{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ORVKCFDEYSW5XBNE3XY5A42R2A","short_pith_number":"pith:ORVKCFDE","canonical_record":{"source":{"id":"2403.00587","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T15:09:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c35f240bef6011495cabc471ba55d2ba6df754092ff29ce7a8299c9638ffef5","abstract_canon_sha256":"1e143688e1231109a4895bad62ccd6195cab0363a3e65cf3c8958709a184bd14"},"schema_version":"1.0"},"canonical_sha256":"746aa11464c4addb85a4ddf1d07351d034c08e5aefdb29f78b2c934bb21d5e9a","source":{"kind":"arxiv","id":"2403.00587","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00587","created_at":"2026-07-05T07:51:06Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00587v1","created_at":"2026-07-05T07:51:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00587","created_at":"2026-07-05T07:51:06Z"},{"alias_kind":"pith_short_12","alias_value":"ORVKCFDEYSW5","created_at":"2026-07-05T07:51:06Z"},{"alias_kind":"pith_short_16","alias_value":"ORVKCFDEYSW5XBNE","created_at":"2026-07-05T07:51:06Z"},{"alias_kind":"pith_short_8","alias_value":"ORVKCFDE","created_at":"2026-07-05T07:51:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ORVKCFDEYSW5XBNE3XY5A42R2A","target":"record","payload":{"canonical_record":{"source":{"id":"2403.00587","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T15:09:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c35f240bef6011495cabc471ba55d2ba6df754092ff29ce7a8299c9638ffef5","abstract_canon_sha256":"1e143688e1231109a4895bad62ccd6195cab0363a3e65cf3c8958709a184bd14"},"schema_version":"1.0"},"canonical_sha256":"746aa11464c4addb85a4ddf1d07351d034c08e5aefdb29f78b2c934bb21d5e9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:06.155656Z","signature_b64":"KDiYoSTZnkxGC1/9Dlh9kJlsaarsM8X7yyqv8k99TbhUxLkQwagwYeF7cEnml1tyleNkTsTnkEjHBZ8AgUfQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"746aa11464c4addb85a4ddf1d07351d034c08e5aefdb29f78b2c934bb21d5e9a","last_reissued_at":"2026-07-05T07:51:06.155116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:06.155116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.00587","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":"2026-07-05T07:51:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vbpq1SzXSlo+MysPXAo/dFPsewN0u7ms5nwLzOvFnPnDMZyQqkx+TkCUS8N3xYKZqTwAAV0negzD7hVlr41xDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:35:59.994746Z"},"content_sha256":"e770c68a46eeff59764f27d39db67b4eed8b56af9aa3e64deee863ff75952804","schema_version":"1.0","event_id":"sha256:e770c68a46eeff59764f27d39db67b4eed8b56af9aa3e64deee863ff75952804"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ORVKCFDEYSW5XBNE3XY5A42R2A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Explicit Spatial Relationships in Text-to-Image Generation through an Automatically Derived Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aitor Soroa, Ander Salaberria, Eneko Agirre, Frank Keller, Gorka Azkune, Oier Lopez de Lacalle","submitted_at":"2024-03-01T15:09:37Z","abstract_excerpt":"Existing work has observed that current text-to-image systems do not accurately reflect explicit spatial relations between objects such as 'left of' or 'below'. We hypothesize that this is because explicit spatial relations rarely appear in the image captions used to train these models. We propose an automatic method that, given existing images, generates synthetic captions that contain 14 explicit spatial relations. We introduce the Spatial Relation for Generation (SR4G) dataset, which contains 9.9 millions image-caption pairs for training, and more than 60 thousand captions for evaluation. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00587","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/2403.00587/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":"2026-07-05T07:51:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9C5TIsfks/WUByvAiHvTBQfocaUt6NNyTNfENEyf0t9dzT4uaqb3e7pfhrcnmFJN5sY3SPxQF1MjJQ5bUZwWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:35:59.995259Z"},"content_sha256":"d015c9df9a3690a8777c6361cf9decc7c8abf165a11c9528a324f0174f79d993","schema_version":"1.0","event_id":"sha256:d015c9df9a3690a8777c6361cf9decc7c8abf165a11c9528a324f0174f79d993"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ORVKCFDEYSW5XBNE3XY5A42R2A/bundle.json","state_url":"https://pith.science