{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PQOO4ZBP5PLSMQOJJVDB5H6MP4","short_pith_number":"pith:PQOO4ZBP","schema_version":"1.0","canonical_sha256":"7c1cee642febd72641c94d461e9fcc7f0cff6f38ead878a473128f88066a6b4a","source":{"kind":"arxiv","id":"2606.01287","version":1},"attestation_state":"computed","paper":{"title":"Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Garvin Guo, Huaxing Liu, Shuai Dong, Shuai Li, Xiang Wang, Xinpei Zhao, Yu Chen","submitted_at":"2026-05-31T15:14:53Z","abstract_excerpt":"Recent latent visual reasoning methods achieve substantial gains by inserting continuous latent tokens into multimodal language models. These gains are commonly attributed to the tokens encoding visual evidence; recent analyses, however, reveal a paradox: the tokens are loosely tied to the image and contribute little to the answer. Critically, these analyses treat latent tokens as a single unit, obscuring the true source of the gains. We therefore decompose latent tokens into three testable components: latent slots, boundary markers, and format, and develop a state-of-the-art method as a probe"},"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":"2606.01287","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T15:14:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c198c2b0e2840cee8e7c5e7c5ef240a18f1daa09c9724a2160ec5093dc9837d","abstract_canon_sha256":"a656ddde5fdfad30fde403e0bed81b0b82731d31dae428bfd006547b79491add"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:29.037491Z","signature_b64":"vk/poYaNHVlCsuC9otTyWLap6SyRXBhpsB18R9urZ7sO7VoDCZS2m5xgb+XRq+pG/Kuh4q0pTeeA4UrItqLJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c1cee642febd72641c94d461e9fcc7f0cff6f38ead878a473128f88066a6b4a","last_reissued_at":"2026-06-02T02:04:29.036738Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:29.036738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Garvin Guo, Huaxing Liu, Shuai Dong, Shuai Li, Xiang Wang, Xinpei Zhao, Yu Chen","submitted_at":"2026-05-31T15:14:53Z","abstract_excerpt":"Recent latent visual reasoning methods achieve substantial gains by inserting continuous latent tokens into multimodal language models. These gains are commonly attributed to the tokens encoding visual evidence; recent analyses, however, reveal a paradox: the tokens are loosely tied to the image and contribute little to the answer. Critically, these analyses treat latent tokens as a single unit, obscuring the true source of the gains. We therefore decompose latent tokens into three testable components: latent slots, boundary markers, and format, and develop a state-of-the-art method as a probe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01287","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/2606.01287/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":"2606.01287","created_at":"2026-06-02T02:04:29.036844+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01287v1","created_at":"2026-06-02T02:04:29.036844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01287","created_at":"2026-06-02T02:04:29.036844+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQOO4ZBP5PLS","created_at":"2026-06-02T02:04:29.036844+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQOO4ZBP5PLSMQOJ","created_at":"2026-06-02T02:04:29.036844+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQOO4ZBP","created_at":"2026-06-02T02:04:29.036844+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/PQOO4ZBP5PLSMQOJJVDB5H6MP4","json":"https://pith.science/pith/PQOO4ZBP5PLSMQOJJVDB5H6MP4.json","graph_json":"https://pith.science/api/pith-number/PQOO4ZBP5PLSMQOJJVDB5H6MP4/graph.json","events_json":"https://pith.science/api/pith-number/PQOO4ZBP5PLSMQOJJVDB5H6MP4/events.json","paper":"https://pith.science/paper/PQOO4ZBP"},"agent_actions":{"view_html":"https://pith.science/pith/PQOO4ZBP5PLSMQOJJVDB5H6MP4","download_json":"https://pith.science/pith/PQOO4ZBP5PLSMQOJJVDB5H6MP4.json","view_paper":"https://pith.science/paper/PQOO4ZBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01287&json=true","fetch_graph":"https://pith.science/api/pith-number/PQOO4ZBP5PLSMQOJJVDB5H6MP4/graph.json","fetch_events":"https://pith.science/api/pith-number/PQOO4ZBP5PLSMQOJJVDB5H6MP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQOO4ZBP5PLSMQOJJVDB5H6MP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQOO4ZBP5PLSMQOJJVDB5H6MP4/action/storage_attestation","attest_author":"https://pith.science/pith/PQOO4ZBP5PLSMQOJJVDB5H6MP4/action/author_attestation","sign_citation":"https://pith.science/pith/PQOO4ZBP5PLSMQOJJVDB5H6MP4/action/citation_signature","submit_replication":"https://pith.science/pith/PQOO4ZBP5PLSMQOJJVDB5H6MP4/action/replication_record"}},"created_at":"2026-06-02T02:04:29.036844+00:00","updated_at":"2026-06-02T02:04:29.036844+00:00"}