{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WH5PNRILDP4TXLINEVE6OENSEV","short_pith_number":"pith:WH5PNRIL","canonical_record":{"source":{"id":"2306.14636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-26T12:15:06Z","cross_cats_sorted":[],"title_canon_sha256":"eb1a362c420062cf41f39c1bece7c92ea433be490b1891e92664cfe4a8b694ad","abstract_canon_sha256":"a03d9c4678ece263808fbfb2ee87d942291f0ecf76a3c51220653e21fd06f9ff"},"schema_version":"1.0"},"canonical_sha256":"b1faf6c50b1bf93bad0d2549e711b225426fe1171b3f5c04a072025514a2be5e","source":{"kind":"arxiv","id":"2306.14636","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14636","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14636v1","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14636","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"pith_short_12","alias_value":"WH5PNRILDP4T","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"pith_short_16","alias_value":"WH5PNRILDP4TXLIN","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"pith_short_8","alias_value":"WH5PNRIL","created_at":"2026-07-05T06:24:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WH5PNRILDP4TXLINEVE6OENSEV","target":"record","payload":{"canonical_record":{"source":{"id":"2306.14636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-26T12:15:06Z","cross_cats_sorted":[],"title_canon_sha256":"eb1a362c420062cf41f39c1bece7c92ea433be490b1891e92664cfe4a8b694ad","abstract_canon_sha256":"a03d9c4678ece263808fbfb2ee87d942291f0ecf76a3c51220653e21fd06f9ff"},"schema_version":"1.0"},"canonical_sha256":"b1faf6c50b1bf93bad0d2549e711b225426fe1171b3f5c04a072025514a2be5e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:38.923551Z","signature_b64":"Wytzo5rGA4BrwNhw4LKB3DOtoZzrOr3RFq0t+K6Yv+4yzhfoABDbZJJ6NlAi6WjrOOXYMVSGJEUMw/J/ySIrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1faf6c50b1bf93bad0d2549e711b225426fe1171b3f5c04a072025514a2be5e","last_reissued_at":"2026-07-05T06:24:38.923136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:38.923136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.14636","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":"2026-07-05T06:24:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V9Fsb0TE8amB3x37hpc/9ixVqogkBBK6pnZzm8SEW704A0MOsfsimJw/dBxGyW0wUimm2nwvWu/ACVHIjOV0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:10:48.885654Z"},"content_sha256":"32df34db033afcf683a0a1c09772fd761d76bec0e2b7aec03db4d8e75b3f324b","schema_version":"1.0","event_id":"sha256:32df34db033afcf683a0a1c09772fd761d76bec0e2b7aec03db4d8e75b3f324b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WH5PNRILDP4TXLINEVE6OENSEV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Localized Text-to-Image Generation for Free via Cross Attention Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"J. Zico Kolter, Ruslan Salakhutdinov, Yutong He","submitted_at":"2023-06-26T12:15:06Z","abstract_excerpt":"Despite the tremendous success in text-to-image generative models, localized text-to-image generation (that is, generating objects or features at specific locations in an image while maintaining a consistent overall generation) still requires either explicit training or substantial additional inference time. In this work, we show that localized generation can be achieved by simply controlling cross attention maps during inference. With no additional training, model architecture modification or inference time, our proposed cross attention control (CAC) provides new open-vocabulary localization "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14636","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/2306.14636/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":"2026-07-05T06:24:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BwRNegkYyxoq4+ZoMC3jKwFIy9ekdD4jALh6j61Mb96UIRiVxLamFwmIP0fw5S+tbyeh6z/IiaGX1Fqa+ElpAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:10:48.886263Z"},"content_sha256":"7f39f3dbecc1025be0e76fb3560c86ff1381e9832d9abf1b4a034200d2009752","schema_version":"1.0","event_id":"sha256:7f39f3dbecc1025be0e76fb3560c86ff1381e9832d9abf1b4a034200d2009752"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WH5PNRILDP4TXLINEVE6OENSEV/bundle.json","state_url":"https://pith