{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OT5ND4W7NBVJIRSVEHWVEEZWOV","short_pith_number":"pith:OT5ND4W7","canonical_record":{"source":{"id":"2605.30231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:00:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fa84491d1e435ea286e16d665807e872ae05565d2c65e102e1d8c0f3ca7d9410","abstract_canon_sha256":"2eb224b62cb69eac29800204714562596cd106e0f78fe211c9e5cc3be5c74aff"},"schema_version":"1.0"},"canonical_sha256":"74fad1f2df686a94465521ed5213367579d27d2bb002a145a0525544d301cb2a","source":{"kind":"arxiv","id":"2605.30231","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30231","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30231v1","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30231","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"pith_short_12","alias_value":"OT5ND4W7NBVJ","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"pith_short_16","alias_value":"OT5ND4W7NBVJIRSV","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"pith_short_8","alias_value":"OT5ND4W7","created_at":"2026-05-29T02:06:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OT5ND4W7NBVJIRSVEHWVEEZWOV","target":"record","payload":{"canonical_record":{"source":{"id":"2605.30231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:00:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fa84491d1e435ea286e16d665807e872ae05565d2c65e102e1d8c0f3ca7d9410","abstract_canon_sha256":"2eb224b62cb69eac29800204714562596cd106e0f78fe211c9e5cc3be5c74aff"},"schema_version":"1.0"},"canonical_sha256":"74fad1f2df686a94465521ed5213367579d27d2bb002a145a0525544d301cb2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:13.482307Z","signature_b64":"UkU412YZ3vcjdAjLSZvDWGut6/0ggpnBeKFxu1Q+JIGmkvfLLUFYbZ+Lz0aA/oHZSChkyCbeMwax/yckDfLdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74fad1f2df686a94465521ed5213367579d27d2bb002a145a0525544d301cb2a","last_reissued_at":"2026-05-29T02:06:13.481928Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:13.481928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.30231","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":"2026-05-29T02:06:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SghrHlJT6d++8pkmr3aHat+t3YoIVV1GO4Ts+gZ07/8/plWvRLZPWubXrYdOciK22M5NosYK0EXPpcPOHUmoAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T17:54:03.114098Z"},"content_sha256":"7d8c0e391efc4d05ff7278dbcd4819d1f1e445ad12bf4b754f44fc54d2c4b920","schema_version":"1.0","event_id":"sha256:7d8c0e391efc4d05ff7278dbcd4819d1f1e445ad12bf4b754f44fc54d2c4b920"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OT5ND4W7NBVJIRSVEHWVEEZWOV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chun-Hsiao Yeh, Fanyi Xiao, Joseph Tighe, Manchen Wang, Shengyi Qian, Yi Ma","submitted_at":"2026-05-28T17:00:52Z","abstract_excerpt":"Vision-Language Models (VLMs) often struggle with robust 3D spatial reasoning. Prevailing methods that rely on fine-tuning with 3D visual question-answering (VQA) datasets may overfit dataset-specific biases, while integrating specialized 3D visual encoders is often inflexible and cumbersome. In this paper, we argue that genuine spatial understanding should emerge from learning fundamental geometric priors, not only from high-level VQA supervision. We propose GASP (Geometric-Aware Spatial Priors), a framework that injects these priors directly into the LLM's transformer layers. GASP employs a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30231","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/2605.30231/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":"2026-05-29T02:06:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9sgzdwgyGJV8JfQ0w5LUumzNbrdAIQJ1P6BaY2vav6Jn+Hgq0LLr1zJ88V0INP4iLgyFxHgq/wHSNSqJ70OoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T17:54:03.114497Z"},"content_sha256":"c5a69c9cf8607e700e547875d2998ed3897b1cad547ba4e02ff0dd3d9ae583ed","schema_version":"1.0","event_id":"sha256:c5a69c9cf8607e700e547875d2998ed3897b1cad547ba4e02ff0dd3d9ae583ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OT5ND4W7NBVJIRSVEHWVEEZWOV/bundle.json","state_url":"https://pith.science/pith