Chen, Yuhuan Wu","submitted_at":"2026-05-18T16:13:09Z","abstract_excerpt":"Vision-Language Models (VLMs) deployed as situated agents in high-resolution visual environments require active perception -- the ability to dynamically decide where to look through operations like zooming, cropping, and panning. However, current training paradigms produce models that mimic the surface form of such operations without functionally depending on their outputs, a phenomenon we term lazy perception. We trace this to a fundamental learning asymmetry: when coarse global views combined with language priors suffice for moderate accuracy, the model has no incentive to learn harder multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18603","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/2605.18603/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.251267Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"71b00cf17528ddf8feae009326ee92883586ce5c40bb19caa581f6ad8889ab39"},"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":"2605.18603","created_at":"2026-05-20T00:06:10.433482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18603v1","created_at":"2026-05-20T00:06:10.433482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18603","created_at":"2026-05-20T00:06:10.433482+00:00"},{"alias_kind":"pith_short_12","alias_value":"JS7DRHU4LWHE","created_at":"2026-05-20T00:06:10.433482+00:00"},{"alias_kind":"pith_short_16","alias_value":"JS7DRHU4LWHEZU5B","created_at":"2026-05-20T00:06:10.433482+00:00"},{"alias_kind":"pith_short_8","alias_value":"JS7DRHU4","created_at":"2026-05-20T00:06:10.433482+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/JS7DRHU4LWHEZU5BIJ22YVNFHN","json":"https://pith.science/pith/JS7DRHU4LWHEZU5BIJ22YVNFHN.json","graph_json":"https://pith.science/api/pith-number/JS7DRHU4LWHEZU5BIJ22YVNFHN/graph.json","events_json":"https://pith.science/api/pith-number/JS7DRHU4LWHEZU5BIJ22YVNFHN/events.json","paper":"https://pith.science/paper/JS7DRHU4"},"agent_actions":{"view_html":"https://pith.science/pith/JS7DRHU4LWHEZU5BIJ22YVNFHN","download_json":"https://pith.science/pith/JS7DRHU4LWHEZU5BIJ22YVNFHN.json","view_paper":"https://pith.science/paper/JS7DRHU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18603&json=true","fetch_graph":"https://pith.science/api/pith-number/JS7DRHU4LWHEZU5BIJ22YVNFHN/graph.json","fetch_events":"https://pith.science/api/pith-number/JS7DRHU4LWHEZU5BIJ22YVNFHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JS7DRHU4LWHEZU5BIJ22YVNFHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JS7DRHU4LWHEZU5BIJ22YVNFHN/action/storage_attestation","attest_author":"https://pith.science/pith/JS7DRHU4LWHEZU5BIJ22YVNFHN/action/author_attestation","sign_citation":"https://pith.science/pith/JS7DRHU4LWHEZU5BIJ22YVNFHN/action/citation_signature","submit_replication":"https://pith.science/pith/JS7DRHU4LWHEZU5BIJ22YVNFHN/action/replication_record"}},"created_at":"2026-05-20T00:06:10.433482+00:00","updated_at":"2026-05-20T00:06:10.433482+00:00"}