{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3KVOJIOHO3V565NYT7WSZFSUOS","short_pith_number":"pith:3KVOJIOH","canonical_record":{"source":{"id":"2401.09340","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-17T17:04:35Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"c6799df4ab7f30c09159791d8da4a01cbba2c006085c2676fe18dca691ecdefa","abstract_canon_sha256":"3de84906a372c774b7a1f1ec2ecd70297ea38350beb96aeb914d9b6dbbc980a2"},"schema_version":"1.0"},"canonical_sha256":"daaae4a1c776ebdf75b89fed2c9654749d6f90bd9b2c49ac4493963f1ed7f406","source":{"kind":"arxiv","id":"2401.09340","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09340","created_at":"2026-07-05T09:10:44Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09340v3","created_at":"2026-07-05T09:10:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09340","created_at":"2026-07-05T09:10:44Z"},{"alias_kind":"pith_short_12","alias_value":"3KVOJIOHO3V5","created_at":"2026-07-05T09:10:44Z"},{"alias_kind":"pith_short_16","alias_value":"3KVOJIOHO3V565NY","created_at":"2026-07-05T09:10:44Z"},{"alias_kind":"pith_short_8","alias_value":"3KVOJIOH","created_at":"2026-07-05T09:10:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3KVOJIOHO3V565NYT7WSZFSUOS","target":"record","payload":{"canonical_record":{"source":{"id":"2401.09340","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-17T17:04:35Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"c6799df4ab7f30c09159791d8da4a01cbba2c006085c2676fe18dca691ecdefa","abstract_canon_sha256":"3de84906a372c774b7a1f1ec2ecd70297ea38350beb96aeb914d9b6dbbc980a2"},"schema_version":"1.0"},"canonical_sha256":"daaae4a1c776ebdf75b89fed2c9654749d6f90bd9b2c49ac4493963f1ed7f406","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:44.984753Z","signature_b64":"C2vTZNb5WpBKSJOSBx4EG060Xk1q1pmjLtpmg1Ip+2Xoc4JFhfe3q+rL4jFof7tKy4DtfA+hUTEMdhKIMqvlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"daaae4a1c776ebdf75b89fed2c9654749d6f90bd9b2c49ac4493963f1ed7f406","last_reissued_at":"2026-07-05T09:10:44.984347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:44.984347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.09340","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:10:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s5LefeUUxdECSU/AAA7O+Cz/2k57JvhSl5POQiUKznUJclb7udpIEkaEwDvly7cEWL08FP2Z9rsUiVRWR0GSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:00:15.440653Z"},"content_sha256":"7a0d0318ca4fd907d7f90a277c9595fbcfa0d11c5cf17b08e0704985ed12bacb","schema_version":"1.0","event_id":"sha256:7a0d0318ca4fd907d7f90a277c9595fbcfa0d11c5cf17b08e0704985ed12bacb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3KVOJIOHO3V565NYT7WSZFSUOS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Baoxiong Jia, Huangyue Yu, Qing Li, Siyuan Huang, Tengyu Liu, Xuesong Niu, Yan Wang, Yixin Chen","submitted_at":"2024-01-17T17:04:35Z","abstract_excerpt":"3D vision-language grounding, which focuses on aligning language with the 3D physical environment, stands as a cornerstone in the development of embodied agents. In comparison to recent advancements in the 2D domain, grounding language in 3D scenes faces several significant challenges: (i) the inherent complexity of 3D scenes due to the diverse object configurations, their rich attributes, and intricate relationships; (ii) the scarcity of paired 3D vision-language data to support grounded learning; and (iii) the absence of a unified learning framework to distill knowledge from grounded 3D data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09340","kind":"arxiv","version":3},"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/2401.09340/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":"2026-07-05T09:10:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EXlf7fDjLnfqcW3GdMH5m758/pqPiw03QhKFBeK1wiKdpNrWUACCtb/Udfm4qb5vmeFU3Ad0FZmSbg3JTKD7Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:00:15.441029Z"},"content_sha256":"25033f2035a5cf54eaf7ba8a70d9d5af2737342a651fc0acdc7414f1c5312a6b","schema_version":"1.0","event_id":"sha256:25033f2035a5cf54eaf7ba8a70d9d5af2737342a651fc0acdc7414f1c5312a6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3KVOJIOHO3V565NYT7WSZFSUOS/bundle.json","state_url":"https://pith.science/pith/3KVOJIOHO3V565NYT