.science/pith/WH5PNRILDP4TXLINEVE6OENSEV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WH5PNRILDP4TXLINEVE6OENSEV/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":"2026-08-06T08:10:48Z","links":{"resolver":"https://pith.science/pith/WH5PNRILDP4TXLINEVE6OENSEV","bundle":"https://pith.science/pith/WH5PNRILDP4TXLINEVE6OENSEV/bundle.json","state":"https://pith.science/pith/WH5PNRILDP4TXLINEVE6OENSEV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WH5PNRILDP4TXLINEVE6OENSEV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WH5PNRILDP4TXLINEVE6OENSEV","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":"a03d9c4678ece263808fbfb2ee87d942291f0ecf76a3c51220653e21fd06f9ff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-26T12:15:06Z","title_canon_sha256":"eb1a362c420062cf41f39c1bece7c92ea433be490b1891e92664cfe4a8b694ad"},"schema_version":"1.0","source":{"id":"2306.14636","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14636","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14636v1","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14636","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"pith_short_12","alias_value":"WH5PNRILDP4T","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"pith_short_16","alias_value":"WH5PNRILDP4TXLIN","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"pith_short_8","alias_value":"WH5PNRIL","created_at":"2026-07-05T06:24:38Z"}],"graph_snapshots":[{"event_id":"sha256:7f39f3dbecc1025be0e76fb3560c86ff1381e9832d9abf1b4a034200d2009752","target":"graph","created_at":"2026-07-05T06:24:38Z","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/2306.14636/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the tremendous success in text-to-image generative models, localized text-to-image generation (that is, generating objects or features at specific locations in an image while maintaining a consistent overall generation) still requires either explicit training or substantial additional inference time. In this work, we show that localized generation can be achieved by simply controlling cross attention maps during inference. With no additional training, model architecture modification or inference time, our proposed cross attention control (CAC) provides new open-vocabulary localization ","authors_text":"J. Zico Kolter, Ruslan Salakhutdinov, Yutong He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-26T12:15:06Z","title":"Localized Text-to-Image Generation for Free via Cross Attention Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14636","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":"sha256:32df34db033afcf683a0a1c09772fd761d76bec0e2b7aec03db4d8e75b3f324b","target":"record","created_at":"2026-07-05T06:24:38Z","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":"a03d9c4678ece263808fbfb2ee87d942291f0ecf76a3c51220653e21fd06f9ff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-26T12:15:06Z","title_canon_sha256":"eb1a362c420062cf41f39c1bece7c92ea433be490b1891e92664cfe4a8b694ad"},"schema_version":"1.0","source":{"id":"2306.14636","kind":"arxiv","version":1}},"canonical_sha256":"b1faf6c50b1bf93bad0d2549e711b225426fe1171b3f5c04a072025514a2be5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1faf6c50b1bf93bad0d2549e711b225426fe1171b3f5c04a072025514a2be5e","first_computed_at":"2026-07-05T06:24:38.923136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:38.923136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wytzo5rGA4BrwNhw4LKB3DOtoZzrOr3RFq0t+K6Yv+4yzhfoABDbZJJ6NlAi6WjrOOXYMVSGJEUMw/J/ySIrBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:38.923551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.14636","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32df34db033afcf683a0a1c09772fd761d76bec0e2b7aec03db4d8e75b3f324b","sha256:7f39f3dbecc1025be0e76fb3560c86ff1381e9832d9abf1b4a034200d2009752"],"state_sha256":"194c3f22b1b21884153c1af48a466930f0b982346c711bf43b6f4ce2572bfec1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tkNY7fPw5WcpI+KW/iI+SQSW22lNjfBWeiXkjAQuozK/4dKR8aLWzCOjd+5bwAEKzLji8kCLIt9XYmFHukRNDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:10:48.892787Z","bundle_sha256":"eecabb75e6fb26f85b214101b8641ad9baad4f3d6f85dd7b07b183dab2b12dd2"}}