{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6OIOEZYLJOQNPXPR4D4WL3RSEU","short_pith_number":"pith:6OIOEZYL","canonical_record":{"source":{"id":"2411.15236","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T23:37:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1d806d9e9cd4880b373df3a1dfa76d9a60914e98a2891368497337eb8dfe44f1","abstract_canon_sha256":"17609ec89e74c569f8ec6c01a42f20eff88dc61abfc889fa838cf795c2d6d9c0"},"schema_version":"1.0"},"canonical_sha256":"f390e2670b4ba0d7ddf1e0f965ee32252aeabb853f6b9ea3a79d03eb56a94179","source":{"kind":"arxiv","id":"2411.15236","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15236","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15236v1","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15236","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"pith_short_12","alias_value":"6OIOEZYLJOQN","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"pith_short_16","alias_value":"6OIOEZYLJOQNPXPR","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"pith_short_8","alias_value":"6OIOEZYL","created_at":"2026-07-05T09:39:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6OIOEZYLJOQNPXPR4D4WL3RSEU","target":"record","payload":{"canonical_record":{"source":{"id":"2411.15236","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T23:37:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1d806d9e9cd4880b373df3a1dfa76d9a60914e98a2891368497337eb8dfe44f1","abstract_canon_sha256":"17609ec89e74c569f8ec6c01a42f20eff88dc61abfc889fa838cf795c2d6d9c0"},"schema_version":"1.0"},"canonical_sha256":"f390e2670b4ba0d7ddf1e0f965ee32252aeabb853f6b9ea3a79d03eb56a94179","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:31.602180Z","signature_b64":"X2kvZUTpJDP0eU4YRTO4PK1EdLVyzDsr7kUNx0MxyjGWg7QpHqgV25uOLsEDMXVUgu+4RNyji0q950wwcx5tDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f390e2670b4ba0d7ddf1e0f965ee32252aeabb853f6b9ea3a79d03eb56a94179","last_reissued_at":"2026-07-05T09:39:31.601688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:31.601688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.15236","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":"2026-07-05T09:39:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9XIXcOusmqvlg+SJ0vxuGU7Vl2Xjy1n/witRh2O3m+h2lFaNDqNocEYICh0KVtwTt+3aXoFmz/8RMQ0KkndtAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:32:39.736289Z"},"content_sha256":"e68c9d02ffe2dd6ac6bdf62ba3e4d149cc95a373046c3ac516c0e44839419f9a","schema_version":"1.0","event_id":"sha256:e68c9d02ffe2dd6ac6bdf62ba3e4d149cc95a373046c3ac516c0e44839419f9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6OIOEZYLJOQNPXPR4D4WL3RSEU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Erfan Esmaeili, Jeeyung Kim, Qiang Qiu","submitted_at":"2024-11-21T23:37:03Z","abstract_excerpt":"In text-to-image diffusion models, the cross-attention map of each text token indicates the specific image regions attended. Comparing these maps of syntactically related tokens provides insights into how well the generated image reflects the text prompt. For example, in the prompt, \"a black car and a white clock\", the cross-attention maps for \"black\" and \"car\" should focus on overlapping regions to depict a black car, while \"car\" and \"clock\" should not. Incorrect overlapping in the maps generally produces generation flaws such as missing objects and incorrect attribute binding. Our study make"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15236","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/2411.15236/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":"2026-07-05T09:39:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"axv5I2CVYpES1xlAQ066QOl2KQpyDfhzqJQl1vATmieZ/Ko2ucKt25Ryj5xje5I44OYUM2NTB9qJoiExJK13Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:32:39.736936Z"},"content_sha256":"187942f1fd80f1c44554a0f2b8077a23d69ce65ed8710b07e76c4abefadbd855","schema_version":"1.0","event_id":"sha256:187942f1fd80f1c44554a0f2b8077a23d69ce65ed8710b07e76c4abefadbd855"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6OIOEZYLJOQNPXPR4D4WL3RSEU/bundle.json","state_url":"https://pith.science/pith/6OIOEZYLJOQNPXPR4D4WL3RSEU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6OIOEZYLJOQNPXPR4D4WL3RSEU/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":"2026-08-12T23:32:39Z","links":{"resolver":"https://pith.science/pith/6OIOEZYLJOQNPXPR4D4WL3RSEU","bundle":"https://pith.science/pith/6OIOEZYLJOQNPXPR4D4WL3RSEU/bundle.json","state":"https://pith.science/pith/6OIOEZYLJOQNPXPR4D4WL3RSEU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6OIOEZYLJOQNPXPR4D4WL3RSEU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6OIOEZYLJOQNPXPR4D4WL3RSEU","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":"17609ec89e74c569f8ec6c01a42f20eff88dc61abfc889fa838cf795c2d6d9c0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T23:37:03Z","title_canon_sha256":"1d806d9e9cd4880b373df3a1dfa76d9a60914e98a2891368497337eb8dfe44f1"},"schema_version":"1.0","source":{"id":"2411.15236","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15236","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15236v1","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15236","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"pith_short_12","alias_value":"6OIOEZYLJOQN","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"pith_short_16","alias_value":"6OIOEZYLJOQNPXPR","created_at":"2026-07-05T09:39:31Z"},{"alias_kind":"pith_short_8","alias_value":"6OIOEZYL","created_at":"2026-07-05T09:39:31Z"}],"graph_snapshots":[{"event_id":"sha256:187942f1fd80f1c44554a0f2b8077a23d69ce65ed8710b07e76c4abefadbd855","target":"graph","created_at":"2026-07-05T09:39:31Z","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/2411.15236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In text-to-image diffusion models, the cross-attention map of each text token indicates the specific image regions attended. Comparing these maps of syntactically related tokens provides insights into how well the generated image reflects the text prompt. For example, in the prompt, \"a black car and a white clock\", the cross-attention maps for \"black\" and \"car\" should focus on overlapping regions to depict a black car, while \"car\" and \"clock\" should not. Incorrect overlapping in the maps generally produces generation flaws such as missing objects and incorrect attribute binding. Our study make","authors_text":"Erfan Esmaeili, Jeeyung Kim, Qiang Qiu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T23:37:03Z","title":"Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15236","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:e68c9d02ffe2dd6ac6bdf62ba3e4d149cc95a373046c3ac516c0e44839419f9a","target":"record","created_at":"2026-07-05T09:39:31Z","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":"17609ec89e74c569f8ec6c01a42f20eff88dc61abfc889fa838cf795c2d6d9c0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T23:37:03Z","title_canon_sha256":"1d806d9e9cd4880b373df3a1dfa76d9a60914e98a2891368497337eb8dfe44f1"},"schema_version":"1.0","source":{"id":"2411.15236","kind":"arxiv","version":1}},"canonical_sha256":"f390e2670b4ba0d7ddf1e0f965ee32252aeabb853f6b9ea3a79d03eb56a94179","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f390e2670b4ba0d7ddf1e0f965ee32252aeabb853f6b9ea3a79d03eb56a94179","first_computed_at":"2026-07-05T09:39:31.601688Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:31.601688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X2kvZUTpJDP0eU4YRTO4PK1EdLVyzDsr7kUNx0MxyjGWg7QpHqgV25uOLsEDMXVUgu+4RNyji0q950wwcx5tDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:31.602180Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15236","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e68c9d02ffe2dd6ac6bdf62ba3e4d149cc95a373046c3ac516c0e44839419f9a","sha256:187942f1fd80f1c44554a0f2b8077a23d69ce65ed8710b07e76c4abefadbd855"],"state_sha256":"e49a96433cc613db7eb68528246cc3004f2e640679a2f1d8f685c885bad8a9e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DsE5r2+Z9acwpCzl1Vr0NKHoYmOohSXkV8vsjzF2j/NyxvFOSpOhcscbfuAQMfg2ZWhUFNpFD/Y8WEuE1by/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T23:32:39.751014Z","bundle_sha256":"27fb9d5512204911d0b7fb572f5afdef32738a3a97a1f9bfd2e22d3ec8706f65"}}