{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:W6YX7AKG4MINWAO5BHMTDPX326","short_pith_number":"pith:W6YX7AKG","canonical_record":{"source":{"id":"2502.17860","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-25T05:10:22Z","cross_cats_sorted":[],"title_canon_sha256":"ad40f2edd2e64e673ae9e70cf6e6d4cc3f0590b69b7f78ab8df260c04d8750a4","abstract_canon_sha256":"777df7dbb92c279594ae7a0c49ca217f6ad81506e81553cb181839acc7ae3d29"},"schema_version":"1.0"},"canonical_sha256":"b7b17f8146e310db01dd09d931befbd7bfeeeaaee4cf26d08d2bfd3e127156fa","source":{"kind":"arxiv","id":"2502.17860","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17860","created_at":"2026-07-05T10:20:45Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17860v2","created_at":"2026-07-05T10:20:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17860","created_at":"2026-07-05T10:20:45Z"},{"alias_kind":"pith_short_12","alias_value":"W6YX7AKG4MIN","created_at":"2026-07-05T10:20:45Z"},{"alias_kind":"pith_short_16","alias_value":"W6YX7AKG4MINWAO5","created_at":"2026-07-05T10:20:45Z"},{"alias_kind":"pith_short_8","alias_value":"W6YX7AKG","created_at":"2026-07-05T10:20:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:W6YX7AKG4MINWAO5BHMTDPX326","target":"record","payload":{"canonical_record":{"source":{"id":"2502.17860","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-25T05:10:22Z","cross_cats_sorted":[],"title_canon_sha256":"ad40f2edd2e64e673ae9e70cf6e6d4cc3f0590b69b7f78ab8df260c04d8750a4","abstract_canon_sha256":"777df7dbb92c279594ae7a0c49ca217f6ad81506e81553cb181839acc7ae3d29"},"schema_version":"1.0"},"canonical_sha256":"b7b17f8146e310db01dd09d931befbd7bfeeeaaee4cf26d08d2bfd3e127156fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:45.461750Z","signature_b64":"fMFMxkG1X3i4XxueXh9mjG/F+83eKF93iJyGVO6f88NpgBYmCAl86M29AUKQ2xbca8mfFtzbW5aHsJmikRJjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7b17f8146e310db01dd09d931befbd7bfeeeaaee4cf26d08d2bfd3e127156fa","last_reissued_at":"2026-07-05T10:20:45.461235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:45.461235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.17860","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":"2026-07-05T10:20:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Iy64X/B8YRAL9NgWkwlfEkbxvtavUQ+kh/0GhGqy16B0UU51K1GN+gZZMixFmf4lBVsxpwD7RUjcrhGJffIOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:55:39.437095Z"},"content_sha256":"9e8f383f236d7d03b8d388c9aaa94cebc559190e7308dc6184ff13ec33049965","schema_version":"1.0","event_id":"sha256:9e8f383f236d7d03b8d388c9aaa94cebc559190e7308dc6184ff13ec33049965"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:W6YX7AKG4MINWAO5BHMTDPX326","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Xu, Haoyuan Li, Jifei Song, Michael Kampffmeyer, Tao Tang, Xiaodan Liang, Yanpeng Zhou, Yihan Zeng","submitted_at":"2025-02-25T05:10:22Z","abstract_excerpt":"Recent advancements in multi-modal 3D pre-training methods have shown promising efficacy in learning joint representations of text, images, and point clouds. However, adopting point clouds as 3D representation fails to fully capture the intricacies of the 3D world and exhibits a noticeable gap between the discrete points and the dense 2D pixels of images. To tackle this issue, we propose UniGS, integrating 3D Gaussian Splatting (3DGS) into multi-modal pre-training to enhance the 3D representation. We first rely on the 3DGS representation to model the 3D world as a collection of 3D Gaussians wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17860","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/2502.17860/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":"2026-07-05T10:20:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ektm32VW593m4JY2Pqm42kucaDo0XvDPYkVdsQPHXCMi3sR05DTTY90VP2su9yJFUA/6MygnrCY5Xa8F7fdMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:55:39.438005Z"},"content_sha256":"db8292dac7f7489854e8c31e0266cfc8f3b36a7109039082b54acfb66f49cb9d","schema_version":"1.0","event_id":"sha256:db8292dac7f7489854e8c31e0266cfc8f3b36a7109039082b54acfb66f49cb9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W6YX7AKG4MINWAO5BHMTDPX326/bundle.json","state_url":"https://pith.science/pith/W6YX7AKG4