{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:B4ULDL6SNX7YXF2XEOUNL76S7O","short_pith_number":"pith:B4ULDL6S","canonical_record":{"source":{"id":"2403.14291","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T10:56:12Z","cross_cats_sorted":[],"title_canon_sha256":"8aeb1b19af71bec5caff96c6cc5b2cca6b2ce1447a3b7c7f99f958d256bb1a0e","abstract_canon_sha256":"c280a0069befb63d28cda38bdc3d3870e8230d1ef8878f5a020ad6782aa04885"},"schema_version":"1.0"},"canonical_sha256":"0f28b1afd26dff8b975723a8d5ffd2fbb07e873e9e76e7af52e103c0120a27fe","source":{"kind":"arxiv","id":"2403.14291","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14291","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14291v1","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14291","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"pith_short_12","alias_value":"B4ULDL6SNX7Y","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"pith_short_16","alias_value":"B4ULDL6SNX7YXF2X","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"pith_short_8","alias_value":"B4ULDL6S","created_at":"2026-07-05T08:32:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:B4ULDL6SNX7YXF2XEOUNL76S7O","target":"record","payload":{"canonical_record":{"source":{"id":"2403.14291","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T10:56:12Z","cross_cats_sorted":[],"title_canon_sha256":"8aeb1b19af71bec5caff96c6cc5b2cca6b2ce1447a3b7c7f99f958d256bb1a0e","abstract_canon_sha256":"c280a0069befb63d28cda38bdc3d3870e8230d1ef8878f5a020ad6782aa04885"},"schema_version":"1.0"},"canonical_sha256":"0f28b1afd26dff8b975723a8d5ffd2fbb07e873e9e76e7af52e103c0120a27fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:38.761637Z","signature_b64":"MOl8eKXZlYXon8zSRoVmJ6dtS4h/KE8LCbvSY01wXiOGniJHDO4ktjjx9s9wM55hrPLDWnuSquKnggI+SXMoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f28b1afd26dff8b975723a8d5ffd2fbb07e873e9e76e7af52e103c0120a27fe","last_reissued_at":"2026-07-05T08:32:38.761125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:38.761125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.14291","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":"2026-07-05T08:32:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ajuTHXA/05kf+tsjkJT19uAWCQUISyxZJDWtgs6CWVswDPRYRyzNMYkgyWhJK3TtJhm5iAQZ6hw9scjsOSrwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:55:07.227661Z"},"content_sha256":"2a727e7ae01f5be12fb794b365b9e6a54b24fea742760752973e5cf76ae20ff2","schema_version":"1.0","event_id":"sha256:2a727e7ae01f5be12fb794b365b9e6a54b24fea742760752973e5cf76ae20ff2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:B4ULDL6SNX7YXF2XEOUNL76S7O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jose M. Mart\\'inez, Juan C. SanMiguel, Pablo Marcos-Manch\\'on, Roberto Alcover-Couso","submitted_at":"2024-03-21T10:56:12Z","abstract_excerpt":"Diffusion models represent a new paradigm in text-to-image generation. Beyond generating high-quality images from text prompts, models such as Stable Diffusion have been successfully extended to the joint generation of semantic segmentation pseudo-masks. However, current extensions primarily rely on extracting attentions linked to prompt words used for image synthesis. This approach limits the generation of segmentation masks derived from word tokens not contained in the text prompt. In this work, we introduce Open-Vocabulary Attention Maps (OVAM)-a training-free method for text-to-image diffu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14291","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/2403.14291/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":"2026-07-05T08:32:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JTxOvHVZkx6dhQBpGhKH2W/BND+TssfHkgr68Bm4SPEl6+IL7XXbnlfmpMiOjjwTAbhB3IWA7Ml1tcDx75HNBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:55:07.228184Z"},"content_sha256":"62fa443c0c11fcfa91874bccf72163fc67aa74b38fc9fe6cb2466a2e5f4154a7","schema_version":"1.0","event_id":"sha256:62fa443c0c11fcfa91874bccf72163fc67aa74b38fc9fe6cb2466a2e5f4154a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B4ULDL6SNX7YXF2XEOUNL76S7O/bundle.json","state_url":"https://pith.science/pith/B4ULDL6SNX7YXF2XEOUNL76S7O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B4ULDL6SNX7YXF2XEOUNL76S7O/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":"2026-08-10T04:55:07Z","links":{"resolver":"https://pith.science/pith/B4ULDL6SNX7YXF2XEOUNL76S7O","bundle":"https://pith.science/pith/B4ULDL6SNX7YXF2XEOUNL76S7O/bundle.json","state":"https://pith.science/pith/B4ULDL6SNX7YXF2XEOUNL76S7O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B4ULDL6SNX7YXF2XEOUNL76S7O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B4ULDL6SNX7YXF2XEOUNL76S7O","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":"c280a0069befb63d28cda38bdc3d3870e8230d1ef8878f5a020ad6782aa04885","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T10:56:12Z","title_canon_sha256":"8aeb1b19af71bec5caff96c6cc5b2cca6b2ce1447a3b7c7f99f958d256bb1a0e"},"schema_version":"1.0","source":{"id":"2403.14291","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14291","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14291v1","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14291","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"pith_short_12","alias_value":"B4ULDL6SNX7Y","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"pith_short_16","alias_value":"B4ULDL6SNX7YXF2X","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"pith_short_8","alias_value":"B4ULDL6S","created_at":"2026-07-05T08:32:38Z"}],"graph_snapshots":[{"event_id":"sha256:62fa443c0c11fcfa91874bccf72163fc67aa74b38fc9fe6cb2466a2e5f4154a7","target":"graph","created_at":"2026-07-05T08:32:38Z","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/2403.14291/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models represent a new paradigm in text-to-image generation. Beyond generating high-quality images from text prompts, models such as Stable Diffusion have been successfully extended to the joint generation of semantic segmentation pseudo-masks. However, current extensions primarily rely on extracting attentions linked to prompt words used for image synthesis. This approach limits the generation of segmentation masks derived from word tokens not contained in the text prompt. In this work, we introduce Open-Vocabulary Attention Maps (OVAM)-a training-free method for text-to-image diffu","authors_text":"Jose M. Mart\\'inez, Juan C. SanMiguel, Pablo Marcos-Manch\\'on, Roberto Alcover-Couso","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T10:56:12Z","title":"Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14291","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":"sha256:2a727e7ae01f5be12fb794b365b9e6a54b24fea742760752973e5cf76ae20ff2","target":"record","created_at":"2026-07-05T08:32:38Z","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":"c280a0069befb63d28cda38bdc3d3870e8230d1ef8878f5a020ad6782aa04885","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T10:56:12Z","title_canon_sha256":"8aeb1b19af71bec5caff96c6cc5b2cca6b2ce1447a3b7c7f99f958d256bb1a0e"},"schema_version":"1.0","source":{"id":"2403.14291","kind":"arxiv","version":1}},"canonical_sha256":"0f28b1afd26dff8b975723a8d5ffd2fbb07e873e9e76e7af52e103c0120a27fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f28b1afd26dff8b975723a8d5ffd2fbb07e873e9e76e7af52e103c0120a27fe","first_computed_at":"2026-07-05T08:32:38.761125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:38.761125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MOl8eKXZlYXon8zSRoVmJ6dtS4h/KE8LCbvSY01wXiOGniJHDO4ktjjx9s9wM55hrPLDWnuSquKnggI+SXMoAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:38.761637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.14291","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a727e7ae01f5be12fb794b365b9e6a54b24fea742760752973e5cf76ae20ff2","sha256:62fa443c0c11fcfa91874bccf72163fc67aa74b38fc9fe6cb2466a2e5f4154a7"],"state_sha256":"5f0b6798d47a56e734309acea0d2099abca9b41ac2261c469cc730191c5ed286"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A3hAxvltcpb39FdKLkzI8GuRSSBacroDYFAnfWHFlgbuvP3hCgw5hjZQDLV11S/WGHUvIwK/Gf/OnytN27E3DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T04:55:07.232356Z","bundle_sha256":"db262a7612268582af6467298525471e8d88d5b63f7da18ed3c104e32e2c88df"}}