{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TGHXXADANOM3EUAAYG7KRQLEP5","short_pith_number":"pith:TGHXXADA","canonical_record":{"source":{"id":"2212.10015","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-20T06:03:51Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e5fa0d5fe89ae2d672f3c431ee6a508e0171537e9c9cf84b05406efaaaa4690f","abstract_canon_sha256":"44e1f268340f322fb06887cc795e530fbfd193a5f716ff02fb92f58fbd2af54a"},"schema_version":"1.0"},"canonical_sha256":"998f7b80606b99b25000c1bea8c1647f44346e172a5dc736fbe1ed60f7d42a89","source":{"kind":"arxiv","id":"2212.10015","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10015","created_at":"2026-07-05T07:05:40Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10015v3","created_at":"2026-07-05T07:05:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10015","created_at":"2026-07-05T07:05:40Z"},{"alias_kind":"pith_short_12","alias_value":"TGHXXADANOM3","created_at":"2026-07-05T07:05:40Z"},{"alias_kind":"pith_short_16","alias_value":"TGHXXADANOM3EUAA","created_at":"2026-07-05T07:05:40Z"},{"alias_kind":"pith_short_8","alias_value":"TGHXXADA","created_at":"2026-07-05T07:05:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TGHXXADANOM3EUAAYG7KRQLEP5","target":"record","payload":{"canonical_record":{"source":{"id":"2212.10015","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-20T06:03:51Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e5fa0d5fe89ae2d672f3c431ee6a508e0171537e9c9cf84b05406efaaaa4690f","abstract_canon_sha256":"44e1f268340f322fb06887cc795e530fbfd193a5f716ff02fb92f58fbd2af54a"},"schema_version":"1.0"},"canonical_sha256":"998f7b80606b99b25000c1bea8c1647f44346e172a5dc736fbe1ed60f7d42a89","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:40.916328Z","signature_b64":"EB1QyLGuNRAYZJGA4S/4zME2UvR3ol8I19oTqn9n2EtlEMUIijKdq5QO2gGE87tfD7jTi2hyEhc9qJ3WD+erBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"998f7b80606b99b25000c1bea8c1647f44346e172a5dc736fbe1ed60f7d42a89","last_reissued_at":"2026-07-05T07:05:40.915779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:40.915779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.10015","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:05:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JSIS4qyMNa7nVQQ3/hXU51ZESZOfIfGngJYfb22+jdOHQ7aT6NGaOPmMx4yU++xSdKTV55FsPmSSLQt3d8giCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:36:57.470459Z"},"content_sha256":"1c13f9aafba0ba28c02cff317e7c793bf9522a17a621e11a335e5544cd1becfd","schema_version":"1.0","event_id":"sha256:1c13f9aafba0ba28c02cff317e7c793bf9522a17a621e11a335e5544cd1becfd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TGHXXADANOM3EUAAYG7KRQLEP5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Spatial Relationships in Text-to-Image Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Besmira Nushi, Chitta Baral, Ece Kamar, Eric Horvitz, Hamid Palangi, Tejas Gokhale, Vibhav Vineet, Yezhou Yang","submitted_at":"2022-12-20T06:03:51Z","abstract_excerpt":"Spatial understanding is a fundamental aspect of computer vision and integral for human-level reasoning about images, making it an important component for grounded language understanding. While recent text-to-image synthesis (T2I) models have shown unprecedented improvements in photorealism, it is unclear whether they have reliable spatial understanding capabilities. We investigate the ability of T2I models to generate correct spatial relationships among objects and present VISOR, an evaluation metric that captures how accurately the spatial relationship described in text is generated in the i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10015","kind":"arxiv","version":3},"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/2212.10015/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":"2026-07-05T07:05:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HoxEZW8+weCPDeCXTMMNz/nc/eduC1aEhfw8w9Z+Ao7vxVRTd6+7FxMULRxBeN/RLaKV0Mvsq3epPZ73QaBnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:36:57.470991Z"},"content_sha256":"545a041d0f502e852d0a2072e44131048ecc4341f4e90d12f48c7392d214e426","schema_version":"1.0","event_id":"sha256:545a041d0f502e852d0a2072e44131048ecc4341f4e90d12f48c7392d214e426"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TGHXXADANOM3EUAAYG7KRQLEP5/bundle.json","state_url":"https://pith