{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2V7MGPF5LIAWRM33PX4GJUOLVL","short_pith_number":"pith:2V7MGPF5","canonical_record":{"source":{"id":"2412.13195","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T18:59:50Z","cross_cats_sorted":[],"title_canon_sha256":"7e273780574c7b1a461253b03e7e132a824304d9b3c2fa502703122dd64bf542","abstract_canon_sha256":"0413b460f8f727a64b57abca79c2ff7e934bcd6e6a863fda02ce06c6095a5243"},"schema_version":"1.0"},"canonical_sha256":"d57ec33cbd5a0168b37b7df864d1cbaaf5339b2cc9eb3db8ccb41e15d25d6bfc","source":{"kind":"arxiv","id":"2412.13195","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13195","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13195v2","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13195","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"2V7MGPF5LIAW","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"pith_short_16","alias_value":"2V7MGPF5LIAWRM33","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"pith_short_8","alias_value":"2V7MGPF5","created_at":"2026-07-05T11:58:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2V7MGPF5LIAWRM33PX4GJUOLVL","target":"record","payload":{"canonical_record":{"source":{"id":"2412.13195","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T18:59:50Z","cross_cats_sorted":[],"title_canon_sha256":"7e273780574c7b1a461253b03e7e132a824304d9b3c2fa502703122dd64bf542","abstract_canon_sha256":"0413b460f8f727a64b57abca79c2ff7e934bcd6e6a863fda02ce06c6095a5243"},"schema_version":"1.0"},"canonical_sha256":"d57ec33cbd5a0168b37b7df864d1cbaaf5339b2cc9eb3db8ccb41e15d25d6bfc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:22.931540Z","signature_b64":"FNYAVdmQTEktVMt1y0mWim5vaiKQHc9U5XVei4ZzQcz0DFsVlZWJIs4OYpUS5EIgkVF0MBk6ZYK8ZTKRy4jzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d57ec33cbd5a0168b37b7df864d1cbaaf5339b2cc9eb3db8ccb41e15d25d6bfc","last_reissued_at":"2026-07-05T11:58:22.930982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:22.930982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.13195","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:58:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rP38QfbCxiP0hI+VqY4xhu/gRlAcS9oJiBFN5Ofi2YSwwzlUs+8uShIU6/ntQNm3Qu5ql/gBkX6wlfK49zUUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:49:57.998983Z"},"content_sha256":"1bd03fe913128b15f99eb101e1a22021b2a3bb9638f1c222aa1357aec352f764","schema_version":"1.0","event_id":"sha256:1bd03fe913128b15f99eb101e1a22021b2a3bb9638f1c222aa1357aec352f764"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2V7MGPF5LIAWRM33PX4GJUOLVL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingtao Fu, Gaoyang Zhang, Hong Gu, Huaqi Zhang, Qingnan Fan, Qi Zhang, Runxing Liu, Xinguo Liu","submitted_at":"2024-12-17T18:59:50Z","abstract_excerpt":"Text-to-image (T2I) diffusion models excel at generating photorealistic images but often fail to render accurate spatial relationships. We identify two core issues underlying this common failure: 1) the ambiguous nature of data concerning spatial relationships in existing datasets, and 2) the inability of current text encoders to accurately interpret the spatial semantics of input descriptions. We propose CoMPaSS, a versatile framework that enhances spatial understanding in T2I models. It first addresses data ambiguity with the Spatial Constraints-Oriented Pairing (SCOP) data engine, which cur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13195","kind":"arxiv","version":2},"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/2412.13195/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":"2026-07-05T11:58:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RwSE79D9VHn5Pwu0w7XGHD0ziEaQKoHp/xxRAZRbJveX/BiYKc7a6cQCrf3nLzC4XC5nIZOghkH3Wdt3u1S3Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:49:57.999373Z"},"content_sha256":"7d3ee0f652d19874a6435d84d379ecb231106c3da5bd7bcafe78ac4a353625eb","schema_version":"1.0","event_id":"sha256:7d3ee0f652d19874a6435d84d379ecb231106c3da5bd7bcafe78ac4a353625eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2V7MGPF5LIAWRM33PX4GJUOLVL/bundle.json","state_url":"https://pith.science/pith/2V7MGPF5LIAWRM33PX