{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PYKWNJV27DLBQDURDMPPXMWFZB","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":"dceff960a9b468722e073cfe9913e2597aeaae6b00a9bd8d284eb7c444d02f57","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-19T08:16:11Z","title_canon_sha256":"afc11c42e3eab8584050c07c67e2f41d0951b8848877b19e4c9357976aaf95f9"},"schema_version":"1.0","source":{"id":"2601.12809","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.12809","created_at":"2026-05-27T02:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2601.12809v2","created_at":"2026-05-27T02:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.12809","created_at":"2026-05-27T02:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"PYKWNJV27DLB","created_at":"2026-05-27T02:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"PYKWNJV27DLBQDUR","created_at":"2026-05-27T02:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"PYKWNJV2","created_at":"2026-05-27T02:05:10Z"}],"graph_snapshots":[{"event_id":"sha256:14e830e9bda23e174c0657b5bc491209a04c27aea80078904b696602ff213921","target":"graph","created_at":"2026-05-27T02:05:10Z","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/2601.12809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial understanding remains a key challenge in vision-language models. Yet it is still unclear whether such understanding is truly acquired, and if so, through what mechanisms. We present a controllable 1D image-text testbed to probe how left-right relational understanding emerges in Transformer-based vision and text encoders trained with a CLIP-style contrastive objective. We train lightweight Transformer-based vision and text encoders end-to-end on paired descriptions of one- and two-object scenes and evaluate generalization to unseen object pairs while systematically varying label and lay","authors_text":"Chihiro Noguchi, Takaki Yamamoto, Toshihiro Tanizawa","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-19T08:16:11Z","title":"Left-Right Symmetry Breaking in CLIP-style Vision-Language Models Trained on Synthetic Spatial-Relation Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.12809","kind":"arxiv","version":2},"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":"sha256:22f26395492b57889e68cc4b0e4254e41e9ff4442f18164729a3632e3e87bffd","target":"record","created_at":"2026-05-27T02:05:10Z","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":"dceff960a9b468722e073cfe9913e2597aeaae6b00a9bd8d284eb7c444d02f57","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-19T08:16:11Z","title_canon_sha256":"afc11c42e3eab8584050c07c67e2f41d0951b8848877b19e4c9357976aaf95f9"},"schema_version":"1.0","source":{"id":"2601.12809","kind":"arxiv","version":2}},"canonical_sha256":"7e1566a6baf8d6180e911b1efbb2c5c874d21af1c44faf8ba5f9d2cab03dc446","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e1566a6baf8d6180e911b1efbb2c5c874d21af1c44faf8ba5f9d2cab03dc446","first_computed_at":"2026-05-27T02:05:10.700081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T02:05:10.700081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ROYQTG3wLdPBHNK5bWVlUx4oyzMCOPmIVifeUHboRuVVOqA6nKoh+KdaJ4I3Xq8gJRc08mlSnhBvZ+kw1a2NCA==","signature_status":"signed_v1","signed_at":"2026-05-27T02:05:10.700749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.12809","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22f26395492b57889e68cc4b0e4254e41e9ff4442f18164729a3632e3e87bffd","sha256:14e830e9bda23e174c0657b5bc491209a04c27aea80078904b696602ff213921"],"state_sha256":"4e692ae7ffa3700eb051a408f6c74bdeb8894ac4ef4eb081d480182871a2afb7"}