{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T324FV4VNTVR6BMAKRPJEGDLTG","short_pith_number":"pith:T324FV4V","schema_version":"1.0","canonical_sha256":"9ef5c2d7956ceb1f0580545e92186b999dd4070020cf5ba5af771b139a194c65","source":{"kind":"arxiv","id":"2608.00110","version":1},"attestation_state":"computed","paper":{"title":"Distill What RGB Can Recover: Privileged 3D Evidence for RGB-Only Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boran Zhao, Jiangcheng Song, Jiepeng Zhou, Jin Cui, Jun Ye, Pengju Ren, Yanbin Hu","submitted_at":"2026-07-31T08:24:05Z","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"},"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":"2608.00110","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-31T08:24:05Z","cross_cats_sorted":[],"title_canon_sha256":"ffb519b69a2d6c8398620adaae064be032450f735f7817dcf3b2ef6ba5326da5","abstract_canon_sha256":"65dfbcfefb7fc52a0490abd47325aa6374ec4f8509b0879b861cf1767d22710c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:32:19.267100Z","signature_b64":"Hs0mnS4/uF06mG9f+roJVlyb+KD9je5QG1FR0UfNrFf2oQPfUtvlUJeUuQu57lmZ18c8t6MOWkCLqIIUjwbVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ef5c2d7956ceb1f0580545e92186b999dd4070020cf5ba5af771b139a194c65","last_reissued_at":"2026-08-04T00:32:19.265681Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:32:19.265681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distill What RGB Can Recover: Privileged 3D Evidence for RGB-Only Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boran Zhao, Jiangcheng Song, Jiepeng Zhou, Jin Cui, Jun Ye, Pengju Ren, Yanbin Hu","submitted_at":"2026-07-31T08:24:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00110","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/2608.00110/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":"2608.00110","created_at":"2026-08-04T00:32:19.266718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00110v1","created_at":"2026-08-04T00:32:19.266718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00110","created_at":"2026-08-04T00:32:19.266718+00:00"},{"alias_kind":"pith_short_12","alias_value":"T324FV4VNTVR","created_at":"2026-08-04T00:32:19.266718+00:00"},{"alias_kind":"pith_short_16","alias_value":"T324FV4VNTVR6BMA","created_at":"2026-08-04T00:32:19.266718+00:00"},{"alias_kind":"pith_short_8","alias_value":"T324FV4V","created_at":"2026-08-04T00:32:19.266718+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/T324FV4VNTVR6BMAKRPJEGDLTG","json":"https://pith.science/pith/T324FV4VNTVR6BMAKRPJEGDLTG.json","graph_json":"https://pith.science/api/pith-number/T324FV4VNTVR6BMAKRPJEGDLTG/graph.json","events_json":"https://pith.science/api/pith-number/T324FV4VNTVR6BMAKRPJEGDLTG/events.json","paper":"https://pith.science/paper/T324FV4V"},"agent_actions":{"view_html":"https://pith.science/pith/T324FV4VNTVR6BMAKRPJEGDLTG","download_json":"https://pith.science/pith/T324FV4VNTVR6BMAKRPJEGDLTG.json","view_paper":"https://pith.science/paper/T324FV4V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00110&json=true","fetch_graph":"https://pith.science/api/pith-number/T324FV4VNTVR6BMAKRPJEGDLTG/graph.json","fetch_events":"https://pith.science/api/pith-number/T324FV4VNTVR6BMAKRPJEGDLTG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T324FV4VNTVR6BMAKRPJEGDLTG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T324FV4VNTVR6BMAKRPJEGDLTG/action/storage_attestation","attest_author":"https://pith.science/pith/T324FV4VNTVR6BMAKRPJEGDLTG/action/author_attestation","sign_citation":"https://pith.science/pith/T324FV4VNTVR6BMAKRPJEGDLTG/action/citation_signature","submit_replication":"https://pith.science/pith/T324FV4VNTVR6BMAKRPJEGDLTG/action/replication_record"}},"created_at":"2026-08-04T00:32:19.266718+00:00","updated_at":"2026-08-04T00:32:19.266718+00:00"}