{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HT7P3VVLESEQD2AMFNUI7FJJBT","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":"f6e1da952b024a038d27ec1a74e21bf1b93120326efc6427d1b7a582ac155167","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T18:25:26Z","title_canon_sha256":"6e8b7f64e371bd670eaa3bf25458b4c42ee2fcf73cd0d6553ac655b4cb099286"},"schema_version":"1.0","source":{"id":"2403.00729","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00729","created_at":"2026-07-05T07:51:07Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00729v1","created_at":"2026-07-05T07:51:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00729","created_at":"2026-07-05T07:51:07Z"},{"alias_kind":"pith_short_12","alias_value":"HT7P3VVLESEQ","created_at":"2026-07-05T07:51:07Z"},{"alias_kind":"pith_short_16","alias_value":"HT7P3VVLESEQD2AM","created_at":"2026-07-05T07:51:07Z"},{"alias_kind":"pith_short_8","alias_value":"HT7P3VVL","created_at":"2026-07-05T07:51:07Z"}],"graph_snapshots":[{"event_id":"sha256:39200242ba9abdd41d9cf18e642b9a6972ca2d4caa1953d8b3dff4fbbc004fae","target":"graph","created_at":"2026-07-05T07:51:07Z","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/2403.00729/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial relationships between objects represent key scene information for humans to understand and interact with the world. To study the capability of current computer vision systems to recognize physically grounded spatial relations, we start by proposing precise relation definitions that permit consistently annotating a benchmark dataset. Despite the apparent simplicity of this task relative to others in the recognition literature, we observe that existing approaches perform poorly on this benchmark. We propose new approaches exploiting the long-range attention capabilities of transformers f","authors_text":"Chuan Wen, Dinesh Jayaraman, Yang Gao","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T18:25:26Z","title":"Can Transformers Capture Spatial Relations between Objects?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00729","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:d1ca23d5d2228dc79da3659a5d0d950af8cf6083be299431a9c4aabdc521c877","target":"record","created_at":"2026-07-05T07:51:07Z","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":"f6e1da952b024a038d27ec1a74e21bf1b93120326efc6427d1b7a582ac155167","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T18:25:26Z","title_canon_sha256":"6e8b7f64e371bd670eaa3bf25458b4c42ee2fcf73cd0d6553ac655b4cb099286"},"schema_version":"1.0","source":{"id":"2403.00729","kind":"arxiv","version":1}},"canonical_sha256":"3cfefdd6ab248901e80c2b688f95290cd5d5e2af343dbad12a6c573b2c4bcbd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cfefdd6ab248901e80c2b688f95290cd5d5e2af343dbad12a6c573b2c4bcbd0","first_computed_at":"2026-07-05T07:51:07.764083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:07.764083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6YcVBIacam6gzUmc2ErGXQ2TLJL7F4tNJKp7lKKrtux5euLwOzjYWr1FjeYJZGiJlcG1095dUMUAiU3Rsi2gCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:07.764500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00729","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1ca23d5d2228dc79da3659a5d0d950af8cf6083be299431a9c4aabdc521c877","sha256:39200242ba9abdd41d9cf18e642b9a6972ca2d4caa1953d8b3dff4fbbc004fae"],"state_sha256":"a79ff78a5cd8dc5e6825144079757b42c8ba50ee5c4da8b026722b37a03a0230"}