/OT5ND4W7NBVJIRSVEHWVEEZWOV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OT5ND4W7NBVJIRSVEHWVEEZWOV/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":"2026-06-02T17:54:03Z","links":{"resolver":"https://pith.science/pith/OT5ND4W7NBVJIRSVEHWVEEZWOV","bundle":"https://pith.science/pith/OT5ND4W7NBVJIRSVEHWVEEZWOV/bundle.json","state":"https://pith.science/pith/OT5ND4W7NBVJIRSVEHWVEEZWOV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OT5ND4W7NBVJIRSVEHWVEEZWOV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OT5ND4W7NBVJIRSVEHWVEEZWOV","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":"2eb224b62cb69eac29800204714562596cd106e0f78fe211c9e5cc3be5c74aff","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:00:52Z","title_canon_sha256":"fa84491d1e435ea286e16d665807e872ae05565d2c65e102e1d8c0f3ca7d9410"},"schema_version":"1.0","source":{"id":"2605.30231","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30231","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30231v1","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30231","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"pith_short_12","alias_value":"OT5ND4W7NBVJ","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"pith_short_16","alias_value":"OT5ND4W7NBVJIRSV","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"pith_short_8","alias_value":"OT5ND4W7","created_at":"2026-05-29T02:06:13Z"}],"graph_snapshots":[{"event_id":"sha256:c5a69c9cf8607e700e547875d2998ed3897b1cad547ba4e02ff0dd3d9ae583ed","target":"graph","created_at":"2026-05-29T02:06:13Z","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/2605.30231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) often struggle with robust 3D spatial reasoning. Prevailing methods that rely on fine-tuning with 3D visual question-answering (VQA) datasets may overfit dataset-specific biases, while integrating specialized 3D visual encoders is often inflexible and cumbersome. In this paper, we argue that genuine spatial understanding should emerge from learning fundamental geometric priors, not only from high-level VQA supervision. We propose GASP (Geometric-Aware Spatial Priors), a framework that injects these priors directly into the LLM's transformer layers. GASP employs a ","authors_text":"Chun-Hsiao Yeh, Fanyi Xiao, Joseph Tighe, Manchen Wang, Shengyi Qian, Yi Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:00:52Z","title":"Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30231","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":"sha256:7d8c0e391efc4d05ff7278dbcd4819d1f1e445ad12bf4b754f44fc54d2c4b920","target":"record","created_at":"2026-05-29T02:06:13Z","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":"2eb224b62cb69eac29800204714562596cd106e0f78fe211c9e5cc3be5c74aff","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:00:52Z","title_canon_sha256":"fa84491d1e435ea286e16d665807e872ae05565d2c65e102e1d8c0f3ca7d9410"},"schema_version":"1.0","source":{"id":"2605.30231","kind":"arxiv","version":1}},"canonical_sha256":"74fad1f2df686a94465521ed5213367579d27d2bb002a145a0525544d301cb2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74fad1f2df686a94465521ed5213367579d27d2bb002a145a0525544d301cb2a","first_computed_at":"2026-05-29T02:06:13.481928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:13.481928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UkU412YZ3vcjdAjLSZvDWGut6/0ggpnBeKFxu1Q+JIGmkvfLLUFYbZ+Lz0aA/oHZSChkyCbeMwax/yckDfLdAw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:13.482307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30231","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d8c0e391efc4d05ff7278dbcd4819d1f1e445ad12bf4b754f44fc54d2c4b920","sha256:c5a69c9cf8607e700e547875d2998ed3897b1cad547ba4e02ff0dd3d9ae583ed"],"state_sha256":"b66d39b4107c176b357d5e52c179811a72bf25e71a3060e871b847cc54af60e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K/xRLvUAc+yTNQdoEeFK7kwaAYcPWYk7L3Ngu2nPgd2LJ1uq9/s7aZO0MmuG0TMzjgTZTsSEnOl0bg6NLBrACg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T17:54:03.116651Z","bundle_sha256":"a11851a8fbe2ee2747add298a44a78f8266b2cbe99ca82473709702a801cab26"}}