{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HUVIGOD3IXTK72VGLTGIVTMTBK","short_pith_number":"pith:HUVIGOD3","canonical_record":{"source":{"id":"2608.02980","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T00:32:09Z","cross_cats_sorted":[],"title_canon_sha256":"41bd64fc927c9b10536d599b925101acf9bfedee2cceb24ed0ab27e76fa3a6df","abstract_canon_sha256":"f23c12303f5e61ebc4aa14e3856af878bb27ba3be6f413efd6d0542b08a8ef73"},"schema_version":"1.0"},"canonical_sha256":"3d2a83387b45e6afeaa65ccc8acd930a99689d3d50d796019e901456dcfdc67b","source":{"kind":"arxiv","id":"2608.02980","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02980","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02980v1","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02980","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"pith_short_12","alias_value":"HUVIGOD3IXTK","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"pith_short_16","alias_value":"HUVIGOD3IXTK72VG","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"pith_short_8","alias_value":"HUVIGOD3","created_at":"2026-08-05T00:44:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HUVIGOD3IXTK72VGLTGIVTMTBK","target":"record","payload":{"canonical_record":{"source":{"id":"2608.02980","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T00:32:09Z","cross_cats_sorted":[],"title_canon_sha256":"41bd64fc927c9b10536d599b925101acf9bfedee2cceb24ed0ab27e76fa3a6df","abstract_canon_sha256":"f23c12303f5e61ebc4aa14e3856af878bb27ba3be6f413efd6d0542b08a8ef73"},"schema_version":"1.0"},"canonical_sha256":"3d2a83387b45e6afeaa65ccc8acd930a99689d3d50d796019e901456dcfdc67b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:44:19.025650Z","signature_b64":"4Ims8JTZvnzmQaMbL/0c9BtclJkUT7XIbk7DFRT98n8X+JPOyzJg/HubpkbmlxK0mFrVzcMjCQI7i0PWlVFmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d2a83387b45e6afeaa65ccc8acd930a99689d3d50d796019e901456dcfdc67b","last_reissued_at":"2026-08-05T00:44:19.023059Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:44:19.023059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.02980","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":"2026-08-05T00:44:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"27b5w2IptdIp725g3lQPHrXyWvgdErqh1vKrLU4Bd/EFsKmGsGLDPa/Uc6JUq2hldnP9/7u8Rno8SKN9T4sjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T00:10:50.607371Z"},"content_sha256":"8284b3f43960519ea920815e9833f56395546e6fa5337b7982de9e15686850a9","schema_version":"1.0","event_id":"sha256:8284b3f43960519ea920815e9833f56395546e6fa5337b7982de9e15686850a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HUVIGOD3IXTK72VGLTGIVTMTBK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayush Jain, Katerina Fragkiadaki, Lucy Lin, Yifan Liu","submitted_at":"2026-08-04T00:32:09Z","abstract_excerpt":"Large Multimodal Models (LMMs) have achieved remarkable success on images and short videos, yet scaling them to long videos remains challenging due to frame-centric tokenization and limited context windows. 3D geometry provides a natural compression mechanism for visual streams: depth and camera pose enable observations from multiple views and time steps to be fused into a persistent, world-aligned representation. While recent 3D LMMs leverage geometry-aware representations to improve spatial reasoning, they continue to lag behind specialist 3D perception systems on grounding and segmentation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02980","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/2608.02980/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":"2026-08-05T00:44:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sqX5nZHc+yNSvJ9lqnOgvsKzbT2fuj8Ad1boISz+pBb6P2BubX6yWyLUQu3lyoVSwYjjGa6MESeatgY05iN3Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T00:10:50.607972Z"},"content_sha256":"5a1dcbd59ef8a7713374259fbcb39a5a254913b26b350070d712e98a92875171","schema_version":"1.0","event_id":"sha256:5a1dcbd59ef8a7713374259fbcb39a5a254913b26b350070d712e98a92875171"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HUVIGOD3IXTK72VGLTGIVTMTBK/bundle.json","state_url":"https://pith.science/pith/HUVIGOD3IXTK72