{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NFFS5B6Z6ELNXT6R6M7R52QEVP","short_pith_number":"pith:NFFS5B6Z","canonical_record":{"source":{"id":"2403.13438","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:38:29Z","cross_cats_sorted":[],"title_canon_sha256":"2a8a7e2a311e420d9f13e06df90a04a4ee5341bb18336568e60341bd26a66c0a","abstract_canon_sha256":"7dd95608aadcabd178094f3ad260214411324100460f85ee18a0a32fbc23287b"},"schema_version":"1.0"},"canonical_sha256":"694b2e87d9f116dbcfd1f33f1eea04abef4d681a2961643188d39f941ee85e65","source":{"kind":"arxiv","id":"2403.13438","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13438","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13438v5","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13438","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"pith_short_12","alias_value":"NFFS5B6Z6ELN","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"pith_short_16","alias_value":"NFFS5B6Z6ELNXT6R","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"pith_short_8","alias_value":"NFFS5B6Z","created_at":"2026-07-05T09:28:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NFFS5B6Z6ELNXT6R6M7R52QEVP","target":"record","payload":{"canonical_record":{"source":{"id":"2403.13438","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:38:29Z","cross_cats_sorted":[],"title_canon_sha256":"2a8a7e2a311e420d9f13e06df90a04a4ee5341bb18336568e60341bd26a66c0a","abstract_canon_sha256":"7dd95608aadcabd178094f3ad260214411324100460f85ee18a0a32fbc23287b"},"schema_version":"1.0"},"canonical_sha256":"694b2e87d9f116dbcfd1f33f1eea04abef4d681a2961643188d39f941ee85e65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:11.276009Z","signature_b64":"yXFq0oa1OyJ3FbmKWPENbKvZgR76jK9LDuVcZI0Pk2Fsgn+Dv+veSIancA63W/6z3TpH+j8vRXW5ZLQFz9XpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"694b2e87d9f116dbcfd1f33f1eea04abef4d681a2961643188d39f941ee85e65","last_reissued_at":"2026-07-05T09:28:11.275556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:11.275556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.13438","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:28:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OdJedpFSEkR7YXrzJ7BnlAOyWFkDxGN7m35Ti1arexbIUplLdODDCaxDtNjPoCYEvYH6hWOaDKj/NhB82Fi0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:38:52.114574Z"},"content_sha256":"070c50ee26e8e3c2a8c9bd31b3839bbd31be614524f8910e07e54b2285d7538c","schema_version":"1.0","event_id":"sha256:070c50ee26e8e3c2a8c9bd31b3839bbd31be614524f8910e07e54b2285d7538c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NFFS5B6Z6ELNXT6R6M7R52QEVP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Markham, Chenyang Ma, Kai Lu, Niki Trigoni, Ta-Ying Cheng","submitted_at":"2024-03-18T17:38:29Z","abstract_excerpt":"Current state-of-the-art spatial reasoning-enhanced VLMs are trained to excel at spatial visual question answering (VQA). However, we believe that higher-level 3D-aware tasks, such as articulating dynamic scene changes and motion planning, require a fundamental and explicit 3D understanding beyond current spatial VQA datasets. In this work, we present SpatialPIN, a framework designed to enhance the spatial reasoning capabilities of VLMs through prompting and interacting with priors from multiple 3D foundation models in a zero-shot, training-free manner. Extensive experiments demonstrate that o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13438","kind":"arxiv","version":5},"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/2403.13438/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":"2026-07-05T09:28:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uy4RhI1+GsV/o9wn5Y5hQrcLGqr8r432TY7ky6MQEYJG4S5MKPpevro4kjCZ/5u8IjHle7dT6+kS8OlZt1ZsDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:38:52.115084Z"},"content_sha256":"6cd0bad72a51d1f250b72f0ab852ad5efe21ac695e179b20efa05f470162dcf9","schema_version":"1.0","event_id":"sha256:6cd0bad72a51d1f250b72f0ab852ad5efe21ac695e179b20efa05f470162dcf9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP/bundle.json","state_url":"https://pith.science/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP/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":"2026-08-05T18:38:52Z","links":{"resolver":"https://pith.science/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP","bundle":"https://pith.science/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP/bundle.json","state":"https://pith.science/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NFFS5B6Z6ELNXT6R6M7R52QEVP","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":"7dd95608aadcabd178094f3ad260214411324100460f85ee18a0a32fbc23287b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:38:29Z","title_canon_sha256":"2a8a7e2a311e420d9f13e06df90a04a4ee5341bb18336568e60341bd26a66c0a"},"schema_version":"1.0","source":{"id":"2403.13438","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13438","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13438v5","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13438","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"pith_short_12","alias_value":"NFFS5B6Z6ELN","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"pith_short_16","alias_value":"NFFS5B6Z6ELNXT6R","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"pith_short_8","alias_value":"NFFS5B6Z","created_at":"2026-07-05T09:28:11Z"}],"graph_snapshots":[{"event_id":"sha256:6cd0bad72a51d1f250b72f0ab852ad5efe21ac695e179b20efa05f470162dcf9","target":"graph","created_at":"2026-07-05T09:28:11Z","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/2403.13438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current state-of-the-art spatial reasoning-enhanced VLMs are trained to excel at spatial visual question answering (VQA). However, we believe that higher-level 3D-aware tasks, such as articulating dynamic scene changes and motion planning, require a fundamental and explicit 3D understanding beyond current spatial VQA datasets. In this work, we present SpatialPIN, a framework designed to enhance the spatial reasoning capabilities of VLMs through prompting and interacting with priors from multiple 3D foundation models in a zero-shot, training-free manner. Extensive experiments demonstrate that o","authors_text":"Andrew Markham, Chenyang Ma, Kai Lu, Niki Trigoni, Ta-Ying Cheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:38:29Z","title":"SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13438","kind":"arxiv","version":5},"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":"sha256:070c50ee26e8e3c2a8c9bd31b3839bbd31be614524f8910e07e54b2285d7538c","target":"record","created_at":"2026-07-05T09:28:11Z","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":"7dd95608aadcabd178094f3ad260214411324100460f85ee18a0a32fbc23287b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:38:29Z","title_canon_sha256":"2a8a7e2a311e420d9f13e06df90a04a4ee5341bb18336568e60341bd26a66c0a"},"schema_version":"1.0","source":{"id":"2403.13438","kind":"arxiv","version":5}},"canonical_sha256":"694b2e87d9f116dbcfd1f33f1eea04abef4d681a2961643188d39f941ee85e65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"694b2e87d9f116dbcfd1f33f1eea04abef4d681a2961643188d39f941ee85e65","first_computed_at":"2026-07-05T09:28:11.275556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:11.275556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yXFq0oa1OyJ3FbmKWPENbKvZgR76jK9LDuVcZI0Pk2Fsgn+Dv+veSIancA63W/6z3TpH+j8vRXW5ZLQFz9XpCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:11.276009Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.13438","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:070c50ee26e8e3c2a8c9bd31b3839bbd31be614524f8910e07e54b2285d7538c","sha256:6cd0bad72a51d1f250b72f0ab852ad5efe21ac695e179b20efa05f470162dcf9"],"state_sha256":"77745c97bcdac4207d82af8491afd6826a199e16809051a51958d2e2836615d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ha4DB6M8QHU85dRnyUmN4JWI8CeY7tmlNjK50c5E9YsW6x4bSCJTCmwJDbFBVa6Bckc5Vm6UVy+2nJxrkVqAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:38:52.118537Z","bundle_sha256":"9093a031db7d6c2bf18074d3416995138ca8b0dbdacbd39aa8445b4922ccac2f"}}