{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JZPCR2W2A2H7QL7DGYEIPDJL2W","short_pith_number":"pith:JZPCR2W2","schema_version":"1.0","canonical_sha256":"4e5e28eada068ff82fe33608878d2bd5b9aac9d8a69589f0766d453db04e9f0d","source":{"kind":"arxiv","id":"2606.00562","version":1},"attestation_state":"computed","paper":{"title":"DeepLatent: Think with Images via Parallel Latent Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongchen Lu, Huo Cao, Mao Shu, Zhimo Li","submitted_at":"2026-05-30T06:33:24Z","abstract_excerpt":"The emerging paradigm of \"thinking with images\" embeds visual states into intermediate reasoning steps, defining a new frontier for Vision-Language Models. Existing approaches diverge along two lines. Tool-assisted methods apply explicit visual operations but suffer from high latency and restricted manipulation types. Latent reasoning methods autoregressively produce implicit visual states, but underperform tool-assisted methods, and their latent tokens fail to capture effective visual information. In this work, we propose DeepLatent, a parallel framework for latent visual reasoning. First, we"},"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":"2606.00562","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T06:33:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"99b5dbda7b00a29b5253ee9a1e146f1a11402dc5db7dba12f0bf09c533e59dfa","abstract_canon_sha256":"5d54f894c8952fddd54cff5335e942a901b64bf667366cabb5083474ced05fe3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:58.339264Z","signature_b64":"uklITKOoV1Ho61FJjliV12zRE+nRGACUcVdFXk28kM7PWhiSTX+sdWcaleFEqLly8PPONYJlBKlT1b5ef3OVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e5e28eada068ff82fe33608878d2bd5b9aac9d8a69589f0766d453db04e9f0d","last_reissued_at":"2026-06-02T01:03:58.338874Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:58.338874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepLatent: Think with Images via Parallel Latent Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongchen Lu, Huo Cao, Mao Shu, Zhimo Li","submitted_at":"2026-05-30T06:33:24Z","abstract_excerpt":"The emerging paradigm of \"thinking with images\" embeds visual states into intermediate reasoning steps, defining a new frontier for Vision-Language Models. Existing approaches diverge along two lines. Tool-assisted methods apply explicit visual operations but suffer from high latency and restricted manipulation types. Latent reasoning methods autoregressively produce implicit visual states, but underperform tool-assisted methods, and their latent tokens fail to capture effective visual information. In this work, we propose DeepLatent, a parallel framework for latent visual reasoning. First, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00562","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/2606.00562/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":"2606.00562","created_at":"2026-06-02T01:03:58.338929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00562v1","created_at":"2026-06-02T01:03:58.338929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00562","created_at":"2026-06-02T01:03:58.338929+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZPCR2W2A2H7","created_at":"2026-06-02T01:03:58.338929+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZPCR2W2A2H7QL7D","created_at":"2026-06-02T01:03:58.338929+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZPCR2W2","created_at":"2026-06-02T01:03:58.338929+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/JZPCR2W2A2H7QL7DGYEIPDJL2W","json":"https://pith.science/pith/JZPCR2W2A2H7QL7DGYEIPDJL2W.json","graph_json":"https://pith.science/api/pith-number/JZPCR2W2A2H7QL7DGYEIPDJL2W/graph.json","events_json":"https://pith.science/api/pith-number/JZPCR2W2A2H7QL7DGYEIPDJL2W/events.json","paper":"https://pith.science/paper/JZPCR2W2"},"agent_actions":{"view_html":"https://pith.science/pith/JZPCR2W2A2H7QL7DGYEIPDJL2W","download_json":"https://pith.science/pith/JZPCR2W2A2H7QL7DGYEIPDJL2W.json","view_paper":"https://pith.science/paper/JZPCR2W2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00562&json=true","fetch_graph":"https://pith.science/api/pith-number/JZPCR2W2A2H7QL7DGYEIPDJL2W/graph.json","fetch_events":"https://pith.science/api/pith-number/JZPCR2W2A2H7QL7DGYEIPDJL2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZPCR2W2A2H7QL7DGYEIPDJL2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZPCR2W2A2H7QL7DGYEIPDJL2W/action/storage_attestation","attest_author":"https://pith.science/pith/JZPCR2W2A2H7QL7DGYEIPDJL2W/action/author_attestation","sign_citation":"https://pith.science/pith/JZPCR2W2A2H7QL7DGYEIPDJL2W/action/citation_signature","submit_replication":"https://pith.science/pith/JZPCR2W2A2H7QL7DGYEIPDJL2W/action/replication_record"}},"created_at":"2026-06-02T01:03:58.338929+00:00","updated_at":"2026-06-02T01:03:58.338929+00:00"}