.science/pith/TGHXXADANOM3EUAAYG7KRQLEP5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TGHXXADANOM3EUAAYG7KRQLEP5/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":"2026-08-15T21:36:57Z","links":{"resolver":"https://pith.science/pith/TGHXXADANOM3EUAAYG7KRQLEP5","bundle":"https://pith.science/pith/TGHXXADANOM3EUAAYG7KRQLEP5/bundle.json","state":"https://pith.science/pith/TGHXXADANOM3EUAAYG7KRQLEP5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TGHXXADANOM3EUAAYG7KRQLEP5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TGHXXADANOM3EUAAYG7KRQLEP5","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":"44e1f268340f322fb06887cc795e530fbfd193a5f716ff02fb92f58fbd2af54a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-20T06:03:51Z","title_canon_sha256":"e5fa0d5fe89ae2d672f3c431ee6a508e0171537e9c9cf84b05406efaaaa4690f"},"schema_version":"1.0","source":{"id":"2212.10015","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10015","created_at":"2026-07-05T07:05:40Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10015v3","created_at":"2026-07-05T07:05:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10015","created_at":"2026-07-05T07:05:40Z"},{"alias_kind":"pith_short_12","alias_value":"TGHXXADANOM3","created_at":"2026-07-05T07:05:40Z"},{"alias_kind":"pith_short_16","alias_value":"TGHXXADANOM3EUAA","created_at":"2026-07-05T07:05:40Z"},{"alias_kind":"pith_short_8","alias_value":"TGHXXADA","created_at":"2026-07-05T07:05:40Z"}],"graph_snapshots":[{"event_id":"sha256:545a041d0f502e852d0a2072e44131048ecc4341f4e90d12f48c7392d214e426","target":"graph","created_at":"2026-07-05T07:05:40Z","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/2212.10015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial understanding is a fundamental aspect of computer vision and integral for human-level reasoning about images, making it an important component for grounded language understanding. While recent text-to-image synthesis (T2I) models have shown unprecedented improvements in photorealism, it is unclear whether they have reliable spatial understanding capabilities. We investigate the ability of T2I models to generate correct spatial relationships among objects and present VISOR, an evaluation metric that captures how accurately the spatial relationship described in text is generated in the i","authors_text":"Besmira Nushi, Chitta Baral, Ece Kamar, Eric Horvitz, Hamid Palangi, Tejas Gokhale, Vibhav Vineet, Yezhou Yang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-20T06:03:51Z","title":"Benchmarking Spatial Relationships in Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10015","kind":"arxiv","version":3},"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":"sha256:1c13f9aafba0ba28c02cff317e7c793bf9522a17a621e11a335e5544cd1becfd","target":"record","created_at":"2026-07-05T07:05:40Z","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":"44e1f268340f322fb06887cc795e530fbfd193a5f716ff02fb92f58fbd2af54a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-20T06:03:51Z","title_canon_sha256":"e5fa0d5fe89ae2d672f3c431ee6a508e0171537e9c9cf84b05406efaaaa4690f"},"schema_version":"1.0","source":{"id":"2212.10015","kind":"arxiv","version":3}},"canonical_sha256":"998f7b80606b99b25000c1bea8c1647f44346e172a5dc736fbe1ed60f7d42a89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"998f7b80606b99b25000c1bea8c1647f44346e172a5dc736fbe1ed60f7d42a89","first_computed_at":"2026-07-05T07:05:40.915779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:40.915779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EB1QyLGuNRAYZJGA4S/4zME2UvR3ol8I19oTqn9n2EtlEMUIijKdq5QO2gGE87tfD7jTi2hyEhc9qJ3WD+erBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:40.916328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10015","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c13f9aafba0ba28c02cff317e7c793bf9522a17a621e11a335e5544cd1becfd","sha256:545a041d0f502e852d0a2072e44131048ecc4341f4e90d12f48c7392d214e426"],"state_sha256":"e45667248af608feb323ff3197531835aa1ae5c61f093cf6c43ad46b152da4d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xRWYHVJhrP/srHN64K/VAw5RfOWz0jdiDYWc8ljPnfOLRYfejzx7s88s/BcKCZx4ru5k5aYQ6Eep7Z/DXXOAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T21:36:57.476876Z","bundle_sha256":"678d50628bdeae607c3fbe63737fa3a0170eb29844ec62b9b787910f6e074119"}}