{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5I7AW4EXQZNFCDJ7JTIO7VA6RK","short_pith_number":"pith:5I7AW4EX","canonical_record":{"source":{"id":"2506.05142","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T15:24:33Z","cross_cats_sorted":[],"title_canon_sha256":"54946b7194a63bc3d6780e3183ddc14975da3f2bcb71a79276bb42c6bc4664df","abstract_canon_sha256":"cdc45a313b9bb51df037876ef85f24eaed9056125ebf702c02aad4e0dc46fb90"},"schema_version":"1.0"},"canonical_sha256":"ea3e0b7097865a510d3f4cd0efd41e8aaa7ecf164079bce0db5871497b60afc9","source":{"kind":"arxiv","id":"2506.05142","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05142","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05142v2","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05142","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"pith_short_12","alias_value":"5I7AW4EXQZNF","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"pith_short_16","alias_value":"5I7AW4EXQZNFCDJ7","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"pith_short_8","alias_value":"5I7AW4EX","created_at":"2026-07-05T11:18:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5I7AW4EXQZNFCDJ7JTIO7VA6RK","target":"record","payload":{"canonical_record":{"source":{"id":"2506.05142","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T15:24:33Z","cross_cats_sorted":[],"title_canon_sha256":"54946b7194a63bc3d6780e3183ddc14975da3f2bcb71a79276bb42c6bc4664df","abstract_canon_sha256":"cdc45a313b9bb51df037876ef85f24eaed9056125ebf702c02aad4e0dc46fb90"},"schema_version":"1.0"},"canonical_sha256":"ea3e0b7097865a510d3f4cd0efd41e8aaa7ecf164079bce0db5871497b60afc9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:23.264991Z","signature_b64":"elqHeFNLfd2OVEo54XuMD4R9ycoMsDbsstM8zuIFY1dYIq0EL0KFhqHMhcpruYmg6ipAtx3yXjBuYwWqrCYpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea3e0b7097865a510d3f4cd0efd41e8aaa7ecf164079bce0db5871497b60afc9","last_reissued_at":"2026-07-05T11:18:23.264513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:23.264513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.05142","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":"2026-07-05T11:18:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GXOWadxKTqOEaFe/vdabqnpSZrsdRrfnWUES1MwGzHaZHsnrS7Oj8sIwpKbnGYUBMHyphagGI0v3dkryVpeMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:58:39.998010Z"},"content_sha256":"2a2ba1d6071806b591cd05d9991071e5cec7f7775a899d1571237f2d2eecaf80","schema_version":"1.0","event_id":"sha256:2a2ba1d6071806b591cd05d9991071e5cec7f7775a899d1571237f2d2eecaf80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5I7AW4EXQZNFCDJ7JTIO7VA6RK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Large Language Models Judge Error Severity Like Humans?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Diege Sun, Guanyi Chen, Tingting He, Xiaorong Cheng, Zhao Fan","submitted_at":"2025-06-05T15:24:33Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used as automated evaluators in natural language generation, yet it remains unclear whether they can accurately replicate human judgments of error severity. In this study, we systematically compare human and LLM assessments of image descriptions containing controlled semantic errors. We extend the experimental framework of van Miltenburg et al. (2020) to both unimodal (text-only) and multimodal (text + image) settings, evaluating four error types: age, gender, clothing type, and clothing colour. Our findings reveal that humans assign varying levels"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05142","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/2506.05142/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":"2026-07-05T11:18:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"446mQgYEe5DlePnus3NZeR/FvOjAlYu7m6487ebPl9s9YKuVc/A7F7iwHCxIuj8L7CnRiXUEkcNSdijlqjVVAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:58:39.998512Z"},"content_sha256":"c4279c3bdb728fc587364acc8013ebfda85f1077d675a578fee11ceae3250641","schema_version":"1.0","event_id":"sha256:c4279c3bdb728fc587364acc8013ebfda85f1077d675a578fee11ceae3250641"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5I7AW4EXQZNFCDJ7JTIO7VA6RK/bundle.json","state_url":"https://