{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:G5ZCZXOP67KLZQDYK7JPNZ4BDL","short_pith_number":"pith:G5ZCZXOP","canonical_record":{"source":{"id":"2406.16562","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T11:56:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"363e52e987d483f3a6e7954900a2a68b2a9fe7d2a613c0939428ed93ef6866c0","abstract_canon_sha256":"4c54012319242f2da73019a34106a7a23463a5319949999ea2f3fddb445043fa"},"schema_version":"1.0"},"canonical_sha256":"37722cddcff7d4bcc07857d2f6e7811acde3169e112dde77ffc47cc2ec1c914e","source":{"kind":"arxiv","id":"2406.16562","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16562","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16562v3","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16562","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_12","alias_value":"G5ZCZXOP67KL","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_16","alias_value":"G5ZCZXOP67KLZQDY","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_8","alias_value":"G5ZCZXOP","created_at":"2026-07-05T09:18:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:G5ZCZXOP67KLZQDYK7JPNZ4BDL","target":"record","payload":{"canonical_record":{"source":{"id":"2406.16562","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T11:56:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"363e52e987d483f3a6e7954900a2a68b2a9fe7d2a613c0939428ed93ef6866c0","abstract_canon_sha256":"4c54012319242f2da73019a34106a7a23463a5319949999ea2f3fddb445043fa"},"schema_version":"1.0"},"canonical_sha256":"37722cddcff7d4bcc07857d2f6e7811acde3169e112dde77ffc47cc2ec1c914e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:27.552139Z","signature_b64":"drR/JSIbzEBtL0DgDxj+oE1wGxWbn1Pkwn02RS+UnjgXGEpx363vkhhg02KshMLhp8Mgw0GLCnN4FNSQ/ii3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37722cddcff7d4bcc07857d2f6e7811acde3169e112dde77ffc47cc2ec1c914e","last_reissued_at":"2026-07-05T09:18:27.551643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:27.551643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.16562","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":"2026-07-05T09:18:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u0ganMnNAsCYFjo6ymvftvfwJbY5rBCemVf9VxTOTYnXkaPrejhA7oWxpnlNieKvybbG4m7gyLIWA56jVsXfAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:23:55.665587Z"},"content_sha256":"8c5fe1f04424734fd6089b7ffc71a01d5f34743772069715939334ffb30e20c8","schema_version":"1.0","event_id":"sha256:8c5fe1f04424734fd6089b7ffc71a01d5f34743772069715939334ffb30e20c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:G5ZCZXOP67KLZQDYK7JPNZ4BDL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Cheng Zhang, Hao Li, Luozheng Qin, Mengping Yang, Xiaomeng Yang, Zhiyu Tan","submitted_at":"2024-06-24T11:56:15Z","abstract_excerpt":"The recent advancements in text-to-image generative models have been remarkable. Yet, the field suffers from a lack of evaluation metrics that accurately reflect the performance of these models, particularly lacking fine-grained metrics that can guide the optimization of the models. In this paper, we propose EvalAlign, a metric characterized by its accuracy, stability, and fine granularity. Our approach leverages the capabilities of Multimodal Large Language Models (MLLMs) pre-trained on extensive data. We develop evaluation protocols that focus on two key dimensions: image faithfulness and te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16562","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/2406.16562/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":"2026-07-05T09:18:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KWh6pGlH+3bv7iQLWUFQsqUbIYrYYkrtbWrc26D7i9DsLqJ0ah4HNT5iscjlBVsFbzC/oL8p7bK0KeLsHQBDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:23:55.666103Z"},"content_sha256":"1ad0354b231df95f789aaac27db987ae30924b909f9be378976a2c4a26cba598","schema_version":"1.0","event_id":"sha256:1ad0354b231df95f789aaac27db987ae30924b909f9be378976a2c4a26cba598"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5ZCZXOP67KLZQDYK7JPNZ4BDL/bundle.json","state_url":"https://pith.science/pith/G5ZCZXOP