{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SP6QPJRCEO4H6SKPYLDQUGFXHQ","short_pith_number":"pith:SP6QPJRC","schema_version":"1.0","canonical_sha256":"93fd07a62223b87f494fc2c70a18b73c2f2b15562ebd0eb924dd005aff914394","source":{"kind":"arxiv","id":"2606.07861","version":1},"attestation_state":"computed","paper":{"title":"The Last Visible Pixel: Probing Fine-Scale Perception in Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lama Sleem, Lujun Li, Niccolo Gentile, Radu State, Wenbo Wu, Yangjie Xu, Yewei Song","submitted_at":"2026-06-05T21:49:34Z","abstract_excerpt":"Recent vision-language models (VLMs) excel at multimodal understanding and reasoning, yet their fine-grained visual perception remains underexplored. A natural extension of ``How many r are there in Strawberry?'' asks: how small a visual pattern can a VLM reliably perceive? As such, we introduce FineSightBench, a new benchmark that systematically probes this limit by separating perception tasks (pixel-level recognition of letters, shapes, objects) from reasoning tasks (spatial reasoning, counting, ordering over small targets) across controlled scales of 4--48px. Through comprehensive experimen"},"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":"2606.07861","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T21:49:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"acdc4de64023bf13e1de7f24c331e8e01072d25d14635722f65f725c2c54c08f","abstract_canon_sha256":"7596755decb097a3cea438a3a943fffa719f31ff3c8544078f2262e00f2e08c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:54.023573Z","signature_b64":"z5lbFJE+x793z0gAzKDMgm6sy25SzDqzDvhlLh0HLr7rbd1RQZ6a7rl9kWQTZ4O/ziLjVy0YMCmsTEWdcyNGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93fd07a62223b87f494fc2c70a18b73c2f2b15562ebd0eb924dd005aff914394","last_reissued_at":"2026-06-09T01:04:54.023137Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:54.023137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Last Visible Pixel: Probing Fine-Scale Perception in Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lama Sleem, Lujun Li, Niccolo Gentile, Radu State, Wenbo Wu, Yangjie Xu, Yewei Song","submitted_at":"2026-06-05T21:49:34Z","abstract_excerpt":"Recent vision-language models (VLMs) excel at multimodal understanding and reasoning, yet their fine-grained visual perception remains underexplored. A natural extension of ``How many r are there in Strawberry?'' asks: how small a visual pattern can a VLM reliably perceive? As such, we introduce FineSightBench, a new benchmark that systematically probes this limit by separating perception tasks (pixel-level recognition of letters, shapes, objects) from reasoning tasks (spatial reasoning, counting, ordering over small targets) across controlled scales of 4--48px. Through comprehensive experimen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07861","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/2606.07861/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":"2606.07861","created_at":"2026-06-09T01:04:54.023209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07861v1","created_at":"2026-06-09T01:04:54.023209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07861","created_at":"2026-06-09T01:04:54.023209+00:00"},{"alias_kind":"pith_short_12","alias_value":"SP6QPJRCEO4H","created_at":"2026-06-09T01:04:54.023209+00:00"},{"alias_kind":"pith_short_16","alias_value":"SP6QPJRCEO4H6SKP","created_at":"2026-06-09T01:04:54.023209+00:00"},{"alias_kind":"pith_short_8","alias_value":"SP6QPJRC","created_at":"2026-06-09T01:04:54.023209+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/SP6QPJRCEO4H6SKPYLDQUGFXHQ","json":"https://pith.science/pith/SP6QPJRCEO4H6SKPYLDQUGFXHQ.json","graph_json":"https://pith.science/api/pith-number/SP6QPJRCEO4H6SKPYLDQUGFXHQ/graph.json","events_json":"https://pith.science/api/pith-number/SP6QPJRCEO4H6SKPYLDQUGFXHQ/events.json","paper":"https://pith.science/paper/SP6QPJRC"},"agent_actions":{"view_html":"https://pith.science/pith/SP6QPJRCEO4H6SKPYLDQUGFXHQ","download_json":"https://pith.science/pith/SP6QPJRCEO4H6SKPYLDQUGFXHQ.json","view_paper":"https://pith.science/paper/SP6QPJRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07861&json=true","fetch_graph":"https://pith.science/api/pith-number/SP6QPJRCEO4H6SKPYLDQUGFXHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SP6QPJRCEO4H6SKPYLDQUGFXHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SP6QPJRCEO4H6SKPYLDQUGFXHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SP6QPJRCEO4H6SKPYLDQUGFXHQ/action/storage_attestation","attest_author":"https://pith.science/pith/SP6QPJRCEO4H6SKPYLDQUGFXHQ/action/author_attestation","sign_citation":"https://pith.science/pith/SP6QPJRCEO4H6SKPYLDQUGFXHQ/action/citation_signature","submit_replication":"https://pith.science/pith/SP6QPJRCEO4H6SKPYLDQUGFXHQ/action/replication_record"}},"created_at":"2026-06-09T01:04:54.023209+00:00","updated_at":"2026-06-09T01:04:54.023209+00:00"}