{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TIBXHO4YEJVE7TGJZS5PCYQJBH","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":"62dcf437034dd2a9ea25c271cb7d29ddbaaab2352dc0955b128f1882b2c292c4","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-29T07:40:39Z","title_canon_sha256":"3ee3cf77c05e114de5006aba03b6b7ce0339077183f78aafd939dd539e4fa923"},"schema_version":"1.0","source":{"id":"2508.21376","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21376","created_at":"2026-07-05T12:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21376v2","created_at":"2026-07-05T12:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21376","created_at":"2026-07-05T12:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"TIBXHO4YEJVE","created_at":"2026-07-05T12:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"TIBXHO4YEJVE7TGJ","created_at":"2026-07-05T12:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"TIBXHO4Y","created_at":"2026-07-05T12:03:52Z"}],"graph_snapshots":[{"event_id":"sha256:b513e0f73cf3f9e817683dac0ff7b9effa63e33fc87828552854927729f8a1c1","target":"graph","created_at":"2026-07-05T12:03:52Z","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/2508.21376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluations of audio-language models (ALMs) -- multimodal models that take interleaved audio and text as input and output text -- are hindered by the lack of standardized benchmarks; most benchmarks measure only one or two capabilities and omit evaluative aspects such as fairness or safety. Furthermore, comparison across models is difficult as separate evaluations test a limited number of models and use different prompting methods and inference parameters. To address these shortfalls, we introduce AHELM, a benchmark that aggregates various datasets -- including 2 new synthetic audio-text datas","authors_text":"Chi Heem Wong, Cihang Xie, Haoqin Tu, Percy Liang, Siwei Yang, Tony Lee, Yifan Mai, Yuyin Zhou, Zijun Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-29T07:40:39Z","title":"AHELM: A Holistic Evaluation of Audio-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21376","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":"sha256:8bbefcb4d11db412481a61060b29630a7cb8cb63f0f7d90aa9531236587aaa03","target":"record","created_at":"2026-07-05T12:03:52Z","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":"62dcf437034dd2a9ea25c271cb7d29ddbaaab2352dc0955b128f1882b2c292c4","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-29T07:40:39Z","title_canon_sha256":"3ee3cf77c05e114de5006aba03b6b7ce0339077183f78aafd939dd539e4fa923"},"schema_version":"1.0","source":{"id":"2508.21376","kind":"arxiv","version":2}},"canonical_sha256":"9a0373bb98226a4fccc9ccbaf1620909d32207b66e92bdb05835dad6ed118496","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a0373bb98226a4fccc9ccbaf1620909d32207b66e92bdb05835dad6ed118496","first_computed_at":"2026-07-05T12:03:52.204508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:52.204508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Meiu7QptaqN2YuY9joHjKt1QENsg/V8r813LKHSdIDqlpmVgEKip9kZNVYhQ7+FkjaAGFQn4STgtb2D98zT8Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:52.205132Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21376","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bbefcb4d11db412481a61060b29630a7cb8cb63f0f7d90aa9531236587aaa03","sha256:b513e0f73cf3f9e817683dac0ff7b9effa63e33fc87828552854927729f8a1c1"],"state_sha256":"9305db9451b38a375d35398195f4bb32812bcc893fc54848f191cd4fc71e48d5"}