{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FZ3ELNLZBCWIURYKI62MPSDTA3","short_pith_number":"pith:FZ3ELNLZ","canonical_record":{"source":{"id":"2406.09401","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:30Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"ff0470f551bb0a139a4971e889b41ebe6ef169fe7a487738637a1f9bd959f555","abstract_canon_sha256":"944666e401654aff255b217c9f347e49ad686d9c1250bfbcd4fca91bc603d3c3"},"schema_version":"1.0"},"canonical_sha256":"2e7645b57908ac8a470a47b4c7c87306c5c528f685c7d3a2049ff434952a193c","source":{"kind":"arxiv","id":"2406.09401","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09401","created_at":"2026-07-05T11:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09401v2","created_at":"2026-07-05T11:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09401","created_at":"2026-07-05T11:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"FZ3ELNLZBCWI","created_at":"2026-07-05T11:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"FZ3ELNLZBCWIURYK","created_at":"2026-07-05T11:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"FZ3ELNLZ","created_at":"2026-07-05T11:18:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FZ3ELNLZBCWIURYKI62MPSDTA3","target":"record","payload":{"canonical_record":{"source":{"id":"2406.09401","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:30Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"ff0470f551bb0a139a4971e889b41ebe6ef169fe7a487738637a1f9bd959f555","abstract_canon_sha256":"944666e401654aff255b217c9f347e49ad686d9c1250bfbcd4fca91bc603d3c3"},"schema_version":"1.0"},"canonical_sha256":"2e7645b57908ac8a470a47b4c7c87306c5c528f685c7d3a2049ff434952a193c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:12.642424Z","signature_b64":"BBK03auqW20dZxmjmb3KzXoDjIaMUCBPuDBYgxJTYaHAIDOE2IgUpNMk/UvwI4GfqQmh+Kl0cDHdNJB36/hDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e7645b57908ac8a470a47b4c7c87306c5c528f685c7d3a2049ff434952a193c","last_reissued_at":"2026-07-05T11:18:12.641980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:12.641980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.09401","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":"2026-07-05T11:18:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X3X93JKMbPbNUVESBFYCnZwHtr4J4XE0YgHuaddugRtcaRE8RBVJCgOecmnhlLDrVECK4jvhcsCe7IHTEoF6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:12:49.005146Z"},"content_sha256":"d760be85005006722c1601d4f3db5baf96eceea2e8d8413cb4ecbd21b627fe0c","schema_version":"1.0","event_id":"sha256:d760be85005006722c1601d4f3db5baf96eceea2e8d8413cb4ecbd21b627fe0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FZ3ELNLZBCWIURYKI62MPSDTA3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chenming Zhu, Dahua Lin, Haifeng Huang, Jiangmiao Pang, Jingli Lin, Ruiyuan Lyu, Runsen Xu, Shuai Yang, Tai Wang, Xiaohan Mao, Yilun Chen","submitted_at":"2024-06-13T17:59:30Z","abstract_excerpt":"With the emergence of LLMs and their integration with other data modalities, multi-modal 3D perception attracts more attention due to its connectivity to the physical world and makes rapid progress. However, limited by existing datasets, previous works mainly focus on understanding object properties or inter-object spatial relationships in a 3D scene. To tackle this problem, this paper builds the first largest ever multi-modal 3D scene dataset and benchmark with hierarchical grounded language annotations, MMScan. It is constructed based on a top-down logic, from region to object level, from a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09401","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/2406.09401/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":"2026-07-05T11:18:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8rY+vziLB2ob3rAfWhRsAe2BC1F2UntzFT67Q02GeJvgkqSU7FAhU7FY2lDt5TToSmj0dEfqvsiZkb7b8R+cDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:12:49.005689Z"},"content_sha256":"71d9613a2ab427b8942ca4d3f306cf9c0faae57d7f3ac028dfc869064f0a5c2b","schema_version":"1.0","event_id":"sha256:71d9613a2ab427b8942ca4d3f306cf9c0faae57d7f3ac028dfc869064f0a5c2b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FZ3ELNLZBCWIURYKI62MPSDTA3/bundle.json","state_url":"https://pith.science/pith/FZ3ELNLZBCWIURYKI62MPSDTA3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FZ3ELNLZBCWIURYKI62MPSDTA3/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":"2026-08-05T02:12:49Z","links":{"resolver":"https://pith.science/pith/FZ3ELNLZBCWIURYKI62MPSDTA3","bundle":"https://pith.science/pith/FZ3ELNLZBCWIURYKI62MPSDTA3/bundle.json","state":"https://pith.science/pith/FZ3ELNLZBCWIURYKI62MPSDTA3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FZ3ELNLZBCWIURYKI62MPSDTA3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FZ3ELNLZBCWIURYKI62MPSDTA3","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":"944666e401654aff255b217c9f347e49ad686d9c1250bfbcd4fca91bc603d3c3","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:30Z","title_canon_sha256":"ff0470f551bb0a139a4971e889b41ebe6ef169fe7a487738637a1f9bd959f555"},"schema_version":"1.0","source":{"id":"2406.09401","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09401","created_at":"2026-07-05T11:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09401v2","created_at":"2026-07-05T11:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09401","created_at":"2026-07-05T11:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"FZ3ELNLZBCWI","created_at":"2026-07-05T11:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"FZ3ELNLZBCWIURYK","created_at":"2026-07-05T11:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"FZ3ELNLZ","created_at":"2026-07-05T11:18:12Z"}],"graph_snapshots":[{"event_id":"sha256:71d9613a2ab427b8942ca4d3f306cf9c0faae57d7f3ac028dfc869064f0a5c2b","target":"graph","created_at":"2026-07-05T11:18:12Z","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/2406.09401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the emergence of LLMs and their integration with other data modalities, multi-modal 3D perception attracts more attention due to its connectivity to the physical world and makes rapid progress. However, limited by existing datasets, previous works mainly focus on understanding object properties or inter-object spatial relationships in a 3D scene. To tackle this problem, this paper builds the first largest ever multi-modal 3D scene dataset and benchmark with hierarchical grounded language annotations, MMScan. It is constructed based on a top-down logic, from region to object level, from a ","authors_text":"Chenming Zhu, Dahua Lin, Haifeng Huang, Jiangmiao Pang, Jingli Lin, Ruiyuan Lyu, Runsen Xu, Shuai Yang, Tai Wang, Xiaohan Mao, Yilun Chen","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:30Z","title":"MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09401","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:d760be85005006722c1601d4f3db5baf96eceea2e8d8413cb4ecbd21b627fe0c","target":"record","created_at":"2026-07-05T11:18:12Z","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":"944666e401654aff255b217c9f347e49ad686d9c1250bfbcd4fca91bc603d3c3","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:30Z","title_canon_sha256":"ff0470f551bb0a139a4971e889b41ebe6ef169fe7a487738637a1f9bd959f555"},"schema_version":"1.0","source":{"id":"2406.09401","kind":"arxiv","version":2}},"canonical_sha256":"2e7645b57908ac8a470a47b4c7c87306c5c528f685c7d3a2049ff434952a193c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e7645b57908ac8a470a47b4c7c87306c5c528f685c7d3a2049ff434952a193c","first_computed_at":"2026-07-05T11:18:12.641980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:12.641980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BBK03auqW20dZxmjmb3KzXoDjIaMUCBPuDBYgxJTYaHAIDOE2IgUpNMk/UvwI4GfqQmh+Kl0cDHdNJB36/hDCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:12.642424Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09401","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d760be85005006722c1601d4f3db5baf96eceea2e8d8413cb4ecbd21b627fe0c","sha256:71d9613a2ab427b8942ca4d3f306cf9c0faae57d7f3ac028dfc869064f0a5c2b"],"state_sha256":"700cb63bac4d81d971f59c178b7f86a6f205f5070198310b17aabb3931d8cf2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ObFOw7dJoHCr5wJrKb0L9wDiloERdksKtNyhXMzNnBPBxjsfXAsZisY6UHlgAg4pAuD5DJw2gecb4MJ3d4kgCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:12:49.011547Z","bundle_sha256":"676948a287c4ac2688c19968238c008912cc0f089160b232b81e838be31e35b4"}}