{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:25ZM27YGHAPHBMGVDFFOQ45QQG","short_pith_number":"pith:25ZM27YG","canonical_record":{"source":{"id":"2404.03653","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T17:59:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d35187837b28d090209cc126d6d68b0f146efacdde462090cf32d46eb8881cc6","abstract_canon_sha256":"2c8a93021a62388bd88cec3533fba9fc4d48e7d68cfad890876924dabd81a50a"},"schema_version":"1.0"},"canonical_sha256":"d772cd7f06381e70b0d5194ae873b081abcf87b4108c5fe4a16a9aa5120be011","source":{"kind":"arxiv","id":"2404.03653","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03653","created_at":"2026-07-05T09:40:56Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03653v3","created_at":"2026-07-05T09:40:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03653","created_at":"2026-07-05T09:40:56Z"},{"alias_kind":"pith_short_12","alias_value":"25ZM27YGHAPH","created_at":"2026-07-05T09:40:56Z"},{"alias_kind":"pith_short_16","alias_value":"25ZM27YGHAPHBMGV","created_at":"2026-07-05T09:40:56Z"},{"alias_kind":"pith_short_8","alias_value":"25ZM27YG","created_at":"2026-07-05T09:40:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:25ZM27YGHAPHBMGVDFFOQ45QQG","target":"record","payload":{"canonical_record":{"source":{"id":"2404.03653","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T17:59:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d35187837b28d090209cc126d6d68b0f146efacdde462090cf32d46eb8881cc6","abstract_canon_sha256":"2c8a93021a62388bd88cec3533fba9fc4d48e7d68cfad890876924dabd81a50a"},"schema_version":"1.0"},"canonical_sha256":"d772cd7f06381e70b0d5194ae873b081abcf87b4108c5fe4a16a9aa5120be011","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:56.416553Z","signature_b64":"bbt7nGdStZj3tdcR6scAqTRO149ajIhCOZ4NwNhXKzC1JoEGP2cpQSkiIjAA7Ove+plsmruOtc0172AfaSUkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d772cd7f06381e70b0d5194ae873b081abcf87b4108c5fe4a16a9aa5120be011","last_reissued_at":"2026-07-05T09:40:56.416026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:56.416026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.03653","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:40:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BEqdrqKK145e+WkFxiWoPzIShs4MygZ75Aq9BcO6tXfykoUCEReC5F50GTT0yRqqXy2VarthIfVccyZKVtgsDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:53:29.796887Z"},"content_sha256":"fb884b722871dac95e9af2b93970ef145db0be55974ac941c3a43fa610b68c36","schema_version":"1.0","event_id":"sha256:fb884b722871dac95e9af2b93970ef145db0be55974ac941c3a43fa610b68c36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:25ZM27YGHAPHBMGVDFFOQ45QQG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Dazhong Shen, Dongzhi Jiang, Guanglu Song, Hongsheng Li, Renrui Zhang, Xiaoshi Wu, Yu Liu, Zhuofan Zong","submitted_at":"2024-04-04T17:59:46Z","abstract_excerpt":"Diffusion models have demonstrated great success in the field of text-to-image generation. However, alleviating the misalignment between the text prompts and images is still challenging. The root reason behind the misalignment has not been extensively investigated. We observe that the misalignment is caused by inadequate token attention activation. We further attribute this phenomenon to the diffusion model's insufficient condition utilization, which is caused by its training paradigm. To address the issue, we propose CoMat, an end-to-end diffusion model fine-tuning strategy with an image-to-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03653","kind":"arxiv","version":3},"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/2404.03653/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":"2026-07-05T09:40:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HCO+Qkg5k62OTGBHUEFpEToZ/k4D66jP1BZ5nA16/A1f2xzC7qsa/R9V//ebMnDiPSa5Qtioi0Z9oBTMZZH/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:53:29.797273Z"},"content_sha256":"b1acd118a3ae2a1a26dab2228f01dfe1b19b9f2b338eb4e5416651d76a0c48b4","schema_version":"1.0","event_id":"sha256:b1acd118a3ae2a1a26dab2228f01dfe1b19b9f2b338eb4e5416651d76a0c48b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/25ZM27YGHAPHBMGVDFFOQ45QQG/bundle.json","state_url":"https://pith.science/pith/25ZM27