{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NW52DGDDMD3FVFB37FQGL4KE4R","short_pith_number":"pith:NW52DGDD","canonical_record":{"source":{"id":"2608.10864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T12:34:41Z","cross_cats_sorted":[],"title_canon_sha256":"7f9db3b8b9fd51c652396c3feddf12c80c41d50f351bb6cd440e2895d0cce651","abstract_canon_sha256":"0a532327492dde5a344f9e1b1c37f85041209a3faeca31cbd43578655097c79e"},"schema_version":"1.0"},"canonical_sha256":"6dbba1986360f65a943bf96065f144e47758f4f398a61eac11a526205ea21a38","source":{"kind":"arxiv","id":"2608.10864","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10864","created_at":"2026-08-12T01:23:37Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10864v1","created_at":"2026-08-12T01:23:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10864","created_at":"2026-08-12T01:23:37Z"},{"alias_kind":"pith_short_12","alias_value":"NW52DGDDMD3F","created_at":"2026-08-12T01:23:37Z"},{"alias_kind":"pith_short_16","alias_value":"NW52DGDDMD3FVFB3","created_at":"2026-08-12T01:23:37Z"},{"alias_kind":"pith_short_8","alias_value":"NW52DGDD","created_at":"2026-08-12T01:23:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NW52DGDDMD3FVFB37FQGL4KE4R","target":"record","payload":{"canonical_record":{"source":{"id":"2608.10864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T12:34:41Z","cross_cats_sorted":[],"title_canon_sha256":"7f9db3b8b9fd51c652396c3feddf12c80c41d50f351bb6cd440e2895d0cce651","abstract_canon_sha256":"0a532327492dde5a344f9e1b1c37f85041209a3faeca31cbd43578655097c79e"},"schema_version":"1.0"},"canonical_sha256":"6dbba1986360f65a943bf96065f144e47758f4f398a61eac11a526205ea21a38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:23:37.669260Z","signature_b64":"jqtCTghp6Q1Cfdwk5VVO1ZLag2Ebsvp0ijNej9aVfTKH0huFmEyDWtB0MuZWgjwfL/Kf4MDqLm61VO1I3theDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dbba1986360f65a943bf96065f144e47758f4f398a61eac11a526205ea21a38","last_reissued_at":"2026-08-12T01:23:37.667625Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:23:37.667625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.10864","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":"2026-08-12T01:23:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FPyrE7NgTEqS47OnzpdhA9fljbILBNCsPgfWnQwqbRWjzrIbb52cq86y+4MHF2S39IgP+plmhtEIsLAtjHc6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T09:17:29.887511Z"},"content_sha256":"461994a1ca64e9ed16051956289b172e3184c32c3499100c3b9775b34aa1c0b8","schema_version":"1.0","event_id":"sha256:461994a1ca64e9ed16051956289b172e3184c32c3499100c3b9775b34aa1c0b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NW52DGDDMD3FVFB37FQGL4KE4R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-View Relational Distillation for Spatial Reasoning with Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanbo Shim, Jinwoo Kim, Kiet T. Nguyen, Seunghoon Hong","submitted_at":"2026-08-11T12:34:41Z","abstract_excerpt":"Vision-language models (VLMs) have achieved strong image and video understanding, yet their visual-spatial representations remain geometrically fragile, leading to failures in spatial reasoning needed for embodied AI, robotics, and autonomous driving. Prior approaches to geometry grounding either fine-tune VLMs on spatial question answering, which can perpetuate spurious visual representations, or fuse features from large geometry-grounded vision models, which substantially increases model size at inference. Knowledge distillation from geometry-grounded vision models offers an alternative, but"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10864","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/2608.10864/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":"2026-08-12T01:23:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vyksBzK+R5Eq5opI8gVT9d7XTVaiFoSZWurZsVzZJjrqkZ5yNUd1uPc0O35lWKVu2OY16voPcWOoygiFiigPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T09:17:29.888836Z"},"content_sha256":"c437fe2696e3c268d2af0692a8adef216cbb7cf70ae4baf4ab38f6fdda02395c","schema_version":"1.0","event_id":"sha256:c437fe2696e3c268d2af0692a8adef216cbb7cf70ae4baf4ab38f6fdda02395c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NW52DGDDMD3FVFB37FQGL4KE4R/bundle.json","state_url":"https://