VGLTGIVTMTBK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HUVIGOD3IXTK72VGLTGIVTMTBK/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":"2026-08-14T00:10:50Z","links":{"resolver":"https://pith.science/pith/HUVIGOD3IXTK72VGLTGIVTMTBK","bundle":"https://pith.science/pith/HUVIGOD3IXTK72VGLTGIVTMTBK/bundle.json","state":"https://pith.science/pith/HUVIGOD3IXTK72VGLTGIVTMTBK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HUVIGOD3IXTK72VGLTGIVTMTBK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HUVIGOD3IXTK72VGLTGIVTMTBK","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":"f23c12303f5e61ebc4aa14e3856af878bb27ba3be6f413efd6d0542b08a8ef73","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T00:32:09Z","title_canon_sha256":"41bd64fc927c9b10536d599b925101acf9bfedee2cceb24ed0ab27e76fa3a6df"},"schema_version":"1.0","source":{"id":"2608.02980","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02980","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02980v1","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02980","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"pith_short_12","alias_value":"HUVIGOD3IXTK","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"pith_short_16","alias_value":"HUVIGOD3IXTK72VG","created_at":"2026-08-05T00:44:19Z"},{"alias_kind":"pith_short_8","alias_value":"HUVIGOD3","created_at":"2026-08-05T00:44:19Z"}],"graph_snapshots":[{"event_id":"sha256:5a1dcbd59ef8a7713374259fbcb39a5a254913b26b350070d712e98a92875171","target":"graph","created_at":"2026-08-05T00:44:19Z","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/2608.02980/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Multimodal Models (LMMs) have achieved remarkable success on images and short videos, yet scaling them to long videos remains challenging due to frame-centric tokenization and limited context windows. 3D geometry provides a natural compression mechanism for visual streams: depth and camera pose enable observations from multiple views and time steps to be fused into a persistent, world-aligned representation. While recent 3D LMMs leverage geometry-aware representations to improve spatial reasoning, they continue to lag behind specialist 3D perception systems on grounding and segmentation ","authors_text":"Ayush Jain, Katerina Fragkiadaki, Lucy Lin, Yifan Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T00:32:09Z","title":"Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02980","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":"sha256:8284b3f43960519ea920815e9833f56395546e6fa5337b7982de9e15686850a9","target":"record","created_at":"2026-08-05T00:44:19Z","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":"f23c12303f5e61ebc4aa14e3856af878bb27ba3be6f413efd6d0542b08a8ef73","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T00:32:09Z","title_canon_sha256":"41bd64fc927c9b10536d599b925101acf9bfedee2cceb24ed0ab27e76fa3a6df"},"schema_version":"1.0","source":{"id":"2608.02980","kind":"arxiv","version":1}},"canonical_sha256":"3d2a83387b45e6afeaa65ccc8acd930a99689d3d50d796019e901456dcfdc67b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d2a83387b45e6afeaa65ccc8acd930a99689d3d50d796019e901456dcfdc67b","first_computed_at":"2026-08-05T00:44:19.023059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:44:19.023059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4Ims8JTZvnzmQaMbL/0c9BtclJkUT7XIbk7DFRT98n8X+JPOyzJg/HubpkbmlxK0mFrVzcMjCQI7i0PWlVFmDw==","signature_status":"signed_v1","signed_at":"2026-08-05T00:44:19.025650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02980","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8284b3f43960519ea920815e9833f56395546e6fa5337b7982de9e15686850a9","sha256:5a1dcbd59ef8a7713374259fbcb39a5a254913b26b350070d712e98a92875171"],"state_sha256":"94ca1c280de1c27c94ba6f89ecba7853f4235701db9345116e71cf8abb6a675b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DUQtF+tZgZz0596VRDf4fPKTfA21yb3YXIA9sNjjLlNCz9FyN+e9JUAxpvzzpJ7YbA59vrUW3RV2Rfvvi1uqDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T00:10:50.639994Z","bundle_sha256":"213f3792a5e558b77f667d61f44eec4983978b65aeebe43a65b31f06c485b72f"}}