{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HQKO4CR35GDUTH465H5BL5CDXN","short_pith_number":"pith:HQKO4CR3","canonical_record":{"source":{"id":"2605.18641","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T16:46:02Z","cross_cats_sorted":[],"title_canon_sha256":"e1af2038767b1e91a24522a642d32fc223dc7802b9e2a807805d7836e28a7557","abstract_canon_sha256":"1bd97e298e23e28d5b0698720dcaa22bbd2dcbcaeab3332cb6a0e883e75be7c3"},"schema_version":"1.0"},"canonical_sha256":"3c14ee0a3be987499f9ee9fa15f443bb4f6b14f86b67a560de3a63a037ce74a7","source":{"kind":"arxiv","id":"2605.18641","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18641","created_at":"2026-05-20T00:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18641v1","created_at":"2026-05-20T00:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18641","created_at":"2026-05-20T00:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"HQKO4CR35GDU","created_at":"2026-05-20T00:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"HQKO4CR35GDUTH46","created_at":"2026-05-20T00:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"HQKO4CR3","created_at":"2026-05-20T00:06:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HQKO4CR35GDUTH465H5BL5CDXN","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18641","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T16:46:02Z","cross_cats_sorted":[],"title_canon_sha256":"e1af2038767b1e91a24522a642d32fc223dc7802b9e2a807805d7836e28a7557","abstract_canon_sha256":"1bd97e298e23e28d5b0698720dcaa22bbd2dcbcaeab3332cb6a0e883e75be7c3"},"schema_version":"1.0"},"canonical_sha256":"3c14ee0a3be987499f9ee9fa15f443bb4f6b14f86b67a560de3a63a037ce74a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:12.321300Z","signature_b64":"qgTVO0TZA03CdenV2EQ56qwVBPeULmJBTHqZJFZgFAR80JlBIvP0eQvk9kvgLdgFAcQuERLiU177hDUjzWjyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c14ee0a3be987499f9ee9fa15f443bb4f6b14f86b67a560de3a63a037ce74a7","last_reissued_at":"2026-05-20T00:06:12.320426Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:12.320426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18641","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jq1IrW6qnB98U3c3fgnduc8v/ngIFb+WD6pqzhlNiLlxGbFGz2UrnzsHjsVouQWH9/uvWb8BCG3Gr3Tg7ZCwCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:49:01.360504Z"},"content_sha256":"308a888b2b928ab178574b805de940826215f396d04ee52666dc05760d281d67","schema_version":"1.0","event_id":"sha256:308a888b2b928ab178574b805de940826215f396d04ee52666dc05760d281d67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HQKO4CR35GDUTH465H5BL5CDXN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Latent Visual Reasoning in Silence","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongyao Zhu, Han Jiang, Jianyang Gu, Raju Vatsavai, Saeed Vahidian, Tanya Berger-Wolf, Wei-Lun Chao, Xi Xiao, Yu Su, Zhen Wang","submitted_at":"2026-05-18T16:46:02Z","abstract_excerpt":"Latent visual reasoning involves visual evidence more directly in multimodal reasoning by inserting continuous latent tokens before textual generation. However, the necessity of these latent tokens at inference remains ambiguous. We show that replacing latent tokens with random noise or removing them completely causes little performance degradation across spatial reasoning benchmarks. Reinforcement learning further diminishes the latent generation behavior after post-training. These observations raise a central question: Is latent visual reasoning still meaningful? We argue that its value shou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18641","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/2605.18641/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.186037Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b427e842ef0c8534736a1fb2600c185e56ac8d234d08ab77fbff3105d1335cbe"},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kE/jriwdgd8buULEdidnGGfvYrYXOEYICTkF3G0xu+LA6z/s6vKzl7uRX8fArZJ1jZa64BneGE7qUE9f4tAuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:49:01.361176Z"},"content_sha256":"91ef6ff0ba9db51aacc933059a2e6d84fd52dbe429015b40f73f1ac225ea3ad9","schema_version":"1.0","event_id":"sha256:91ef6ff0ba9db51aacc933059a2e6d84fd52dbe429015b40f73f1ac225ea3ad9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HQKO4CR35GDUTH465H5BL5CDXN/bundle.json","state_url":"https://pith.science/pith/HQKO4CR35GDUTH465H5BL5CDXN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HQKO4CR35GDUTH465H5BL5CDXN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T23:49:01Z","links":{"resolver":"https://pith.science/pith/HQKO4CR35GDUTH465H5BL5CDXN","bundle":"https://pith.science/pith/HQKO4CR35GDUTH465H5BL5CDXN/bundle.json","state":"https://pith.science/pith/HQKO4CR35GDUTH465H5BL5CDXN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HQKO4CR35GDUTH465H5BL5CDXN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HQKO4CR35GDUTH465H5BL5CDXN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1bd97e298e23e28d5b0698720dcaa22bbd2dcbcaeab3332cb6a0e883e75be7c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T16:46:02Z","title_canon_sha256":"e1af2038767b1e91a24522a642d32fc223dc7802b9e2a807805d7836e28a7557"},"schema_version":"1.0","source":{"id":"2605.18641","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18641","created_at":"2026-05-20T00:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18641v1","created_at":"2026-05-20T00:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18641","created_at":"2026-05-20T00:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"HQKO4CR35GDU","created_at":"2026-05-20T00:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"HQKO4CR35GDUTH46","created_at":"2026-05-20T00:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"HQKO4CR3","created_at":"2026-05-20T00:06:12Z"}],"graph_snapshots":[{"event_id":"sha256:91ef6ff0ba9db51aacc933059a2e6d84fd52dbe429015b40f73f1ac225ea3ad9","target":"graph","created_at":"2026-05-20T00:06:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.186037Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18641/integrity.json","findings":[],"snapshot_sha256":"b427e842ef0c8534736a1fb2600c185e56ac8d234d08ab77fbff3105d1335cbe","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Latent visual reasoning involves visual evidence more directly in multimodal reasoning by inserting continuous latent tokens before textual generation. However, the necessity of these latent tokens at inference remains ambiguous. We show that replacing latent tokens with random noise or removing them completely causes little performance degradation across spatial reasoning benchmarks. Reinforcement learning further diminishes the latent generation behavior after post-training. These observations raise a central question: Is latent visual reasoning still meaningful? We argue that its value shou","authors_text":"Dongyao Zhu, Han Jiang, Jianyang Gu, Raju Vatsavai, Saeed Vahidian, Tanya Berger-Wolf, Wei-Lun Chao, Xi Xiao, Yu Su, Zhen Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T16:46:02Z","title":"Leveraging Latent Visual Reasoning in Silence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18641","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:308a888b2b928ab178574b805de940826215f396d04ee52666dc05760d281d67","target":"record","created_at":"2026-05-20T00:06:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1bd97e298e23e28d5b0698720dcaa22bbd2dcbcaeab3332cb6a0e883e75be7c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T16:46:02Z","title_canon_sha256":"e1af2038767b1e91a24522a642d32fc223dc7802b9e2a807805d7836e28a7557"},"schema_version":"1.0","source":{"id":"2605.18641","kind":"arxiv","version":1}},"canonical_sha256":"3c14ee0a3be987499f9ee9fa15f443bb4f6b14f86b67a560de3a63a037ce74a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c14ee0a3be987499f9ee9fa15f443bb4f6b14f86b67a560de3a63a037ce74a7","first_computed_at":"2026-05-20T00:06:12.320426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:12.320426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qgTVO0TZA03CdenV2EQ56qwVBPeULmJBTHqZJFZgFAR80JlBIvP0eQvk9kvgLdgFAcQuERLiU177hDUjzWjyCw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:12.321300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18641","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:308a888b2b928ab178574b805de940826215f396d04ee52666dc05760d281d67","sha256:91ef6ff0ba9db51aacc933059a2e6d84fd52dbe429015b40f73f1ac225ea3ad9"],"state_sha256":"02784ead95cf3c898bebac2201c51a82cab252e0bcea620a53075082dbe1ec35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bhPDvEnWgu1nZfchHCoGVdR1a5sUTRK36tY2MY2okausNWEylq6ys1DbBGYfRtUptmVwX/ng4Fh3NVnP1EQ+Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T23:49:01.365635Z","bundle_sha256":"cb893f6e0bc29b80805ee7c1ec2ff7065294e999176558d14044031c81432d70"}}