{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:U7IOWKOAMZOZ77XYCH3XPN7LRS","short_pith_number":"pith:U7IOWKOA","canonical_record":{"source":{"id":"2502.20389","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T18:59:11Z","cross_cats_sorted":[],"title_canon_sha256":"2547d61d421123a98a62fe6482c8d3f2120aae74f671c16f4a0f9f7dbcd18d09","abstract_canon_sha256":"1a2654e05ac44a3257cd37751ed86a2b51b190591a8ea49b63232f06374858ef"},"schema_version":"1.0"},"canonical_sha256":"a7d0eb29c0665d9ffef811f777b7eb8c97bbeeb703a81abe7a0dc93098dd14fe","source":{"kind":"arxiv","id":"2502.20389","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20389","created_at":"2026-07-05T11:18:18Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20389v2","created_at":"2026-07-05T11:18:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20389","created_at":"2026-07-05T11:18:18Z"},{"alias_kind":"pith_short_12","alias_value":"U7IOWKOAMZOZ","created_at":"2026-07-05T11:18:18Z"},{"alias_kind":"pith_short_16","alias_value":"U7IOWKOAMZOZ77XY","created_at":"2026-07-05T11:18:18Z"},{"alias_kind":"pith_short_8","alias_value":"U7IOWKOA","created_at":"2026-07-05T11:18:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:U7IOWKOAMZOZ77XYCH3XPN7LRS","target":"record","payload":{"canonical_record":{"source":{"id":"2502.20389","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T18:59:11Z","cross_cats_sorted":[],"title_canon_sha256":"2547d61d421123a98a62fe6482c8d3f2120aae74f671c16f4a0f9f7dbcd18d09","abstract_canon_sha256":"1a2654e05ac44a3257cd37751ed86a2b51b190591a8ea49b63232f06374858ef"},"schema_version":"1.0"},"canonical_sha256":"a7d0eb29c0665d9ffef811f777b7eb8c97bbeeb703a81abe7a0dc93098dd14fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:18.901832Z","signature_b64":"XrYLLREDXIBEW7Fr6H/Db5K3xEuc4EPda1IH8Nx+9SfOfY12Sysc3cC2F1kIG/pEdIISOhLfKPAL6qRvnqhuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7d0eb29c0665d9ffef811f777b7eb8c97bbeeb703a81abe7a0dc93098dd14fe","last_reissued_at":"2026-07-05T11:18:18.901376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:18.901376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.20389","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LKtU4eGgpHkdbFEHSQzxG3pkcDgcMoH1xM1hWtLfWXux3cSlza6TzJRv0cSZfvZzm4Ccfp4RaW5Be2YfL9oEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:48:28.362716Z"},"content_sha256":"ccc059389a4f478aa3f8c0ecaf0b9edff05caa4b30691bc48c565f7ba6714923","schema_version":"1.0","event_id":"sha256:ccc059389a4f478aa3f8c0ecaf0b9edff05caa4b30691bc48c565f7ba6714923"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:U7IOWKOAMZOZ77XYCH3XPN7LRS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ada Martin, Alexander Sax, Ang Cao, Aravind Rajeswaran, Ayush Jain, Franziska Meier, Jeong Joon Park, Jianing Yang, Justin Johnson, Oleksandr Maksymets, Paul Mcvay, Ruslan Partsey, Sergio Arnaud, Sriram Yenamandra, Vincent-Pierre Berges","submitted_at":"2025-02-27T18:59:11Z","abstract_excerpt":"3D vision-language grounding faces a fundamental data bottleneck: while 2D models train on billions of images, 3D models have access to only thousands of labeled scenes--a six-order-of-magnitude gap that severely limits performance. We introduce $\\textbf{LIFT-GS}$, a practical distillation technique that overcomes this limitation by using differentiable rendering to bridge 3D and 2D supervision. LIFT-GS predicts 3D Gaussian representations from point clouds and uses them to render predicted language-conditioned 3D masks into 2D views, enabling supervision from 2D foundation models (SAM, CLIP, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20389","kind":"arxiv","version":2},"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/2502.20389/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lcb/Z1NDj8adZjiOenhZ2RW4drESaLidWwN89o5BKDyAHrbzW5ByjzswUvx7pic3OwmF4yOhcBxSHYjTSZ4tBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:48:28.363255Z"},"content_sha256":"8012f42d32ee238a733599757475f49ba5414487e6796c71ed59c501398fb789","schema_version":"1.0","event_id":"sha256:8012f42d32ee238a733599757475f49ba5414487e6796c71ed59c501398fb789"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U7IOWKOAMZOZ77XYCH3XPN7LRS/bundle.json","state_url":"https://pith.science/pith/U7IOWKOAMZOZ77XYCH3XPN7LRS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U7IOWKOAMZOZ77XYCH3XPN7LRS/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":"2026-08-10T23:48:28Z","links":{"resolver":"https://pith.science/pith/U7IOWKOAMZOZ77XYCH3XPN7LRS","bundle":"https://pith.science/pith/U7IOWKOAMZOZ77XYCH3XPN7LRS/bundle.json","state":"https://pith.science/pith/U7IOWKOAMZOZ77XYCH3XPN7LRS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U7IOWKOAMZOZ77XYCH3XPN7LRS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U7IOWKOAMZOZ77XYCH3XPN7LRS","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":"1a2654e05ac44a3257cd37751ed86a2b51b190591a8ea49b63232f06374858ef","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T18:59:11Z","title_canon_sha256":"2547d61d421123a98a62fe6482c8d3f2120aae74f671c16f4a0f9f7dbcd18d09"},"schema_version":"1.0","source":{"id":"2502.20389","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20389","created_at":"2026-07-05T11:18:18Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20389v2","created_at":"2026-07-05T11:18:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20389","created_at":"2026-07-05T11:18:18Z"},{"alias_kind":"pith_short_12","alias_value":"U7IOWKOAMZOZ","created_at":"2026-07-05T11:18:18Z"},{"alias_kind":"pith_short_16","alias_value":"U7IOWKOAMZOZ77XY","created_at":"2026-07-05T11:18:18Z"},{"alias_kind":"pith_short_8","alias_value":"U7IOWKOA","created_at":"2026-07-05T11:18:18Z"}],"graph_snapshots":[{"event_id":"sha256:8012f42d32ee238a733599757475f49ba5414487e6796c71ed59c501398fb789","target":"graph","created_at":"2026-07-05T11:18:18Z","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/2502.20389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D vision-language grounding faces a fundamental data bottleneck: while 2D models train on billions of images, 3D models have access to only thousands of labeled scenes--a six-order-of-magnitude gap that severely limits performance. We introduce $\\textbf{LIFT-GS}$, a practical distillation technique that overcomes this limitation by using differentiable rendering to bridge 3D and 2D supervision. LIFT-GS predicts 3D Gaussian representations from point clouds and uses them to render predicted language-conditioned 3D masks into 2D views, enabling supervision from 2D foundation models (SAM, CLIP, ","authors_text":"Ada Martin, Alexander Sax, Ang Cao, Aravind Rajeswaran, Ayush Jain, Franziska Meier, Jeong Joon Park, Jianing Yang, Justin Johnson, Oleksandr Maksymets, Paul Mcvay, Ruslan Partsey, Sergio Arnaud, Sriram Yenamandra, Vincent-Pierre Berges","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T18:59:11Z","title":"From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20389","kind":"arxiv","version":2},"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:ccc059389a4f478aa3f8c0ecaf0b9edff05caa4b30691bc48c565f7ba6714923","target":"record","created_at":"2026-07-05T11:18:18Z","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":"1a2654e05ac44a3257cd37751ed86a2b51b190591a8ea49b63232f06374858ef","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T18:59:11Z","title_canon_sha256":"2547d61d421123a98a62fe6482c8d3f2120aae74f671c16f4a0f9f7dbcd18d09"},"schema_version":"1.0","source":{"id":"2502.20389","kind":"arxiv","version":2}},"canonical_sha256":"a7d0eb29c0665d9ffef811f777b7eb8c97bbeeb703a81abe7a0dc93098dd14fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7d0eb29c0665d9ffef811f777b7eb8c97bbeeb703a81abe7a0dc93098dd14fe","first_computed_at":"2026-07-05T11:18:18.901376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:18.901376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XrYLLREDXIBEW7Fr6H/Db5K3xEuc4EPda1IH8Nx+9SfOfY12Sysc3cC2F1kIG/pEdIISOhLfKPAL6qRvnqhuAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:18.901832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20389","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccc059389a4f478aa3f8c0ecaf0b9edff05caa4b30691bc48c565f7ba6714923","sha256:8012f42d32ee238a733599757475f49ba5414487e6796c71ed59c501398fb789"],"state_sha256":"5318a2b942e1e02ade71146ca926dd9e14c92aa25995ae2cf7538b7b0a5f5006"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gzAzfq87syoPqeM8z9lGT0Fkj9BcCnsIX2UHNYrMI3IEBomt9RzX0kKpMzhpOiKRBUyff78LGzBYfhsrL2+DCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:48:28.368006Z","bundle_sha256":"96fda276c43df8687b4212e52f2ff96292a81a51034f6a061d5837b5fca86ccd"}}