{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZJPJ35TP2UTTMLH3SKY54GUMBI","short_pith_number":"pith:ZJPJ35TP","canonical_record":{"source":{"id":"2411.07664","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T09:30:02Z","cross_cats_sorted":[],"title_canon_sha256":"c4a68bc0d2dd6a53560fe696cc528b92c5d360b99c2c720a26ae719c1e975e5d","abstract_canon_sha256":"2a178187c857cb91c6f7f9c8b05e70ae798bcb0ec1eeaa0c82885db0821b7bce"},"schema_version":"1.0"},"canonical_sha256":"ca5e9df66fd527362cfb92b1de1a8c0a0e7bf7ee2005155495972f205fa0daa6","source":{"kind":"arxiv","id":"2411.07664","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07664","created_at":"2026-07-05T09:34:26Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07664v1","created_at":"2026-07-05T09:34:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07664","created_at":"2026-07-05T09:34:26Z"},{"alias_kind":"pith_short_12","alias_value":"ZJPJ35TP2UTT","created_at":"2026-07-05T09:34:26Z"},{"alias_kind":"pith_short_16","alias_value":"ZJPJ35TP2UTTMLH3","created_at":"2026-07-05T09:34:26Z"},{"alias_kind":"pith_short_8","alias_value":"ZJPJ35TP","created_at":"2026-07-05T09:34:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZJPJ35TP2UTTMLH3SKY54GUMBI","target":"record","payload":{"canonical_record":{"source":{"id":"2411.07664","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T09:30:02Z","cross_cats_sorted":[],"title_canon_sha256":"c4a68bc0d2dd6a53560fe696cc528b92c5d360b99c2c720a26ae719c1e975e5d","abstract_canon_sha256":"2a178187c857cb91c6f7f9c8b05e70ae798bcb0ec1eeaa0c82885db0821b7bce"},"schema_version":"1.0"},"canonical_sha256":"ca5e9df66fd527362cfb92b1de1a8c0a0e7bf7ee2005155495972f205fa0daa6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:26.988070Z","signature_b64":"uUbHLe/SaLRxlYWXpOtJ/+dbBjsmWrrfO3AmokmN1RuQCFIhRqfIIDiI+saJWF9YDendS2bgjRW13hSHp8XqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca5e9df66fd527362cfb92b1de1a8c0a0e7bf7ee2005155495972f205fa0daa6","last_reissued_at":"2026-07-05T09:34:26.987594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:26.987594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.07664","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":"2026-07-05T09:34:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oI5BITHdQY+7OX9ao6bNS0F6/1AXY8BKw+oq6RNyDX7fCe4eFlVC+4hIClMxELt/AC1iV4qzKbT7kKLbcv6+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:54:41.189414Z"},"content_sha256":"216fd5c150a3c20fd24e4e5aba79472476696cfe1f5bc1048867d4de76c7ec17","schema_version":"1.0","event_id":"sha256:216fd5c150a3c20fd24e4e5aba79472476696cfe1f5bc1048867d4de76c7ec17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZJPJ35TP2UTTMLH3SKY54GUMBI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating the Generation of Spatial Relations in Text and Image Generative Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alvin Tan, Cheston Tan, Clarence Lee, Shang Hong Sim","submitted_at":"2024-11-12T09:30:02Z","abstract_excerpt":"Understanding spatial relations is a crucial cognitive ability for both humans and AI. While current research has predominantly focused on the benchmarking of text-to-image (T2I) models, we propose a more comprehensive evaluation that includes \\textit{both} T2I and Large Language Models (LLMs). As spatial relations are naturally understood in a visuo-spatial manner, we develop an approach to convert LLM outputs into an image, thereby allowing us to evaluate both T2I models and LLMs \\textit{visually}. We examined the spatial relation understanding of 8 prominent generative models (3 T2I models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07664","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/2411.07664/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":"2026-07-05T09:34:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HAz5mLJwWECmWNkrLqsgFtOT03S7pFPYuPon0q2YE5+OoNDuS5JFkaTewLagzPKYpVPJD+UHIaMl0R7pQwF2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:54:41.190528Z"},"content_sha256":"b84215abd8a357d41ae5e684c0dd6e57c4ca01e4688a79e0427397ac0f8c9bf7","schema_version":"1.0","event_id":"sha256:b84215abd8a357d41ae5e684c0dd6e57c4ca01e4688a79e0427397ac0f8c9bf7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZJPJ35TP2UTTMLH3SKY54GUMBI/bundle.json","state_url":"https://