{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OJSR747US7T5HIOS6SD44M5QP6","short_pith_number":"pith:OJSR747U","canonical_record":{"source":{"id":"2607.28442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:14:30Z","cross_cats_sorted":[],"title_canon_sha256":"396e7fede05eefda420d4438821310bc9ffec32e36f712d15455f0a23fcf8ec9","abstract_canon_sha256":"d8d235c2fac9d9d8220056b6ec782323056e52916feac85e17dfd8bb127b634b"},"schema_version":"1.0"},"canonical_sha256":"72651ff3f497e7d3a1d2f487ce33b07f86d990443578e3a6bb647c10f5f4fa2b","source":{"kind":"arxiv","id":"2607.28442","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28442","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28442v1","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28442","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"pith_short_12","alias_value":"OJSR747US7T5","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"pith_short_16","alias_value":"OJSR747US7T5HIOS","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"pith_short_8","alias_value":"OJSR747U","created_at":"2026-07-31T01:37:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OJSR747US7T5HIOS6SD44M5QP6","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:14:30Z","cross_cats_sorted":[],"title_canon_sha256":"396e7fede05eefda420d4438821310bc9ffec32e36f712d15455f0a23fcf8ec9","abstract_canon_sha256":"d8d235c2fac9d9d8220056b6ec782323056e52916feac85e17dfd8bb127b634b"},"schema_version":"1.0"},"canonical_sha256":"72651ff3f497e7d3a1d2f487ce33b07f86d990443578e3a6bb647c10f5f4fa2b","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72651ff3f497e7d3a1d2f487ce33b07f86d990443578e3a6bb647c10f5f4fa2b","last_reissued_at":"2026-07-31T01:37:39.024913Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:37:39.024913Z"},"source_kind":"arxiv","source_id":"2607.28442","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":"2026-07-31T01:37:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KA3NnderAhL3Kp+DZLOPV/Jyz3JfFj+3dHJNBYef/9P9E3DTfzyivWP6shHX8aw1cwtY7HDhmiVGDrcoKIm3Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:27:58.694818Z"},"content_sha256":"aeffd0549a1d4fc24a3c4a4b94ee7397ad0fbb6151be62479563991da14c21f6","schema_version":"1.0","event_id":"sha256:aeffd0549a1d4fc24a3c4a4b94ee7397ad0fbb6151be62479563991da14c21f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OJSR747US7T5HIOS6SD44M5QP6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ViewMind3D: Modular View-Aware Inference for Training-Free 3D-QA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kun-Ru Wu, Ping-Kun Chiang, Po-han Li, Sandeep Chinchali, Ufuk Topcu, Yu-Chee Tseng","submitted_at":"2026-07-30T16:14:30Z","abstract_excerpt":"Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled new possibilities for 3D question answering (3D-QA), a key capability for embodied AI and robotic perception. However, most existing methods rely on 3D-specific training or fine-tuning with costly annotations, limiting their scalability and real-world applicability. We present \\textbf{ViewMind3D}, a fully training-free and modular framework for 3D spatial reasoning over multi-view observations of a scene without requiring complete 3D reconstruction. The framework decomposes the 3D-QA task into four i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28442","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/2607.28442/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":"2026-07-31T01:37:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUujM03Sq594aKz3USTcK0vOS/QxmDTSmwRunuaGm199KRGpCRclbv3e9K0HNpW5uoZrwasGumwzE8DlJHJ2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:27:58.695347Z"},"content_sha256":"f2db0babfb6e3272e8777be9ca6fd65543144481b992873256df716e265a6a7f","schema_version":"1.0","event_id":"sha256:f2db0babfb6e3272e8777be9ca6fd65543144481b992873256df716e265a6a7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OJSR747US7T5HIOS6SD44M5QP6/bundle.json","state_url":"https://pith.science/pith/OJSR747US7T5HIOS6SD44M5QP6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OJSR747US7T5HIOS6SD44M5QP6/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":"2026-08-04T03:27:58Z","links":{"resolver":"https://pith.science/pith/OJSR747US7T5HIOS6SD44M5QP6","bundle":"https://pith.science/pith/OJSR747US7T5HIOS6SD44M5QP6/bundle.json","state":"https://pith.science/pith/OJSR747US7T5HIOS6SD44M5QP6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OJSR747US7T5HIOS6SD44M5QP6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OJSR747US7T5HIOS6SD44M5QP6","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":"d8d235c2fac9d9d8220056b6ec782323056e52916feac85e17dfd8bb127b634b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:14:30Z","title_canon_sha256":"396e7fede05eefda420d4438821310bc9ffec32e36f712d15455f0a23fcf8ec9"},"schema_version":"1.0","source":{"id":"2607.28442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28442","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28442v1","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28442","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"pith_short_12","alias_value":"OJSR747US7T5","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"pith_short_16","alias_value":"OJSR747US7T5HIOS","created_at":"2026-07-31T01:37:39Z"},{"alias_kind":"pith_short_8","alias_value":"OJSR747U","created_at":"2026-07-31T01:37:39Z"}],"graph_snapshots":[{"event_id":"sha256:f2db0babfb6e3272e8777be9ca6fd65543144481b992873256df716e265a6a7f","target":"graph","created_at":"2026-07-31T01:37:39Z","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/2607.28442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled new possibilities for 3D question answering (3D-QA), a key capability for embodied AI and robotic perception. However, most existing methods rely on 3D-specific training or fine-tuning with costly annotations, limiting their scalability and real-world applicability. We present \\textbf{ViewMind3D}, a fully training-free and modular framework for 3D spatial reasoning over multi-view observations of a scene without requiring complete 3D reconstruction. The framework decomposes the 3D-QA task into four i","authors_text":"Kun-Ru Wu, Ping-Kun Chiang, Po-han Li, Sandeep Chinchali, Ufuk Topcu, Yu-Chee Tseng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:14:30Z","title":"ViewMind3D: Modular View-Aware Inference for Training-Free 3D-QA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28442","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:aeffd0549a1d4fc24a3c4a4b94ee7397ad0fbb6151be62479563991da14c21f6","target":"record","created_at":"2026-07-31T01:37:39Z","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":"d8d235c2fac9d9d8220056b6ec782323056e52916feac85e17dfd8bb127b634b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:14:30Z","title_canon_sha256":"396e7fede05eefda420d4438821310bc9ffec32e36f712d15455f0a23fcf8ec9"},"schema_version":"1.0","source":{"id":"2607.28442","kind":"arxiv","version":1}},"canonical_sha256":"72651ff3f497e7d3a1d2f487ce33b07f86d990443578e3a6bb647c10f5f4fa2b","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72651ff3f497e7d3a1d2f487ce33b07f86d990443578e3a6bb647c10f5f4fa2b","first_computed_at":"2026-07-31T01:37:39.024913Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:37:39.024913Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aeffd0549a1d4fc24a3c4a4b94ee7397ad0fbb6151be62479563991da14c21f6","sha256:f2db0babfb6e3272e8777be9ca6fd65543144481b992873256df716e265a6a7f"],"state_sha256":"d57907db3ad977cef8abbcf107c3fc366e68a8bb106c422dcfa4f88ee4f4df85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lp7+4Tese0tLDl/VRsMRgaUNVoC5ctteq7k5jxwxNqc9Uxf3tIn38gzbcAtKlOQWcXmoWns+PEW3d6hAygh/Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:27:58.700604Z","bundle_sha256":"a22b01c01304df88125ac5ea48a97bfc1785f0db987347414053106cfeb66240"}}