{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T324FV4VNTVR6BMAKRPJEGDLTG","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":"65dfbcfefb7fc52a0490abd47325aa6374ec4f8509b0879b861cf1767d22710c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-31T08:24:05Z","title_canon_sha256":"ffb519b69a2d6c8398620adaae064be032450f735f7817dcf3b2ef6ba5326da5"},"schema_version":"1.0","source":{"id":"2608.00110","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00110","created_at":"2026-08-04T00:32:19Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00110v1","created_at":"2026-08-04T00:32:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00110","created_at":"2026-08-04T00:32:19Z"},{"alias_kind":"pith_short_12","alias_value":"T324FV4VNTVR","created_at":"2026-08-04T00:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"T324FV4VNTVR6BMA","created_at":"2026-08-04T00:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"T324FV4V","created_at":"2026-08-04T00:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:19c68df115e8da208bb058c9012d78179985298962f9ed7c79c08948594dab4c","target":"graph","created_at":"2026-08-04T00:32:19Z","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/2608.00110/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D scene understanding requires reasoning about entity existence, spatial layout, and object relations, yet RGB images alone often provide insufficient 3D cues. Existing 3D-VLMs commonly rely on depth or 3D-position-aware inputs at inference time, introducing additional acquisition, reconstruction, or annotation costs that limit RGB-only deployment. We therefore study how training-time 3D evidence can be converted into spatial reasoning capabilities retained under RGB-only inference. We propose a privileged-evidence distillation framework that constructs a distillable teacher through a unified","authors_text":"Boran Zhao, Jiangcheng Song, Jiepeng Zhou, Jin Cui, Jun Ye, Pengju Ren, Yanbin Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-31T08:24:05Z","title":"Distill What RGB Can Recover: Privileged 3D Evidence for RGB-Only Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00110","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":"sha256:59d07d2b337dc4ce9b7abb01b28326337075959de45606468673b88df36b84cf","target":"record","created_at":"2026-08-04T00:32:19Z","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":"65dfbcfefb7fc52a0490abd47325aa6374ec4f8509b0879b861cf1767d22710c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-31T08:24:05Z","title_canon_sha256":"ffb519b69a2d6c8398620adaae064be032450f735f7817dcf3b2ef6ba5326da5"},"schema_version":"1.0","source":{"id":"2608.00110","kind":"arxiv","version":1}},"canonical_sha256":"9ef5c2d7956ceb1f0580545e92186b999dd4070020cf5ba5af771b139a194c65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ef5c2d7956ceb1f0580545e92186b999dd4070020cf5ba5af771b139a194c65","first_computed_at":"2026-08-04T00:32:19.265681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:32:19.265681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hs0mnS4/uF06mG9f+roJVlyb+KD9je5QG1FR0UfNrFf2oQPfUtvlUJeUuQu57lmZ18c8t6MOWkCLqIIUjwbVDg==","signature_status":"signed_v1","signed_at":"2026-08-04T00:32:19.267100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00110","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59d07d2b337dc4ce9b7abb01b28326337075959de45606468673b88df36b84cf","sha256:19c68df115e8da208bb058c9012d78179985298962f9ed7c79c08948594dab4c"],"state_sha256":"8665d9e2d3b9e70466ff429219596c470db542f43e9491e3a0afc82ac8317810"}