pith.science/pith/ZJPJ35TP2UTTMLH3SKY54GUMBI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZJPJ35TP2UTTMLH3SKY54GUMBI/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":"2026-08-08T22:54:41Z","links":{"resolver":"https://pith.science/pith/ZJPJ35TP2UTTMLH3SKY54GUMBI","bundle":"https://pith.science/pith/ZJPJ35TP2UTTMLH3SKY54GUMBI/bundle.json","state":"https://pith.science/pith/ZJPJ35TP2UTTMLH3SKY54GUMBI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZJPJ35TP2UTTMLH3SKY54GUMBI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZJPJ35TP2UTTMLH3SKY54GUMBI","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":"2a178187c857cb91c6f7f9c8b05e70ae798bcb0ec1eeaa0c82885db0821b7bce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T09:30:02Z","title_canon_sha256":"c4a68bc0d2dd6a53560fe696cc528b92c5d360b99c2c720a26ae719c1e975e5d"},"schema_version":"1.0","source":{"id":"2411.07664","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07664","created_at":"2026-07-05T09:34:26Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07664v1","created_at":"2026-07-05T09:34:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07664","created_at":"2026-07-05T09:34:26Z"},{"alias_kind":"pith_short_12","alias_value":"ZJPJ35TP2UTT","created_at":"2026-07-05T09:34:26Z"},{"alias_kind":"pith_short_16","alias_value":"ZJPJ35TP2UTTMLH3","created_at":"2026-07-05T09:34:26Z"},{"alias_kind":"pith_short_8","alias_value":"ZJPJ35TP","created_at":"2026-07-05T09:34:26Z"}],"graph_snapshots":[{"event_id":"sha256:b84215abd8a357d41ae5e684c0dd6e57c4ca01e4688a79e0427397ac0f8c9bf7","target":"graph","created_at":"2026-07-05T09:34:26Z","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/2411.07664/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding spatial relations is a crucial cognitive ability for both humans and AI. While current research has predominantly focused on the benchmarking of text-to-image (T2I) models, we propose a more comprehensive evaluation that includes \\textit{both} T2I and Large Language Models (LLMs). As spatial relations are naturally understood in a visuo-spatial manner, we develop an approach to convert LLM outputs into an image, thereby allowing us to evaluate both T2I models and LLMs \\textit{visually}. We examined the spatial relation understanding of 8 prominent generative models (3 T2I models ","authors_text":"Alvin Tan, Cheston Tan, Clarence Lee, Shang Hong Sim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T09:30:02Z","title":"Evaluating the Generation of Spatial Relations in Text and Image Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07664","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":"sha256:216fd5c150a3c20fd24e4e5aba79472476696cfe1f5bc1048867d4de76c7ec17","target":"record","created_at":"2026-07-05T09:34:26Z","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":"2a178187c857cb91c6f7f9c8b05e70ae798bcb0ec1eeaa0c82885db0821b7bce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T09:30:02Z","title_canon_sha256":"c4a68bc0d2dd6a53560fe696cc528b92c5d360b99c2c720a26ae719c1e975e5d"},"schema_version":"1.0","source":{"id":"2411.07664","kind":"arxiv","version":1}},"canonical_sha256":"ca5e9df66fd527362cfb92b1de1a8c0a0e7bf7ee2005155495972f205fa0daa6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca5e9df66fd527362cfb92b1de1a8c0a0e7bf7ee2005155495972f205fa0daa6","first_computed_at":"2026-07-05T09:34:26.987594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:26.987594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uUbHLe/SaLRxlYWXpOtJ/+dbBjsmWrrfO3AmokmN1RuQCFIhRqfIIDiI+saJWF9YDendS2bgjRW13hSHp8XqCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:26.988070Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07664","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:216fd5c150a3c20fd24e4e5aba79472476696cfe1f5bc1048867d4de76c7ec17","sha256:b84215abd8a357d41ae5e684c0dd6e57c4ca01e4688a79e0427397ac0f8c9bf7"],"state_sha256":"5b3629f068d246b8aab412e4796297ed3f7c25f4204d3369e1cef971e613536c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rS/hRQCjXM0j5hYXJwd749BWrlZ9w8nK4MiFV3gxgKJWaT+MAgcO4cQ4PPFzXiz0amsrg+PPD3XTGU+L8i6nCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:54:41.198426Z","bundle_sha256":"e171472b6a704b6d911c1989fe8d66a52b4f6ddeef1fb64ba44d16f7cd8d3308"}}