{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ADNTYHO44527NCEUXVNFP3CERY","short_pith_number":"pith:ADNTYHO4","canonical_record":{"source":{"id":"2309.04109","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-08T04:10:01Z","cross_cats_sorted":[],"title_canon_sha256":"b32b291fc95b28344e8fa73d4c826715df6f38974446f33f4c19772d57bbfb73","abstract_canon_sha256":"d255af7d8226b7ba0e74fed7e3a561852305df10389175632ebd237d94fecab0"},"schema_version":"1.0"},"canonical_sha256":"00db3c1ddce775f68894bd5a57ec448e3930ee04bb2476322c90c557aeda6d87","source":{"kind":"arxiv","id":"2309.04109","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04109","created_at":"2026-07-05T09:13:47Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04109v2","created_at":"2026-07-05T09:13:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04109","created_at":"2026-07-05T09:13:47Z"},{"alias_kind":"pith_short_12","alias_value":"ADNTYHO44527","created_at":"2026-07-05T09:13:47Z"},{"alias_kind":"pith_short_16","alias_value":"ADNTYHO44527NCEU","created_at":"2026-07-05T09:13:47Z"},{"alias_kind":"pith_short_8","alias_value":"ADNTYHO4","created_at":"2026-07-05T09:13:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ADNTYHO44527NCEUXVNFP3CERY","target":"record","payload":{"canonical_record":{"source":{"id":"2309.04109","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-08T04:10:01Z","cross_cats_sorted":[],"title_canon_sha256":"b32b291fc95b28344e8fa73d4c826715df6f38974446f33f4c19772d57bbfb73","abstract_canon_sha256":"d255af7d8226b7ba0e74fed7e3a561852305df10389175632ebd237d94fecab0"},"schema_version":"1.0"},"canonical_sha256":"00db3c1ddce775f68894bd5a57ec448e3930ee04bb2476322c90c557aeda6d87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:47.692289Z","signature_b64":"MxaU7z9SdW+OaPDBgwryy/RNIciXeaSvLLADxBXPeCKphSEHkiRdNGdQ7ASzvGmhVd16535OIzwEyrihv+5QDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00db3c1ddce775f68894bd5a57ec448e3930ee04bb2476322c90c557aeda6d87","last_reissued_at":"2026-07-05T09:13:47.691760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:47.691760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.04109","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":"2026-07-05T09:13:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WCqn9rwmd5h5UNYJLD50SyVA2xINhRdLt++VB0VWfrFvp/Yg+h1bkBDEeqBJLyNI5Uo69dqVwWN5jkkiyLpnAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T12:11:49.203832Z"},"content_sha256":"aea79f8e71875b511f101f7c481261692e989bf16c3fae9f09231fae2a8065f8","schema_version":"1.0","event_id":"sha256:aea79f8e71875b511f101f7c481261692e989bf16c3fae9f09231fae2a8065f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ADNTYHO44527NCEUXVNFP3CERY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changming Xiao, Changshui Zhang, Feng Zhou, Qi Yang","submitted_at":"2023-09-08T04:10:01Z","abstract_excerpt":"Diffusion models have revolted the field of text-to-image generation recently. The unique way of fusing text and image information contributes to their remarkable capability of generating highly text-related images. From another perspective, these generative models imply clues about the precise correlation between words and pixels. In this work, a simple but effective method is proposed to utilize the attention mechanism in the denoising network of text-to-image diffusion models. Without re-training nor inference-time optimization, the semantic grounding of phrases can be attained directly. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04109","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/2309.04109/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":"2026-07-05T09:13:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VkUPFBspbGuJBGouSnoKgls0VLfBdo2f6e5r4UPnA0QMBRElgu/fs6b33KaSiuqz+sJEQJMPh+tKG2s6AbXKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T12:11:49.204851Z"},"content_sha256":"86d841f8419b02d779e9120299eda2df5eacf2c0832fb6e901ba2e689a765c37","schema_version":"1.0","event_id":"sha256:86d841f8419b02d779e9120299eda2df5eacf2c0832fb6e901ba2e689a765c37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ADNTYHO44527NCEUXVNFP3CERY/bundle.json","state_url":"https://pith.science/pith/ADNTYHO44527NCEUXVNFP3CERY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ADNTYHO44527NCEUXVNFP3CERY/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":"2026-08-13T12:11:49Z","links":{"resolver":"https://pith.science/pith/ADNTYHO44527NCEUXVNFP3CERY","bundle":"https://pith.science/pith/ADNTYHO44527NCEUXVNFP3CERY/bundle.json","state":"https://pith.science/pith/ADNTYHO44527NCEUXVNFP3CERY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ADNTYHO44527NCEUXVNFP3CERY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ADNTYHO44527NCEUXVNFP3CERY","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":"d255af7d8226b7ba0e74fed7e3a561852305df10389175632ebd237d94fecab0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-08T04:10:01Z","title_canon_sha256":"b32b291fc95b28344e8fa73d4c826715df6f38974446f33f4c19772d57bbfb73"},"schema_version":"1.0","source":{"id":"2309.04109","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04109","created_at":"2026-07-05T09:13:47Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04109v2","created_at":"2026-07-05T09:13:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04109","created_at":"2026-07-05T09:13:47Z"},{"alias_kind":"pith_short_12","alias_value":"ADNTYHO44527","created_at":"2026-07-05T09:13:47Z"},{"alias_kind":"pith_short_16","alias_value":"ADNTYHO44527NCEU","created_at":"2026-07-05T09:13:47Z"},{"alias_kind":"pith_short_8","alias_value":"ADNTYHO4","created_at":"2026-07-05T09:13:47Z"}],"graph_snapshots":[{"event_id":"sha256:86d841f8419b02d779e9120299eda2df5eacf2c0832fb6e901ba2e689a765c37","target":"graph","created_at":"2026-07-05T09:13:47Z","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/2309.04109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have revolted the field of text-to-image generation recently. The unique way of fusing text and image information contributes to their remarkable capability of generating highly text-related images. From another perspective, these generative models imply clues about the precise correlation between words and pixels. In this work, a simple but effective method is proposed to utilize the attention mechanism in the denoising network of text-to-image diffusion models. Without re-training nor inference-time optimization, the semantic grounding of phrases can be attained directly. We","authors_text":"Changming Xiao, Changshui Zhang, Feng Zhou, Qi Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-08T04:10:01Z","title":"From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04109","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:aea79f8e71875b511f101f7c481261692e989bf16c3fae9f09231fae2a8065f8","target":"record","created_at":"2026-07-05T09:13:47Z","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":"d255af7d8226b7ba0e74fed7e3a561852305df10389175632ebd237d94fecab0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-08T04:10:01Z","title_canon_sha256":"b32b291fc95b28344e8fa73d4c826715df6f38974446f33f4c19772d57bbfb73"},"schema_version":"1.0","source":{"id":"2309.04109","kind":"arxiv","version":2}},"canonical_sha256":"00db3c1ddce775f68894bd5a57ec448e3930ee04bb2476322c90c557aeda6d87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00db3c1ddce775f68894bd5a57ec448e3930ee04bb2476322c90c557aeda6d87","first_computed_at":"2026-07-05T09:13:47.691760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:47.691760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MxaU7z9SdW+OaPDBgwryy/RNIciXeaSvLLADxBXPeCKphSEHkiRdNGdQ7ASzvGmhVd16535OIzwEyrihv+5QDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:47.692289Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.04109","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aea79f8e71875b511f101f7c481261692e989bf16c3fae9f09231fae2a8065f8","sha256:86d841f8419b02d779e9120299eda2df5eacf2c0832fb6e901ba2e689a765c37"],"state_sha256":"da311c434508b554964a8f67991c7a889482aad12cc26f08aceecb4453079614"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HitlvCbzylKh6h5Q1uUZ4ts6G69VxUt2FZQWY+K7MLEpn32u6LE8xdblVhSW5HX3ptZ55I/Q1hBpSqidGQgbAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T12:11:49.221100Z","bundle_sha256":"c49cfd0caef5eb9a294b3680408d25479ae8c92f1987c5f4d894dff0d34fbb55"}}