67KLZQDYK7JPNZ4BDL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5ZCZXOP67KLZQDYK7JPNZ4BDL/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":"2026-08-05T02:23:55Z","links":{"resolver":"https://pith.science/pith/G5ZCZXOP67KLZQDYK7JPNZ4BDL","bundle":"https://pith.science/pith/G5ZCZXOP67KLZQDYK7JPNZ4BDL/bundle.json","state":"https://pith.science/pith/G5ZCZXOP67KLZQDYK7JPNZ4BDL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5ZCZXOP67KLZQDYK7JPNZ4BDL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G5ZCZXOP67KLZQDYK7JPNZ4BDL","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":"4c54012319242f2da73019a34106a7a23463a5319949999ea2f3fddb445043fa","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T11:56:15Z","title_canon_sha256":"363e52e987d483f3a6e7954900a2a68b2a9fe7d2a613c0939428ed93ef6866c0"},"schema_version":"1.0","source":{"id":"2406.16562","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16562","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16562v3","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16562","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_12","alias_value":"G5ZCZXOP67KL","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_16","alias_value":"G5ZCZXOP67KLZQDY","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_8","alias_value":"G5ZCZXOP","created_at":"2026-07-05T09:18:27Z"}],"graph_snapshots":[{"event_id":"sha256:1ad0354b231df95f789aaac27db987ae30924b909f9be378976a2c4a26cba598","target":"graph","created_at":"2026-07-05T09:18:27Z","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/2406.16562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent advancements in text-to-image generative models have been remarkable. Yet, the field suffers from a lack of evaluation metrics that accurately reflect the performance of these models, particularly lacking fine-grained metrics that can guide the optimization of the models. In this paper, we propose EvalAlign, a metric characterized by its accuracy, stability, and fine granularity. Our approach leverages the capabilities of Multimodal Large Language Models (MLLMs) pre-trained on extensive data. We develop evaluation protocols that focus on two key dimensions: image faithfulness and te","authors_text":"Cheng Zhang, Hao Li, Luozheng Qin, Mengping Yang, Xiaomeng Yang, Zhiyu Tan","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T11:56:15Z","title":"EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16562","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":"sha256:8c5fe1f04424734fd6089b7ffc71a01d5f34743772069715939334ffb30e20c8","target":"record","created_at":"2026-07-05T09:18:27Z","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":"4c54012319242f2da73019a34106a7a23463a5319949999ea2f3fddb445043fa","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T11:56:15Z","title_canon_sha256":"363e52e987d483f3a6e7954900a2a68b2a9fe7d2a613c0939428ed93ef6866c0"},"schema_version":"1.0","source":{"id":"2406.16562","kind":"arxiv","version":3}},"canonical_sha256":"37722cddcff7d4bcc07857d2f6e7811acde3169e112dde77ffc47cc2ec1c914e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37722cddcff7d4bcc07857d2f6e7811acde3169e112dde77ffc47cc2ec1c914e","first_computed_at":"2026-07-05T09:18:27.551643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:27.551643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"drR/JSIbzEBtL0DgDxj+oE1wGxWbn1Pkwn02RS+UnjgXGEpx363vkhhg02KshMLhp8Mgw0GLCnN4FNSQ/ii3Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:27.552139Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.16562","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c5fe1f04424734fd6089b7ffc71a01d5f34743772069715939334ffb30e20c8","sha256:1ad0354b231df95f789aaac27db987ae30924b909f9be378976a2c4a26cba598"],"state_sha256":"1fc336d0c2bcf6b5519028cf943373f5a9498574fcc305c10812a8cea4e337f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L6pFlIVTvoMRP0iq675iKUpu13RJAhcsFedWtvtJY++Do1bEvKFlRAwqb6As11IHMB3DrwltUIDGKo0yYjWXDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:23:55.673436Z","bundle_sha256":"3c22af2298a75cb26dccc3852a014160ece60abe6b9106b61d09d7ecb5efcbbf"}}