7WSZFSUOS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3KVOJIOHO3V565NYT7WSZFSUOS/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":"2026-07-07T11:00:15Z","links":{"resolver":"https://pith.science/pith/3KVOJIOHO3V565NYT7WSZFSUOS","bundle":"https://pith.science/pith/3KVOJIOHO3V565NYT7WSZFSUOS/bundle.json","state":"https://pith.science/pith/3KVOJIOHO3V565NYT7WSZFSUOS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3KVOJIOHO3V565NYT7WSZFSUOS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3KVOJIOHO3V565NYT7WSZFSUOS","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":"3de84906a372c774b7a1f1ec2ecd70297ea38350beb96aeb914d9b6dbbc980a2","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-17T17:04:35Z","title_canon_sha256":"c6799df4ab7f30c09159791d8da4a01cbba2c006085c2676fe18dca691ecdefa"},"schema_version":"1.0","source":{"id":"2401.09340","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09340","created_at":"2026-07-05T09:10:44Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09340v3","created_at":"2026-07-05T09:10:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09340","created_at":"2026-07-05T09:10:44Z"},{"alias_kind":"pith_short_12","alias_value":"3KVOJIOHO3V5","created_at":"2026-07-05T09:10:44Z"},{"alias_kind":"pith_short_16","alias_value":"3KVOJIOHO3V565NY","created_at":"2026-07-05T09:10:44Z"},{"alias_kind":"pith_short_8","alias_value":"3KVOJIOH","created_at":"2026-07-05T09:10:44Z"}],"graph_snapshots":[{"event_id":"sha256:25033f2035a5cf54eaf7ba8a70d9d5af2737342a651fc0acdc7414f1c5312a6b","target":"graph","created_at":"2026-07-05T09:10:44Z","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/2401.09340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D vision-language grounding, which focuses on aligning language with the 3D physical environment, stands as a cornerstone in the development of embodied agents. In comparison to recent advancements in the 2D domain, grounding language in 3D scenes faces several significant challenges: (i) the inherent complexity of 3D scenes due to the diverse object configurations, their rich attributes, and intricate relationships; (ii) the scarcity of paired 3D vision-language data to support grounded learning; and (iii) the absence of a unified learning framework to distill knowledge from grounded 3D data","authors_text":"Baoxiong Jia, Huangyue Yu, Qing Li, Siyuan Huang, Tengyu Liu, Xuesong Niu, Yan Wang, Yixin Chen","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-17T17:04:35Z","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09340","kind":"arxiv","version":3},"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":"sha256:7a0d0318ca4fd907d7f90a277c9595fbcfa0d11c5cf17b08e0704985ed12bacb","target":"record","created_at":"2026-07-05T09:10:44Z","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":"3de84906a372c774b7a1f1ec2ecd70297ea38350beb96aeb914d9b6dbbc980a2","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-17T17:04:35Z","title_canon_sha256":"c6799df4ab7f30c09159791d8da4a01cbba2c006085c2676fe18dca691ecdefa"},"schema_version":"1.0","source":{"id":"2401.09340","kind":"arxiv","version":3}},"canonical_sha256":"daaae4a1c776ebdf75b89fed2c9654749d6f90bd9b2c49ac4493963f1ed7f406","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"daaae4a1c776ebdf75b89fed2c9654749d6f90bd9b2c49ac4493963f1ed7f406","first_computed_at":"2026-07-05T09:10:44.984347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:44.984347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C2vTZNb5WpBKSJOSBx4EG060Xk1q1pmjLtpmg1Ip+2Xoc4JFhfe3q+rL4jFof7tKy4DtfA+hUTEMdhKIMqvlDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:44.984753Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.09340","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a0d0318ca4fd907d7f90a277c9595fbcfa0d11c5cf17b08e0704985ed12bacb","sha256:25033f2035a5cf54eaf7ba8a70d9d5af2737342a651fc0acdc7414f1c5312a6b"],"state_sha256":"b3dc8ed57e8d2479b8270f6db78c08a4f79f2714b01e9e9cc2d43afb711175f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zSfUo2s9sCG4p2IhnhBe38ZXSvuUCBlh4q4PpEYRFKsqwgYZ/1tKxwVTCiDgidpFBOSTRAhP4s7G8m+fWPiYBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:00:15.443030Z","bundle_sha256":"4da4e60962dbc7cf59ee9817f2e9a002d93366aa53f7749bb2868c9002aa33fd"}}