{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TTBYZLUU5TPTKIQWHJEFLBORVX","short_pith_number":"pith:TTBYZLUU","canonical_record":{"source":{"id":"2311.11477","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-20T01:07:30Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5e1a55069957d669c3ca53c616d8d1ffb7785d8a5001531959020e06754f89d4","abstract_canon_sha256":"40a207e9ad284723f194007841685ee3a1cd8ff374ac4d944ef161651b1b60f2"},"schema_version":"1.0"},"canonical_sha256":"9cc38cae94ecdf3522163a485585d1add6a0af128e888daed5a78e3d2fab3a0d","source":{"kind":"arxiv","id":"2311.11477","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.11477","created_at":"2026-07-05T07:14:33Z"},{"alias_kind":"arxiv_version","alias_value":"2311.11477v1","created_at":"2026-07-05T07:14:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11477","created_at":"2026-07-05T07:14:33Z"},{"alias_kind":"pith_short_12","alias_value":"TTBYZLUU5TPT","created_at":"2026-07-05T07:14:33Z"},{"alias_kind":"pith_short_16","alias_value":"TTBYZLUU5TPTKIQW","created_at":"2026-07-05T07:14:33Z"},{"alias_kind":"pith_short_8","alias_value":"TTBYZLUU","created_at":"2026-07-05T07:14:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TTBYZLUU5TPTKIQWHJEFLBORVX","target":"record","payload":{"canonical_record":{"source":{"id":"2311.11477","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-20T01:07:30Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5e1a55069957d669c3ca53c616d8d1ffb7785d8a5001531959020e06754f89d4","abstract_canon_sha256":"40a207e9ad284723f194007841685ee3a1cd8ff374ac4d944ef161651b1b60f2"},"schema_version":"1.0"},"canonical_sha256":"9cc38cae94ecdf3522163a485585d1add6a0af128e888daed5a78e3d2fab3a0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:33.805662Z","signature_b64":"puTcUW0OhxddPDHJUN2pSv+WyE3eMIQu138sVAfi0adQM8QpBgnNXWeN1t3AXJ4dSlKtSFFJ9VuDH1u4X9CNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cc38cae94ecdf3522163a485585d1add6a0af128e888daed5a78e3d2fab3a0d","last_reissued_at":"2026-07-05T07:14:33.805110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:33.805110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.11477","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":"2026-07-05T07:14:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sps1ML7C5M7s8trUdFhSyehaRUUhEynVOXWBGT35ObN2/WPJsWcbCoaeXqZKtoplrghg1Ltl4Q0VCLzmKF/MDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:00:39.830835Z"},"content_sha256":"7bea98a3a47de848b778a0c74e4d6b4ac7f00793cce3abaab53ecd6490a740a0","schema_version":"1.0","event_id":"sha256:7bea98a3a47de848b778a0c74e4d6b4ac7f00793cce3abaab53ecd6490a740a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TTBYZLUU5TPTKIQWHJEFLBORVX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What's left can't be right -- The remaining positional incompetence of contrastive vision-language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anthony Ventresque, Ellen Rushe, Nils Hoehing","submitted_at":"2023-11-20T01:07:30Z","abstract_excerpt":"Contrastive vision-language models like CLIP have been found to lack spatial understanding capabilities. In this paper we discuss the possible causes of this phenomenon by analysing both datasets and embedding space. By focusing on simple left-right positional relations, we show that this behaviour is entirely predictable, even with large-scale datasets, demonstrate that these relations can be taught using synthetic data and show that this approach can generalise well to natural images - improving the performance on left-right relations on Visual Genome Relations."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11477","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/2311.11477/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":"2026-07-05T07:14:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FD+5m+4UpprLm4LILyuIut3zBEnmFtG1g8fxvAgpUp4h5zNhec675gKqKKvGTqPHecEpLbKh6zEC4l/M3GyzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:00:39.831258Z"},"content_sha256":"58e61794c5d06de99f049f29c32e087cf88c943fb82796e9af488aa1b8180f7b","schema_version":"1.0","event_id":"sha256:58e61794c5d06de99f049f29c32e087cf88c943fb82796e9af488aa1b8180f7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TTBYZLUU5TPTKIQWHJEFLBORVX/bundle.json","state_url":"https://pith.science/pith/TTBYZLUU5TPTKIQWHJEFLBORVX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TTBYZLUU5TPTKIQWHJEFLBORVX/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":"2026-08-06T16:00:39Z","links":{"resolver":"https://pith.science/pith/TTBYZLUU5TPTKIQWHJEFLBORVX","bundle":"https://pith.science/pith/TTBYZLUU5TPTKIQWHJEFLBORVX/bundle.json","state":"https://pith.science/pith/TTBYZLUU5TPTKIQWHJEFLBORVX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TTBYZLUU5TPTKIQWHJEFLBORVX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TTBYZLUU5TPTKIQWHJEFLBORVX","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":"40a207e9ad284723f194007841685ee3a1cd8ff374ac4d944ef161651b1b60f2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-20T01:07:30Z","title_canon_sha256":"5e1a55069957d669c3ca53c616d8d1ffb7785d8a5001531959020e06754f89d4"},"schema_version":"1.0","source":{"id":"2311.11477","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.11477","created_at":"2026-07-05T07:14:33Z"},{"alias_kind":"arxiv_version","alias_value":"2311.11477v1","created_at":"2026-07-05T07:14:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11477","created_at":"2026-07-05T07:14:33Z"},{"alias_kind":"pith_short_12","alias_value":"TTBYZLUU5TPT","created_at":"2026-07-05T07:14:33Z"},{"alias_kind":"pith_short_16","alias_value":"TTBYZLUU5TPTKIQW","created_at":"2026-07-05T07:14:33Z"},{"alias_kind":"pith_short_8","alias_value":"TTBYZLUU","created_at":"2026-07-05T07:14:33Z"}],"graph_snapshots":[{"event_id":"sha256:58e61794c5d06de99f049f29c32e087cf88c943fb82796e9af488aa1b8180f7b","target":"graph","created_at":"2026-07-05T07:14:33Z","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/2311.11477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive vision-language models like CLIP have been found to lack spatial understanding capabilities. In this paper we discuss the possible causes of this phenomenon by analysing both datasets and embedding space. By focusing on simple left-right positional relations, we show that this behaviour is entirely predictable, even with large-scale datasets, demonstrate that these relations can be taught using synthetic data and show that this approach can generalise well to natural images - improving the performance on left-right relations on Visual Genome Relations.","authors_text":"Anthony Ventresque, Ellen Rushe, Nils Hoehing","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-20T01:07:30Z","title":"What's left can't be right -- The remaining positional incompetence of contrastive vision-language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11477","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":"sha256:7bea98a3a47de848b778a0c74e4d6b4ac7f00793cce3abaab53ecd6490a740a0","target":"record","created_at":"2026-07-05T07:14:33Z","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":"40a207e9ad284723f194007841685ee3a1cd8ff374ac4d944ef161651b1b60f2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-20T01:07:30Z","title_canon_sha256":"5e1a55069957d669c3ca53c616d8d1ffb7785d8a5001531959020e06754f89d4"},"schema_version":"1.0","source":{"id":"2311.11477","kind":"arxiv","version":1}},"canonical_sha256":"9cc38cae94ecdf3522163a485585d1add6a0af128e888daed5a78e3d2fab3a0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cc38cae94ecdf3522163a485585d1add6a0af128e888daed5a78e3d2fab3a0d","first_computed_at":"2026-07-05T07:14:33.805110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:14:33.805110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"puTcUW0OhxddPDHJUN2pSv+WyE3eMIQu138sVAfi0adQM8QpBgnNXWeN1t3AXJ4dSlKtSFFJ9VuDH1u4X9CNBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:14:33.805662Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.11477","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bea98a3a47de848b778a0c74e4d6b4ac7f00793cce3abaab53ecd6490a740a0","sha256:58e61794c5d06de99f049f29c32e087cf88c943fb82796e9af488aa1b8180f7b"],"state_sha256":"9edfd2b7600dfacc92a8e37a342463a2bbd3a78f5b59df5d1e8073d6c8be9f7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nRXqYSthHytPOwaXcCSFcPChs++/VTlFsyEOxPCSuFA9yYTMF2wszU+GwKG5QCg0MgiH4W91+Altjhlb6bzkBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:00:39.835196Z","bundle_sha256":"d10e416bc0442269482f712734d19ca685258d11e8d45a36d6fd605fe97ff585"}}