{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:B3RCSLPZX6QWAXRRBIUD2GAVJQ","short_pith_number":"pith:B3RCSLPZ","canonical_record":{"source":{"id":"2409.02389","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-04T02:37:38Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"2b7bc5c6a53903b33f908da43f952a1c2bd373bacfae54b20ac54cca0f83bd48","abstract_canon_sha256":"6da697fa9a18ce0a00ad0d2d4b8e649c5df686ed01399d5bedd941139e772a8b"},"schema_version":"1.0"},"canonical_sha256":"0ee2292df9bfa1605e310a283d18154c314754dc0d492456c6571dbfa8f552a3","source":{"kind":"arxiv","id":"2409.02389","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02389","created_at":"2026-07-05T09:36:48Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02389v2","created_at":"2026-07-05T09:36:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02389","created_at":"2026-07-05T09:36:48Z"},{"alias_kind":"pith_short_12","alias_value":"B3RCSLPZX6QW","created_at":"2026-07-05T09:36:48Z"},{"alias_kind":"pith_short_16","alias_value":"B3RCSLPZX6QWAXRR","created_at":"2026-07-05T09:36:48Z"},{"alias_kind":"pith_short_8","alias_value":"B3RCSLPZ","created_at":"2026-07-05T09:36:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:B3RCSLPZX6QWAXRRBIUD2GAVJQ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.02389","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-04T02:37:38Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"2b7bc5c6a53903b33f908da43f952a1c2bd373bacfae54b20ac54cca0f83bd48","abstract_canon_sha256":"6da697fa9a18ce0a00ad0d2d4b8e649c5df686ed01399d5bedd941139e772a8b"},"schema_version":"1.0"},"canonical_sha256":"0ee2292df9bfa1605e310a283d18154c314754dc0d492456c6571dbfa8f552a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:48.027941Z","signature_b64":"I4pcQd9Xu8nUEIHPvTO4TQLUZP6dU2wV7KdIbIC7umduKqUK1ldj9PGCTDl8I1Ls/dSjaR3N1RTfvkc+3bozCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ee2292df9bfa1605e310a283d18154c314754dc0d492456c6571dbfa8f552a3","last_reissued_at":"2026-07-05T09:36:48.027480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:48.027480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.02389","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":"2026-07-05T09:36:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dTcJJma4GBVBrSNdoZIkg4BdANFz01nVj8QDsjmb2ER0NUmTO89TVJTC8ED26nd5cQFFRnD0MDt4E60QpTK+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:29:25.169746Z"},"content_sha256":"135c4d6fea94e3afd2de48a04904cecf7151a579da0fe85fc6beb55d2e53367d","schema_version":"1.0","event_id":"sha256:135c4d6fea94e3afd2de48a04904cecf7151a579da0fe85fc6beb55d2e53367d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:B3RCSLPZX6QWAXRRBIUD2GAVJQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-modal Situated Reasoning in 3D Scenes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Baoxiong Jia, Jiangyong Huang, Siyuan Huang, Xiaojian Ma, Xiongkun Linghu, Xuesong Niu","submitted_at":"2024-09-04T02:37:38Z","abstract_excerpt":"Situation awareness is essential for understanding and reasoning about 3D scenes in embodied AI agents. However, existing datasets and benchmarks for situated understanding are limited in data modality, diversity, scale, and task scope. To address these limitations, we propose Multi-modal Situated Question Answering (MSQA), a large-scale multi-modal situated reasoning dataset, scalably collected leveraging 3D scene graphs and vision-language models (VLMs) across a diverse range of real-world 3D scenes. MSQA includes 251K situated question-answering pairs across 9 distinct question categories, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02389","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/2409.02389/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":"2026-07-05T09:36:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iZ76s+w+Fgsu+kHu4hZAEorvNfGh34LorXUIcPXqi44dmXKqOdUmhY+q/pfSf2zY9MSqZIDo7qurX0BftmISDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:29:25.170256Z"},"content_sha256":"6ef85c887845cd54eff2dace656eb3ef6817ce564bfa03c30c9bd721c5117b92","schema_version":"1.0","event_id":"sha256:6ef85c887845cd54eff2dace656eb3ef6817ce564bfa03c30c9bd721c5117b92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B3RCSLPZX6QWAXRRBIUD2GAVJQ/bundle.json","state_url":"https://pith.science/pith/B3RCSLPZX6QWAXRRBIUD2GAVJQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B3RCSLPZX6QWAXRRBIUD2GAVJQ/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":"2026-08-10T10:29:25Z","links":{"resolver":"https://pith.science/pith/B3RCSLPZX6QWAXRRBIUD2GAVJQ","bundle":"https://pith.science/pith/B3RCSLPZX6QWAXRRBIUD2GAVJQ/bundle.json","state":"https://pith.science/pith/B3RCSLPZX6QWAXRRBIUD2GAVJQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B3RCSLPZX6QWAXRRBIUD2GAVJQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B3RCSLPZX6QWAXRRBIUD2GAVJQ","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":"6da697fa9a18ce0a00ad0d2d4b8e649c5df686ed01399d5bedd941139e772a8b","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-04T02:37:38Z","title_canon_sha256":"2b7bc5c6a53903b33f908da43f952a1c2bd373bacfae54b20ac54cca0f83bd48"},"schema_version":"1.0","source":{"id":"2409.02389","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02389","created_at":"2026-07-05T09:36:48Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02389v2","created_at":"2026-07-05T09:36:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02389","created_at":"2026-07-05T09:36:48Z"},{"alias_kind":"pith_short_12","alias_value":"B3RCSLPZX6QW","created_at":"2026-07-05T09:36:48Z"},{"alias_kind":"pith_short_16","alias_value":"B3RCSLPZX6QWAXRR","created_at":"2026-07-05T09:36:48Z"},{"alias_kind":"pith_short_8","alias_value":"B3RCSLPZ","created_at":"2026-07-05T09:36:48Z"}],"graph_snapshots":[{"event_id":"sha256:6ef85c887845cd54eff2dace656eb3ef6817ce564bfa03c30c9bd721c5117b92","target":"graph","created_at":"2026-07-05T09:36:48Z","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/2409.02389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Situation awareness is essential for understanding and reasoning about 3D scenes in embodied AI agents. However, existing datasets and benchmarks for situated understanding are limited in data modality, diversity, scale, and task scope. To address these limitations, we propose Multi-modal Situated Question Answering (MSQA), a large-scale multi-modal situated reasoning dataset, scalably collected leveraging 3D scene graphs and vision-language models (VLMs) across a diverse range of real-world 3D scenes. MSQA includes 251K situated question-answering pairs across 9 distinct question categories, ","authors_text":"Baoxiong Jia, Jiangyong Huang, Siyuan Huang, Xiaojian Ma, Xiongkun Linghu, Xuesong Niu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-04T02:37:38Z","title":"Multi-modal Situated Reasoning in 3D Scenes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02389","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":"sha256:135c4d6fea94e3afd2de48a04904cecf7151a579da0fe85fc6beb55d2e53367d","target":"record","created_at":"2026-07-05T09:36:48Z","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":"6da697fa9a18ce0a00ad0d2d4b8e649c5df686ed01399d5bedd941139e772a8b","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-04T02:37:38Z","title_canon_sha256":"2b7bc5c6a53903b33f908da43f952a1c2bd373bacfae54b20ac54cca0f83bd48"},"schema_version":"1.0","source":{"id":"2409.02389","kind":"arxiv","version":2}},"canonical_sha256":"0ee2292df9bfa1605e310a283d18154c314754dc0d492456c6571dbfa8f552a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ee2292df9bfa1605e310a283d18154c314754dc0d492456c6571dbfa8f552a3","first_computed_at":"2026-07-05T09:36:48.027480Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:48.027480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I4pcQd9Xu8nUEIHPvTO4TQLUZP6dU2wV7KdIbIC7umduKqUK1ldj9PGCTDl8I1Ls/dSjaR3N1RTfvkc+3bozCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:48.027941Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.02389","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:135c4d6fea94e3afd2de48a04904cecf7151a579da0fe85fc6beb55d2e53367d","sha256:6ef85c887845cd54eff2dace656eb3ef6817ce564bfa03c30c9bd721c5117b92"],"state_sha256":"4470738eb2845026bd672e54c7e7c2b3dd91245689a3d62dd1f3970e00b2376f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yr5vZXIWlEAZVN2SqVNobIzuxunIsrNkZQPb6ftvuEhMlUZgKQNMacpR5vB5VIMm87Gvkx3hIN62IWfg/bkHDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:29:25.175219Z","bundle_sha256":"6c42acd92e27883b10c6abc0cd4fa4ace9344ff52401e34beee77ba654fbf824"}}