{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EMKALQZMY4PA6ZGGMB76BLBCNC","short_pith_number":"pith:EMKALQZM","canonical_record":{"source":{"id":"2412.18150","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T04:08:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"87c5856c39d0fef95802bb04c647ba037115e91044845e00bff69903542188cc","abstract_canon_sha256":"08e9d4becfbb61ffe67fc3e5dccac53ea08b659bbf25428e1996de6fc31f3b15"},"schema_version":"1.0"},"canonical_sha256":"231405c32cc71e0f64c6607fe0ac2268a73aa436fbe7eecb6a1b78401ea07867","source":{"kind":"arxiv","id":"2412.18150","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18150","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18150v2","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18150","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"pith_short_12","alias_value":"EMKALQZMY4PA","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"pith_short_16","alias_value":"EMKALQZMY4PA6ZGG","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"pith_short_8","alias_value":"EMKALQZM","created_at":"2026-07-05T09:54:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EMKALQZMY4PA6ZGGMB76BLBCNC","target":"record","payload":{"canonical_record":{"source":{"id":"2412.18150","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T04:08:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"87c5856c39d0fef95802bb04c647ba037115e91044845e00bff69903542188cc","abstract_canon_sha256":"08e9d4becfbb61ffe67fc3e5dccac53ea08b659bbf25428e1996de6fc31f3b15"},"schema_version":"1.0"},"canonical_sha256":"231405c32cc71e0f64c6607fe0ac2268a73aa436fbe7eecb6a1b78401ea07867","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:07.753961Z","signature_b64":"gluv5HKk9waV9dtTqYPpTodMv52MnIo6WTNNoD062t8frqBVWIuSNcO/ArnQwD1+Q1jyoyJpm+tMWEBURNfODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"231405c32cc71e0f64c6607fe0ac2268a73aa436fbe7eecb6a1b78401ea07867","last_reissued_at":"2026-07-05T09:54:07.753497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:07.753497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.18150","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:54:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sovaPAUIOo3sYSxH1NkLGh5ft3TO80EvMbLOm8r3HTeUGVErgkHkXdrfN+u+3UyhMXxg5yxeYygjW2pBXpJ4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T11:05:40.615187Z"},"content_sha256":"af2c490141dd326315217bc22239912fa99fed5c6188d8683bfbd0a502d992a0","schema_version":"1.0","event_id":"sha256:af2c490141dd326315217bc22239912fa99fed5c6188d8683bfbd0a502d992a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EMKALQZMY4PA6ZGGMB76BLBCNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chongyi Li, Chunle Guo, Haotian Fan, Jiachen Fu, Jingwei Sun, Junhui Cui, Liang Li, Shuhao Han, Tao Li, Yang Tai, Yunqiu Wang","submitted_at":"2024-12-24T04:08:25Z","abstract_excerpt":"Recently, Text-to-Image (T2I) generation models have achieved significant advancements. Correspondingly, many automated metrics have emerged to evaluate the image-text alignment capabilities of generative models. However, the performance comparison among these automated metrics is limited by existing small datasets. Additionally, these datasets lack the capacity to assess the performance of automated metrics at a fine-grained level. In this study, we contribute an EvalMuse-40K benchmark, gathering 40K image-text pairs with fine-grained human annotations for image-text alignment-related tasks. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18150","kind":"arxiv","version":2},"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/2412.18150/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":"2026-07-05T09:54:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ul48PLFCHeUSdCTVzSP6j/1zHQu4xtczA1PumY0FeolCKD64oRLH5hL5+MjOl1JQPaZ1o7fJsmKC6A1kj13cCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T11:05:40.615579Z"},"content_sha256":"729ff1dd60c65d3f5f74a0c5ecf29c3d0123ac4b92969bd193a7f77ae9e62aaf","schema_version":"1.0","event_id":"sha256:729ff1dd60c65d3f5f74a0c5ecf29c3d0123ac4b92969bd193a7f77ae9e62aaf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EMKALQZMY4PA6ZGGMB76BLBCNC/bundle.json","state_url":"https://pith.science/pith/EMKALQZMY4PA6ZGGMB76BLBCNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EMKALQZMY4PA6ZGGMB76BLBCNC/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":"2026-07-13T11:05:40Z","links":{"resolver":"https://pith.science/pith/EMKALQZMY4PA6ZGGMB76BLBCNC","bundle":"https://pith.science/pith/EMKALQZMY4PA6ZGGMB76BLBCNC/bundle.json","state":"https://pith.science/pith/EMKALQZMY4PA6ZGGMB76BLBCNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EMKALQZMY4PA6ZGGMB76BLBCNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EMKALQZMY4PA6ZGGMB76BLBCNC","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":"08e9d4becfbb61ffe67fc3e5dccac53ea08b659bbf25428e1996de6fc31f3b15","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T04:08:25Z","title_canon_sha256":"87c5856c39d0fef95802bb04c647ba037115e91044845e00bff69903542188cc"},"schema_version":"1.0","source":{"id":"2412.18150","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18150","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18150v2","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18150","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"pith_short_12","alias_value":"EMKALQZMY4PA","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"pith_short_16","alias_value":"EMKALQZMY4PA6ZGG","created_at":"2026-07-05T09:54:07Z"},{"alias_kind":"pith_short_8","alias_value":"EMKALQZM","created_at":"2026-07-05T09:54:07Z"}],"graph_snapshots":[{"event_id":"sha256:729ff1dd60c65d3f5f74a0c5ecf29c3d0123ac4b92969bd193a7f77ae9e62aaf","target":"graph","created_at":"2026-07-05T09:54:07Z","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/2412.18150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, Text-to-Image (T2I) generation models have achieved significant advancements. Correspondingly, many automated metrics have emerged to evaluate the image-text alignment capabilities of generative models. However, the performance comparison among these automated metrics is limited by existing small datasets. Additionally, these datasets lack the capacity to assess the performance of automated metrics at a fine-grained level. In this study, we contribute an EvalMuse-40K benchmark, gathering 40K image-text pairs with fine-grained human annotations for image-text alignment-related tasks. ","authors_text":"Chongyi Li, Chunle Guo, Haotian Fan, Jiachen Fu, Jingwei Sun, Junhui Cui, Liang Li, Shuhao Han, Tao Li, Yang Tai, Yunqiu Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T04:08:25Z","title":"EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18150","kind":"arxiv","version":2},"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:af2c490141dd326315217bc22239912fa99fed5c6188d8683bfbd0a502d992a0","target":"record","created_at":"2026-07-05T09:54:07Z","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":"08e9d4becfbb61ffe67fc3e5dccac53ea08b659bbf25428e1996de6fc31f3b15","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T04:08:25Z","title_canon_sha256":"87c5856c39d0fef95802bb04c647ba037115e91044845e00bff69903542188cc"},"schema_version":"1.0","source":{"id":"2412.18150","kind":"arxiv","version":2}},"canonical_sha256":"231405c32cc71e0f64c6607fe0ac2268a73aa436fbe7eecb6a1b78401ea07867","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"231405c32cc71e0f64c6607fe0ac2268a73aa436fbe7eecb6a1b78401ea07867","first_computed_at":"2026-07-05T09:54:07.753497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:07.753497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gluv5HKk9waV9dtTqYPpTodMv52MnIo6WTNNoD062t8frqBVWIuSNcO/ArnQwD1+Q1jyoyJpm+tMWEBURNfODA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:07.753961Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18150","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af2c490141dd326315217bc22239912fa99fed5c6188d8683bfbd0a502d992a0","sha256:729ff1dd60c65d3f5f74a0c5ecf29c3d0123ac4b92969bd193a7f77ae9e62aaf"],"state_sha256":"708076232b25c43fe44b94727686ead75fadc4b6381b28d24fe0e491f6b93c7b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x5B2Vv0ad838qfScUrUSUjnSGuzBJaKC8DQ2gQZ7Od+xWC9eHCtT2CwmT6VH3sL/7op3JgkxpHJEp0JtxOpECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T11:05:40.617654Z","bundle_sha256":"82e7a3252b660e8fc8d9b32d700bab9f4447e7d2866dd04487e018357f218df0"}}