{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NFZ2QAGY5REKPOGSP34OAU766K","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":"f361db9c8dca74c45323f2e7a2fcb2e70b57f8087745552e3c89a718deb69d2b","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T08:07:22Z","title_canon_sha256":"35f72e60b278e23e91da9f2d6403b0dc6d9bcb0eae154b57ae83cf36b809dd18"},"schema_version":"1.0","source":{"id":"2607.17657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17657","created_at":"2026-07-21T02:21:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17657v1","created_at":"2026-07-21T02:21:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17657","created_at":"2026-07-21T02:21:53Z"},{"alias_kind":"pith_short_12","alias_value":"NFZ2QAGY5REK","created_at":"2026-07-21T02:21:53Z"},{"alias_kind":"pith_short_16","alias_value":"NFZ2QAGY5REKPOGS","created_at":"2026-07-21T02:21:53Z"},{"alias_kind":"pith_short_8","alias_value":"NFZ2QAGY","created_at":"2026-07-21T02:21:53Z"}],"graph_snapshots":[{"event_id":"sha256:bdf6fa16a038420e9d6c96d441950cbc6976f56fe0803a4badc29ad641c1cb03","target":"graph","created_at":"2026-07-21T02:21:53Z","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/2607.17657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) still struggle with spatial reasoning that requires perspective transformation. In particular, they often rely on camera-centric cues rather than reasoning from the reference object's viewpoint, leading to systematic errors in non-camera reference settings. In this paper, we first analyze this failure mode and show that object orientation is a key factor underlying such camera-centric shortcut behavior. To address this issue, we propose OrientSAM, an orientation-aware spatial alignment framework for multimodal models. OrientSAM injects explicit orientat","authors_text":"Hang Yin, Kan Li, Wenxiao Fan","cross_cats":["cs.CV","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T08:07:22Z","title":"OrientSAM: Mitigating Camera-Centric Shortcut in Multimodal Spatial Reasoning via Orientation-Aware Spatial Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17657","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":"sha256:55ba5a836f8f65da17fc6a1a17a6ee09cee103633d72e658630385969496f1cf","target":"record","created_at":"2026-07-21T02:21:53Z","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":"f361db9c8dca74c45323f2e7a2fcb2e70b57f8087745552e3c89a718deb69d2b","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T08:07:22Z","title_canon_sha256":"35f72e60b278e23e91da9f2d6403b0dc6d9bcb0eae154b57ae83cf36b809dd18"},"schema_version":"1.0","source":{"id":"2607.17657","kind":"arxiv","version":1}},"canonical_sha256":"6973a800d8ec48a7b8d27ef8e053fef2be1a8f4847a51d0169bd49151d93d090","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6973a800d8ec48a7b8d27ef8e053fef2be1a8f4847a51d0169bd49151d93d090","first_computed_at":"2026-07-21T02:21:53.270545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T02:21:53.270545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SxBJDC7SocMbMK97dYOeTw8qnxKASQ0+UDChAFAQ8TJf2wSck3LpXDNqCwv1SnAG/oLVYOPMBnkAgYkJf44QCw==","signature_status":"signed_v1","signed_at":"2026-07-21T02:21:53.271455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55ba5a836f8f65da17fc6a1a17a6ee09cee103633d72e658630385969496f1cf","sha256:bdf6fa16a038420e9d6c96d441950cbc6976f56fe0803a4badc29ad641c1cb03"],"state_sha256":"19534f8405aef10dbea47b6fa8208d31d0dedaf939b82b9d6c86f2430e70a977"}