{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HW6NEU34MVI4SBUB2DVZV6GN4J","short_pith_number":"pith:HW6NEU34","canonical_record":{"source":{"id":"2501.07819","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T03:50:23Z","cross_cats_sorted":[],"title_canon_sha256":"25fe5a083c3b4529c380455d77af9b8af2c86593f4d4079add2882c5374bb81e","abstract_canon_sha256":"69ffa7f977cf2269cbf032e078c93b92d0fa16fdb293e696c179eb3530c3a433"},"schema_version":"1.0"},"canonical_sha256":"3dbcd2537c6551c90681d0eb9af8cde27c712886ac2fab481fb476af9376baeb","source":{"kind":"arxiv","id":"2501.07819","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07819","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07819v1","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07819","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_12","alias_value":"HW6NEU34MVI4","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_16","alias_value":"HW6NEU34MVI4SBUB","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_8","alias_value":"HW6NEU34","created_at":"2026-07-05T10:00:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HW6NEU34MVI4SBUB2DVZV6GN4J","target":"record","payload":{"canonical_record":{"source":{"id":"2501.07819","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T03:50:23Z","cross_cats_sorted":[],"title_canon_sha256":"25fe5a083c3b4529c380455d77af9b8af2c86593f4d4079add2882c5374bb81e","abstract_canon_sha256":"69ffa7f977cf2269cbf032e078c93b92d0fa16fdb293e696c179eb3530c3a433"},"schema_version":"1.0"},"canonical_sha256":"3dbcd2537c6551c90681d0eb9af8cde27c712886ac2fab481fb476af9376baeb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:50.633460Z","signature_b64":"Tu4OkOsU06FMBb7ZHPy1J9BwSEZ4ipRyiYj32oDks4o//23Np/98WFLtaeu4T8zCu+hHubnaKwCaPhwXI6p0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dbcd2537c6551c90681d0eb9af8cde27c712886ac2fab481fb476af9376baeb","last_reissued_at":"2026-07-05T10:00:50.632912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:50.632912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.07819","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:00:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bnNghsCHE1ufWOAFrLryAgeR/KUD0uiJfcmYEu/zx7OnPgsEsA9FXjxkS/7KX8f8NajnmrImCahOxzeM+7R4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:46:42.471505Z"},"content_sha256":"cb0bee9b4d75d62f95ace885186b81d2cb3d965b9b89b5a6633695d4da88e000","schema_version":"1.0","event_id":"sha256:cb0bee9b4d75d62f95ace885186b81d2cb3d965b9b89b5a6633695d4da88e000"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HW6NEU34MVI4SBUB2DVZV6GN4J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haomiao Xiong, Huchuan Lu, Jiawen Zhu, Lu Zhang, Yunzhi Zhuge","submitted_at":"2025-01-14T03:50:23Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) exhibit impressive capabilities in 2D tasks, yet encounter challenges in discerning the spatial positions, interrelations, and causal logic in scenes when transitioning from 2D to 3D representations. We find that the limitations mainly lie in: i) the high annotation cost restricting the scale-up of volumes of 3D scene data, and ii) the lack of a straightforward and effective way to perceive 3D information which results in prolonged training durations and complicates the streamlined framework. To this end, we develop pipeline based on open-source 2D MLL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07819","kind":"arxiv","version":1},"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/2501.07819/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":"2026-07-05T10:00:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XuN9UAwrROQiBGv8mKpacYeGfnybUBBrToCh/hxqdXBVgurM1Xpzup00GNB0awCYYl6OPr7pBmnCSxQw6xLdAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:46:42.472473Z"},"content_sha256":"5c136c31070c3fd97c22f23de4c6e963c01d5c1a14088619c31ed83051369b96","schema_version":"1.0","event_id":"sha256:5c136c31070c3fd97c22f23de4c6e963c01d5c1a14088619c31ed83051369b96"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HW6NEU34MVI4SBUB2DVZV6GN4J/bundle.json","state_url":"https://pith.science/pith/HW6NEU34MVI4SBUB2DVZV6