pith.science/pith/NW52DGDDMD3FVFB37FQGL4KE4R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NW52DGDDMD3FVFB37FQGL4KE4R/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":"2026-08-13T09:17:29Z","links":{"resolver":"https://pith.science/pith/NW52DGDDMD3FVFB37FQGL4KE4R","bundle":"https://pith.science/pith/NW52DGDDMD3FVFB37FQGL4KE4R/bundle.json","state":"https://pith.science/pith/NW52DGDDMD3FVFB37FQGL4KE4R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NW52DGDDMD3FVFB37FQGL4KE4R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NW52DGDDMD3FVFB37FQGL4KE4R","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":"0a532327492dde5a344f9e1b1c37f85041209a3faeca31cbd43578655097c79e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T12:34:41Z","title_canon_sha256":"7f9db3b8b9fd51c652396c3feddf12c80c41d50f351bb6cd440e2895d0cce651"},"schema_version":"1.0","source":{"id":"2608.10864","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10864","created_at":"2026-08-12T01:23:37Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10864v1","created_at":"2026-08-12T01:23:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10864","created_at":"2026-08-12T01:23:37Z"},{"alias_kind":"pith_short_12","alias_value":"NW52DGDDMD3F","created_at":"2026-08-12T01:23:37Z"},{"alias_kind":"pith_short_16","alias_value":"NW52DGDDMD3FVFB3","created_at":"2026-08-12T01:23:37Z"},{"alias_kind":"pith_short_8","alias_value":"NW52DGDD","created_at":"2026-08-12T01:23:37Z"}],"graph_snapshots":[{"event_id":"sha256:c437fe2696e3c268d2af0692a8adef216cbb7cf70ae4baf4ab38f6fdda02395c","target":"graph","created_at":"2026-08-12T01:23:37Z","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/2608.10864/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have achieved strong image and video understanding, yet their visual-spatial representations remain geometrically fragile, leading to failures in spatial reasoning needed for embodied AI, robotics, and autonomous driving. Prior approaches to geometry grounding either fine-tune VLMs on spatial question answering, which can perpetuate spurious visual representations, or fuse features from large geometry-grounded vision models, which substantially increases model size at inference. Knowledge distillation from geometry-grounded vision models offers an alternative, but","authors_text":"Hanbo Shim, Jinwoo Kim, Kiet T. Nguyen, Seunghoon Hong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T12:34:41Z","title":"Multi-View Relational Distillation for Spatial Reasoning with Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10864","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":"sha256:461994a1ca64e9ed16051956289b172e3184c32c3499100c3b9775b34aa1c0b8","target":"record","created_at":"2026-08-12T01:23:37Z","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":"0a532327492dde5a344f9e1b1c37f85041209a3faeca31cbd43578655097c79e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T12:34:41Z","title_canon_sha256":"7f9db3b8b9fd51c652396c3feddf12c80c41d50f351bb6cd440e2895d0cce651"},"schema_version":"1.0","source":{"id":"2608.10864","kind":"arxiv","version":1}},"canonical_sha256":"6dbba1986360f65a943bf96065f144e47758f4f398a61eac11a526205ea21a38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6dbba1986360f65a943bf96065f144e47758f4f398a61eac11a526205ea21a38","first_computed_at":"2026-08-12T01:23:37.667625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:23:37.667625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jqtCTghp6Q1Cfdwk5VVO1ZLag2Ebsvp0ijNej9aVfTKH0huFmEyDWtB0MuZWgjwfL/Kf4MDqLm61VO1I3theDg==","signature_status":"signed_v1","signed_at":"2026-08-12T01:23:37.669260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10864","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:461994a1ca64e9ed16051956289b172e3184c32c3499100c3b9775b34aa1c0b8","sha256:c437fe2696e3c268d2af0692a8adef216cbb7cf70ae4baf4ab38f6fdda02395c"],"state_sha256":"fe857b4950650421c33cb472b1f4b07d944d3b57b2905b463324094688033cfa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/bOsz0sdIjyobh1YMcEQrzeVCu0A899v6HHrSK0gT8T3NEbWF6vz6rNw1fHoZTHTojUbdCATrUIQ/LYjpfTKAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T09:17:29.899006Z","bundle_sha256":"c267762d32d774ea7747b677c66cc3a7b2ff503817765711b2ac9bad9b6db14c"}}