YGHAPHBMGVDFFOQ45QQG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/25ZM27YGHAPHBMGVDFFOQ45QQG/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":"2026-07-07T14:53:29Z","links":{"resolver":"https://pith.science/pith/25ZM27YGHAPHBMGVDFFOQ45QQG","bundle":"https://pith.science/pith/25ZM27YGHAPHBMGVDFFOQ45QQG/bundle.json","state":"https://pith.science/pith/25ZM27YGHAPHBMGVDFFOQ45QQG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/25ZM27YGHAPHBMGVDFFOQ45QQG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:25ZM27YGHAPHBMGVDFFOQ45QQG","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":"2c8a93021a62388bd88cec3533fba9fc4d48e7d68cfad890876924dabd81a50a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T17:59:46Z","title_canon_sha256":"d35187837b28d090209cc126d6d68b0f146efacdde462090cf32d46eb8881cc6"},"schema_version":"1.0","source":{"id":"2404.03653","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03653","created_at":"2026-07-05T09:40:56Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03653v3","created_at":"2026-07-05T09:40:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03653","created_at":"2026-07-05T09:40:56Z"},{"alias_kind":"pith_short_12","alias_value":"25ZM27YGHAPH","created_at":"2026-07-05T09:40:56Z"},{"alias_kind":"pith_short_16","alias_value":"25ZM27YGHAPHBMGV","created_at":"2026-07-05T09:40:56Z"},{"alias_kind":"pith_short_8","alias_value":"25ZM27YG","created_at":"2026-07-05T09:40:56Z"}],"graph_snapshots":[{"event_id":"sha256:b1acd118a3ae2a1a26dab2228f01dfe1b19b9f2b338eb4e5416651d76a0c48b4","target":"graph","created_at":"2026-07-05T09:40:56Z","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/2404.03653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have demonstrated great success in the field of text-to-image generation. However, alleviating the misalignment between the text prompts and images is still challenging. The root reason behind the misalignment has not been extensively investigated. We observe that the misalignment is caused by inadequate token attention activation. We further attribute this phenomenon to the diffusion model's insufficient condition utilization, which is caused by its training paradigm. To address the issue, we propose CoMat, an end-to-end diffusion model fine-tuning strategy with an image-to-t","authors_text":"Dazhong Shen, Dongzhi Jiang, Guanglu Song, Hongsheng Li, Renrui Zhang, Xiaoshi Wu, Yu Liu, Zhuofan Zong","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T17:59:46Z","title":"CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03653","kind":"arxiv","version":3},"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:fb884b722871dac95e9af2b93970ef145db0be55974ac941c3a43fa610b68c36","target":"record","created_at":"2026-07-05T09:40:56Z","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":"2c8a93021a62388bd88cec3533fba9fc4d48e7d68cfad890876924dabd81a50a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T17:59:46Z","title_canon_sha256":"d35187837b28d090209cc126d6d68b0f146efacdde462090cf32d46eb8881cc6"},"schema_version":"1.0","source":{"id":"2404.03653","kind":"arxiv","version":3}},"canonical_sha256":"d772cd7f06381e70b0d5194ae873b081abcf87b4108c5fe4a16a9aa5120be011","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d772cd7f06381e70b0d5194ae873b081abcf87b4108c5fe4a16a9aa5120be011","first_computed_at":"2026-07-05T09:40:56.416026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:56.416026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bbt7nGdStZj3tdcR6scAqTRO149ajIhCOZ4NwNhXKzC1JoEGP2cpQSkiIjAA7Ove+plsmruOtc0172AfaSUkAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:56.416553Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.03653","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb884b722871dac95e9af2b93970ef145db0be55974ac941c3a43fa610b68c36","sha256:b1acd118a3ae2a1a26dab2228f01dfe1b19b9f2b338eb4e5416651d76a0c48b4"],"state_sha256":"5685143ece395b6658daeed44878b2b44d01bbeac0e67651cea6a9b4ffb551bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K6V3jHLxJH4AUjOEeCiLEsQee/vJTC7z8fqW/kQJZZAUHPLtanlEQULjffLxNSaEv6VN9W73q6qjQQP95QWHCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:53:29.799287Z","bundle_sha256":"8a64b835f4fa9f2dc46ba5cdbcf17924deb991f359a54d2eff10be7ed8c1d1ed"}}