pith.science/pith/5I7AW4EXQZNFCDJ7JTIO7VA6RK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5I7AW4EXQZNFCDJ7JTIO7VA6RK/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":"2026-08-08T12:58:40Z","links":{"resolver":"https://pith.science/pith/5I7AW4EXQZNFCDJ7JTIO7VA6RK","bundle":"https://pith.science/pith/5I7AW4EXQZNFCDJ7JTIO7VA6RK/bundle.json","state":"https://pith.science/pith/5I7AW4EXQZNFCDJ7JTIO7VA6RK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5I7AW4EXQZNFCDJ7JTIO7VA6RK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5I7AW4EXQZNFCDJ7JTIO7VA6RK","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":"cdc45a313b9bb51df037876ef85f24eaed9056125ebf702c02aad4e0dc46fb90","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T15:24:33Z","title_canon_sha256":"54946b7194a63bc3d6780e3183ddc14975da3f2bcb71a79276bb42c6bc4664df"},"schema_version":"1.0","source":{"id":"2506.05142","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05142","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05142v2","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05142","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"pith_short_12","alias_value":"5I7AW4EXQZNF","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"pith_short_16","alias_value":"5I7AW4EXQZNFCDJ7","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"pith_short_8","alias_value":"5I7AW4EX","created_at":"2026-07-05T11:18:23Z"}],"graph_snapshots":[{"event_id":"sha256:c4279c3bdb728fc587364acc8013ebfda85f1077d675a578fee11ceae3250641","target":"graph","created_at":"2026-07-05T11:18:23Z","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/2506.05142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are increasingly used as automated evaluators in natural language generation, yet it remains unclear whether they can accurately replicate human judgments of error severity. In this study, we systematically compare human and LLM assessments of image descriptions containing controlled semantic errors. We extend the experimental framework of van Miltenburg et al. (2020) to both unimodal (text-only) and multimodal (text + image) settings, evaluating four error types: age, gender, clothing type, and clothing colour. Our findings reveal that humans assign varying levels","authors_text":"Diege Sun, Guanyi Chen, Tingting He, Xiaorong Cheng, Zhao Fan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T15:24:33Z","title":"Do Large Language Models Judge Error Severity Like Humans?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05142","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":"sha256:2a2ba1d6071806b591cd05d9991071e5cec7f7775a899d1571237f2d2eecaf80","target":"record","created_at":"2026-07-05T11:18:23Z","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":"cdc45a313b9bb51df037876ef85f24eaed9056125ebf702c02aad4e0dc46fb90","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T15:24:33Z","title_canon_sha256":"54946b7194a63bc3d6780e3183ddc14975da3f2bcb71a79276bb42c6bc4664df"},"schema_version":"1.0","source":{"id":"2506.05142","kind":"arxiv","version":2}},"canonical_sha256":"ea3e0b7097865a510d3f4cd0efd41e8aaa7ecf164079bce0db5871497b60afc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea3e0b7097865a510d3f4cd0efd41e8aaa7ecf164079bce0db5871497b60afc9","first_computed_at":"2026-07-05T11:18:23.264513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:23.264513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"elqHeFNLfd2OVEo54XuMD4R9ycoMsDbsstM8zuIFY1dYIq0EL0KFhqHMhcpruYmg6ipAtx3yXjBuYwWqrCYpAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:23.264991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05142","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a2ba1d6071806b591cd05d9991071e5cec7f7775a899d1571237f2d2eecaf80","sha256:c4279c3bdb728fc587364acc8013ebfda85f1077d675a578fee11ceae3250641"],"state_sha256":"e71a8406f42b3818bbcc042fdca048e9a35c9cfaa6d085a443ba8c00420d113e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uRekPhYgoHwaaVMHtt1D3+tTiCE9XRxqY0VRX4Nl0C/GN0H4ATZFVV6U29UdoZSuz8A29EiMR1asT5N7ORsCBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:58:40.003581Z","bundle_sha256":"d47e217600a14d148101429c30bc304b140bf0faf8d4b89edd5452af8b5c5acd"}}