GN4J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HW6NEU34MVI4SBUB2DVZV6GN4J/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":"2026-08-10T20:46:42Z","links":{"resolver":"https://pith.science/pith/HW6NEU34MVI4SBUB2DVZV6GN4J","bundle":"https://pith.science/pith/HW6NEU34MVI4SBUB2DVZV6GN4J/bundle.json","state":"https://pith.science/pith/HW6NEU34MVI4SBUB2DVZV6GN4J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HW6NEU34MVI4SBUB2DVZV6GN4J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HW6NEU34MVI4SBUB2DVZV6GN4J","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":"69ffa7f977cf2269cbf032e078c93b92d0fa16fdb293e696c179eb3530c3a433","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T03:50:23Z","title_canon_sha256":"25fe5a083c3b4529c380455d77af9b8af2c86593f4d4079add2882c5374bb81e"},"schema_version":"1.0","source":{"id":"2501.07819","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07819","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07819v1","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07819","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_12","alias_value":"HW6NEU34MVI4","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_16","alias_value":"HW6NEU34MVI4SBUB","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_8","alias_value":"HW6NEU34","created_at":"2026-07-05T10:00:50Z"}],"graph_snapshots":[{"event_id":"sha256:5c136c31070c3fd97c22f23de4c6e963c01d5c1a14088619c31ed83051369b96","target":"graph","created_at":"2026-07-05T10:00:50Z","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/2501.07819/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal Large Language Models (MLLMs) exhibit impressive capabilities in 2D tasks, yet encounter challenges in discerning the spatial positions, interrelations, and causal logic in scenes when transitioning from 2D to 3D representations. We find that the limitations mainly lie in: i) the high annotation cost restricting the scale-up of volumes of 3D scene data, and ii) the lack of a straightforward and effective way to perceive 3D information which results in prolonged training durations and complicates the streamlined framework. To this end, we develop pipeline based on open-source 2D MLL","authors_text":"Haomiao Xiong, Huchuan Lu, Jiawen Zhu, Lu Zhang, Yunzhi Zhuge","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T03:50:23Z","title":"3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07819","kind":"arxiv","version":1},"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:cb0bee9b4d75d62f95ace885186b81d2cb3d965b9b89b5a6633695d4da88e000","target":"record","created_at":"2026-07-05T10:00:50Z","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":"69ffa7f977cf2269cbf032e078c93b92d0fa16fdb293e696c179eb3530c3a433","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T03:50:23Z","title_canon_sha256":"25fe5a083c3b4529c380455d77af9b8af2c86593f4d4079add2882c5374bb81e"},"schema_version":"1.0","source":{"id":"2501.07819","kind":"arxiv","version":1}},"canonical_sha256":"3dbcd2537c6551c90681d0eb9af8cde27c712886ac2fab481fb476af9376baeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3dbcd2537c6551c90681d0eb9af8cde27c712886ac2fab481fb476af9376baeb","first_computed_at":"2026-07-05T10:00:50.632912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:50.632912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tu4OkOsU06FMBb7ZHPy1J9BwSEZ4ipRyiYj32oDks4o//23Np/98WFLtaeu4T8zCu+hHubnaKwCaPhwXI6p0DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:50.633460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07819","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb0bee9b4d75d62f95ace885186b81d2cb3d965b9b89b5a6633695d4da88e000","sha256:5c136c31070c3fd97c22f23de4c6e963c01d5c1a14088619c31ed83051369b96"],"state_sha256":"e274e4752c99dcb4abc1311df4c26208a9244fd3f7044cfe6ca7a08e1e930031"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WuehqVFuZ9SvGHUCF6NjwzTApbZo59ImN31lm0iT+uDfDeJtbbkl3/nCOroDIedfyq4kmcOk8fPajyd5q8JRDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T20:46:42.480320Z","bundle_sha256":"5a5edea1541a23b8f66ed3c6cb8418543d67e8a7f9864edb16a6d0323bd1dc7c"}}