{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F3GXSEIWG6WGIXE7VTU34X37HP","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":"05208f75ad232e32c094afcc5f6c4444d05611558f4fbe0f9cda72eac771aeed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T11:59:15Z","title_canon_sha256":"37cfa63616864418177cb43e613425bf53bea3c831ddd06108474a1a3484c6ef"},"schema_version":"1.0","source":{"id":"2606.18974","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18974","created_at":"2026-06-19T16:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18974v1","created_at":"2026-06-19T16:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18974","created_at":"2026-06-19T16:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"F3GXSEIWG6WG","created_at":"2026-06-19T16:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"F3GXSEIWG6WGIXE7","created_at":"2026-06-19T16:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"F3GXSEIW","created_at":"2026-06-19T16:11:53Z"}],"graph_snapshots":[{"event_id":"sha256:6f628b2a7bab4e06e0152cd20a3728610abf9911a86abdfc81d954f7dc01eb19","target":"graph","created_at":"2026-06-19T16:11:53Z","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":[],"endpoint":"/pith/2606.18974/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unified multimodal models (UMMs) interleave generated ''visual thoughts'' (VTs) with text reasoning to improve spatial tasks. This incurs roughly an order-of-magnitude inference cost from multi-step diffusion. We find this cost yields limited direct benefit. On ThinkMorph, removing or noising VTs barely changes accuracy across nine benchmarks. Once rendered, attention concentrates on the VT regardless of content. Yet a KL diagnostic shows that conditioning on a privileged VT trace shifts the model's completion distribution. This suggests the generation pathway encodes useful reasoning beyond t","authors_text":"Fangzhi Xu, Jun Liu, Lingling Zhang, Muye Huang, Pengyu Li, Yuanming Li, Zhitao Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T11:59:15Z","title":"Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18974","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:ca398023e1cf91cf41f6492775b3e79fea3bbfe0ad5b09543cfef9f11a2bc9ff","target":"record","created_at":"2026-06-19T16:11:53Z","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":"05208f75ad232e32c094afcc5f6c4444d05611558f4fbe0f9cda72eac771aeed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T11:59:15Z","title_canon_sha256":"37cfa63616864418177cb43e613425bf53bea3c831ddd06108474a1a3484c6ef"},"schema_version":"1.0","source":{"id":"2606.18974","kind":"arxiv","version":1}},"canonical_sha256":"2ecd79111637ac645c9face9be5f7f3bd8b0648d5280bd862f31c1e3ff0b9672","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ecd79111637ac645c9face9be5f7f3bd8b0648d5280bd862f31c1e3ff0b9672","first_computed_at":"2026-06-19T16:11:53.506957Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:53.506957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jRGfx7uQTbNRjrEsUhmwRpwUtvnhMi0xvpdoNTk8+qmXYx2lhqHiZghbq2Ge31oo0KVvO7Y1IjrnayS9Ly1hDA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:53.507335Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18974","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca398023e1cf91cf41f6492775b3e79fea3bbfe0ad5b09543cfef9f11a2bc9ff","sha256:6f628b2a7bab4e06e0152cd20a3728610abf9911a86abdfc81d954f7dc01eb19"],"state_sha256":"4cfc4d3acd85cef2e3e191cbb6ec8ee05a7fadc665be997bec1dd7916b79c7e9"}