4GJUOLVL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2V7MGPF5LIAWRM33PX4GJUOLVL/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":"2026-07-07T10:49:58Z","links":{"resolver":"https://pith.science/pith/2V7MGPF5LIAWRM33PX4GJUOLVL","bundle":"https://pith.science/pith/2V7MGPF5LIAWRM33PX4GJUOLVL/bundle.json","state":"https://pith.science/pith/2V7MGPF5LIAWRM33PX4GJUOLVL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2V7MGPF5LIAWRM33PX4GJUOLVL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2V7MGPF5LIAWRM33PX4GJUOLVL","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":"0413b460f8f727a64b57abca79c2ff7e934bcd6e6a863fda02ce06c6095a5243","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T18:59:50Z","title_canon_sha256":"7e273780574c7b1a461253b03e7e132a824304d9b3c2fa502703122dd64bf542"},"schema_version":"1.0","source":{"id":"2412.13195","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13195","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13195v2","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13195","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"2V7MGPF5LIAW","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"pith_short_16","alias_value":"2V7MGPF5LIAWRM33","created_at":"2026-07-05T11:58:22Z"},{"alias_kind":"pith_short_8","alias_value":"2V7MGPF5","created_at":"2026-07-05T11:58:22Z"}],"graph_snapshots":[{"event_id":"sha256:7d3ee0f652d19874a6435d84d379ecb231106c3da5bd7bcafe78ac4a353625eb","target":"graph","created_at":"2026-07-05T11:58:22Z","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/2412.13195/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-image (T2I) diffusion models excel at generating photorealistic images but often fail to render accurate spatial relationships. We identify two core issues underlying this common failure: 1) the ambiguous nature of data concerning spatial relationships in existing datasets, and 2) the inability of current text encoders to accurately interpret the spatial semantics of input descriptions. We propose CoMPaSS, a versatile framework that enhances spatial understanding in T2I models. It first addresses data ambiguity with the Spatial Constraints-Oriented Pairing (SCOP) data engine, which cur","authors_text":"Bingtao Fu, Gaoyang Zhang, Hong Gu, Huaqi Zhang, Qingnan Fan, Qi Zhang, Runxing Liu, Xinguo Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T18:59:50Z","title":"CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13195","kind":"arxiv","version":2},"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":"sha256:1bd03fe913128b15f99eb101e1a22021b2a3bb9638f1c222aa1357aec352f764","target":"record","created_at":"2026-07-05T11:58:22Z","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":"0413b460f8f727a64b57abca79c2ff7e934bcd6e6a863fda02ce06c6095a5243","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T18:59:50Z","title_canon_sha256":"7e273780574c7b1a461253b03e7e132a824304d9b3c2fa502703122dd64bf542"},"schema_version":"1.0","source":{"id":"2412.13195","kind":"arxiv","version":2}},"canonical_sha256":"d57ec33cbd5a0168b37b7df864d1cbaaf5339b2cc9eb3db8ccb41e15d25d6bfc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d57ec33cbd5a0168b37b7df864d1cbaaf5339b2cc9eb3db8ccb41e15d25d6bfc","first_computed_at":"2026-07-05T11:58:22.930982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:22.930982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FNYAVdmQTEktVMt1y0mWim5vaiKQHc9U5XVei4ZzQcz0DFsVlZWJIs4OYpUS5EIgkVF0MBk6ZYK8ZTKRy4jzBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:22.931540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13195","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bd03fe913128b15f99eb101e1a22021b2a3bb9638f1c222aa1357aec352f764","sha256:7d3ee0f652d19874a6435d84d379ecb231106c3da5bd7bcafe78ac4a353625eb"],"state_sha256":"f7a7cc6573af36227c2883aa72b57ac50adf43a677e818ac9cb812a03943e252"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KJST2FLdRsncSQBuhYFuoU+xBnHX0WuPd/UIO6TXRH/H2lBc75ohD+fL9RWt4Z4ZI08Vp9RznzYgOZoNvysnAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:49:58.001262Z","bundle_sha256":"6f373d3fa8922582b93f9b1945782a5bae5a4d4bd51176854bfebbaac4e982c6"}}