/pith/ORVKCFDEYSW5XBNE3XY5A42R2A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ORVKCFDEYSW5XBNE3XY5A42R2A/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":"2026-08-18T09:35:59Z","links":{"resolver":"https://pith.science/pith/ORVKCFDEYSW5XBNE3XY5A42R2A","bundle":"https://pith.science/pith/ORVKCFDEYSW5XBNE3XY5A42R2A/bundle.json","state":"https://pith.science/pith/ORVKCFDEYSW5XBNE3XY5A42R2A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ORVKCFDEYSW5XBNE3XY5A42R2A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ORVKCFDEYSW5XBNE3XY5A42R2A","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":"1e143688e1231109a4895bad62ccd6195cab0363a3e65cf3c8958709a184bd14","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T15:09:37Z","title_canon_sha256":"7c35f240bef6011495cabc471ba55d2ba6df754092ff29ce7a8299c9638ffef5"},"schema_version":"1.0","source":{"id":"2403.00587","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00587","created_at":"2026-07-05T07:51:06Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00587v1","created_at":"2026-07-05T07:51:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00587","created_at":"2026-07-05T07:51:06Z"},{"alias_kind":"pith_short_12","alias_value":"ORVKCFDEYSW5","created_at":"2026-07-05T07:51:06Z"},{"alias_kind":"pith_short_16","alias_value":"ORVKCFDEYSW5XBNE","created_at":"2026-07-05T07:51:06Z"},{"alias_kind":"pith_short_8","alias_value":"ORVKCFDE","created_at":"2026-07-05T07:51:06Z"}],"graph_snapshots":[{"event_id":"sha256:d015c9df9a3690a8777c6361cf9decc7c8abf165a11c9528a324f0174f79d993","target":"graph","created_at":"2026-07-05T07:51:06Z","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/2403.00587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing work has observed that current text-to-image systems do not accurately reflect explicit spatial relations between objects such as 'left of' or 'below'. We hypothesize that this is because explicit spatial relations rarely appear in the image captions used to train these models. We propose an automatic method that, given existing images, generates synthetic captions that contain 14 explicit spatial relations. We introduce the Spatial Relation for Generation (SR4G) dataset, which contains 9.9 millions image-caption pairs for training, and more than 60 thousand captions for evaluation. I","authors_text":"Aitor Soroa, Ander Salaberria, Eneko Agirre, Frank Keller, Gorka Azkune, Oier Lopez de Lacalle","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T15:09:37Z","title":"Improving Explicit Spatial Relationships in Text-to-Image Generation through an Automatically Derived Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00587","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:e770c68a46eeff59764f27d39db67b4eed8b56af9aa3e64deee863ff75952804","target":"record","created_at":"2026-07-05T07:51:06Z","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":"1e143688e1231109a4895bad62ccd6195cab0363a3e65cf3c8958709a184bd14","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T15:09:37Z","title_canon_sha256":"7c35f240bef6011495cabc471ba55d2ba6df754092ff29ce7a8299c9638ffef5"},"schema_version":"1.0","source":{"id":"2403.00587","kind":"arxiv","version":1}},"canonical_sha256":"746aa11464c4addb85a4ddf1d07351d034c08e5aefdb29f78b2c934bb21d5e9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"746aa11464c4addb85a4ddf1d07351d034c08e5aefdb29f78b2c934bb21d5e9a","first_computed_at":"2026-07-05T07:51:06.155116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:06.155116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KDiYoSTZnkxGC1/9Dlh9kJlsaarsM8X7yyqv8k99TbhUxLkQwagwYeF7cEnml1tyleNkTsTnkEjHBZ8AgUfQBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:06.155656Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00587","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e770c68a46eeff59764f27d39db67b4eed8b56af9aa3e64deee863ff75952804","sha256:d015c9df9a3690a8777c6361cf9decc7c8abf165a11c9528a324f0174f79d993"],"state_sha256":"dabf1504323f5186d28b3175ed8a42ac482271e69ea19eab9039903d557bc37a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o9ncrp8NVSnNZHXFxQ28X7s7CfgJf/zd/1ppgQpLltLdsYWD92h9e4in4tlkft2PI3X66Z/jjPjUAXogA8l6Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T09:36:00.001450Z","bundle_sha256":"eba099e7fa8903da269264d20e8f8d5581f29fd70e21482d7595f58c893b4e62"}}