MINWAO5BHMTDPX326/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W6YX7AKG4MINWAO5BHMTDPX326/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":"2026-08-03T17:55:39Z","links":{"resolver":"https://pith.science/pith/W6YX7AKG4MINWAO5BHMTDPX326","bundle":"https://pith.science/pith/W6YX7AKG4MINWAO5BHMTDPX326/bundle.json","state":"https://pith.science/pith/W6YX7AKG4MINWAO5BHMTDPX326/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W6YX7AKG4MINWAO5BHMTDPX326/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W6YX7AKG4MINWAO5BHMTDPX326","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":"777df7dbb92c279594ae7a0c49ca217f6ad81506e81553cb181839acc7ae3d29","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-25T05:10:22Z","title_canon_sha256":"ad40f2edd2e64e673ae9e70cf6e6d4cc3f0590b69b7f78ab8df260c04d8750a4"},"schema_version":"1.0","source":{"id":"2502.17860","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17860","created_at":"2026-07-05T10:20:45Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17860v2","created_at":"2026-07-05T10:20:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17860","created_at":"2026-07-05T10:20:45Z"},{"alias_kind":"pith_short_12","alias_value":"W6YX7AKG4MIN","created_at":"2026-07-05T10:20:45Z"},{"alias_kind":"pith_short_16","alias_value":"W6YX7AKG4MINWAO5","created_at":"2026-07-05T10:20:45Z"},{"alias_kind":"pith_short_8","alias_value":"W6YX7AKG","created_at":"2026-07-05T10:20:45Z"}],"graph_snapshots":[{"event_id":"sha256:db8292dac7f7489854e8c31e0266cfc8f3b36a7109039082b54acfb66f49cb9d","target":"graph","created_at":"2026-07-05T10:20:45Z","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/2502.17860/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in multi-modal 3D pre-training methods have shown promising efficacy in learning joint representations of text, images, and point clouds. However, adopting point clouds as 3D representation fails to fully capture the intricacies of the 3D world and exhibits a noticeable gap between the discrete points and the dense 2D pixels of images. To tackle this issue, we propose UniGS, integrating 3D Gaussian Splatting (3DGS) into multi-modal pre-training to enhance the 3D representation. We first rely on the 3DGS representation to model the 3D world as a collection of 3D Gaussians wi","authors_text":"Hang Xu, Haoyuan Li, Jifei Song, Michael Kampffmeyer, Tao Tang, Xiaodan Liang, Yanpeng Zhou, Yihan Zeng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-25T05:10:22Z","title":"UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17860","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":"sha256:9e8f383f236d7d03b8d388c9aaa94cebc559190e7308dc6184ff13ec33049965","target":"record","created_at":"2026-07-05T10:20:45Z","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":"777df7dbb92c279594ae7a0c49ca217f6ad81506e81553cb181839acc7ae3d29","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-25T05:10:22Z","title_canon_sha256":"ad40f2edd2e64e673ae9e70cf6e6d4cc3f0590b69b7f78ab8df260c04d8750a4"},"schema_version":"1.0","source":{"id":"2502.17860","kind":"arxiv","version":2}},"canonical_sha256":"b7b17f8146e310db01dd09d931befbd7bfeeeaaee4cf26d08d2bfd3e127156fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7b17f8146e310db01dd09d931befbd7bfeeeaaee4cf26d08d2bfd3e127156fa","first_computed_at":"2026-07-05T10:20:45.461235Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:45.461235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fMFMxkG1X3i4XxueXh9mjG/F+83eKF93iJyGVO6f88NpgBYmCAl86M29AUKQ2xbca8mfFtzbW5aHsJmikRJjDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:45.461750Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.17860","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e8f383f236d7d03b8d388c9aaa94cebc559190e7308dc6184ff13ec33049965","sha256:db8292dac7f7489854e8c31e0266cfc8f3b36a7109039082b54acfb66f49cb9d"],"state_sha256":"493cd4beefb5b012276ae9233e0d4a72d09570b46d421980789c80baac44e5ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y3q8PuzuBsb2jBZ60fw0JZoAzmETHR32qTayWmQhpGeuPEQpvAmmu1/maGCRLOSxN2XATGXAIX9lIdBrFfkjBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:55:39.444420Z","bundle_sha256":"4a799bf1d9a8abdbb2e131e42183642e32c6fe3eeeb6dafa7327b856b6f262fa"}}