{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QQJOIIPRZVHFWPYNHFFHHIED4Y","short_pith_number":"pith:QQJOIIPR","schema_version":"1.0","canonical_sha256":"8412e421f1cd4e5b3f0d394a73a083e61a2a4b1da832af815c7056e76efa33d4","source":{"kind":"arxiv","id":"2607.27109","version":1},"attestation_state":"computed","paper":{"title":"MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Junbo Li, Jun Fang, Lin Li, Qingyang Hong, Weijie Wu","submitted_at":"2026-07-29T16:38:08Z","abstract_excerpt":"With the development of audio large language models (AudioLLMs), audio captioning needs to move from brief descriptions toward open-ended and fine-grained free-form descriptions. Existing evaluations often focus on generation quality or task performance, making it difficult to diagnose information coverage and description reliability. We propose MMAC, a \\textbf{M}assive \\textbf{M}ulti-dimensional benchmark for \\textbf{A}udio \\textbf{C}aptioning. MMAC contains 5,638 audio clips from more than 20 data sources, covering 6 capability categories and 15 evaluation dimensions. Given a model-generated"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.27109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-29T16:38:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d24783f48bf36bee886dbd2cae2270b4241475d6680b36f65665d78c003ccdb","abstract_canon_sha256":"663ea12a20a789d86e89a6bd5716ee8396b32393fb23ce042d2a1c948c72f950"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8412e421f1cd4e5b3f0d394a73a083e61a2a4b1da832af815c7056e76efa33d4","last_reissued_at":"2026-07-30T01:23:36.423090Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:23:36.423090Z"},"graph_snapshot":{"paper":{"title":"MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Junbo Li, Jun Fang, Lin Li, Qingyang Hong, Weijie Wu","submitted_at":"2026-07-29T16:38:08Z","abstract_excerpt":"With the development of audio large language models (AudioLLMs), audio captioning needs to move from brief descriptions toward open-ended and fine-grained free-form descriptions. Existing evaluations often focus on generation quality or task performance, making it difficult to diagnose information coverage and description reliability. We propose MMAC, a \\textbf{M}assive \\textbf{M}ulti-dimensional benchmark for \\textbf{A}udio \\textbf{C}aptioning. MMAC contains 5,638 audio clips from more than 20 data sources, covering 6 capability categories and 15 evaluation dimensions. Given a model-generated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27109","kind":"arxiv","version":1},"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/2607.27109/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.27109","created_at":"2026-07-30T01:23:36.428088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27109v1","created_at":"2026-07-30T01:23:36.428088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27109","created_at":"2026-07-30T01:23:36.428088+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQJOIIPRZVHF","created_at":"2026-07-30T01:23:36.428088+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQJOIIPRZVHFWPYN","created_at":"2026-07-30T01:23:36.428088+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQJOIIPR","created_at":"2026-07-30T01:23:36.428088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y","json":"https://pith.science/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y.json","graph_json":"https://pith.science/api/pith-number/QQJOIIPRZVHFWPYNHFFHHIED4Y/graph.json","events_json":"https://pith.science/api/pith-number/QQJOIIPRZVHFWPYNHFFHHIED4Y/events.json","paper":"https://pith.science/paper/QQJOIIPR"},"agent_actions":{"view_html":"https://pith.science/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y","download_json":"https://pith.science/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y.json","view_paper":"https://pith.science/paper/QQJOIIPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27109&json=true","fetch_graph":"https://pith.science/api/pith-number/QQJOIIPRZVHFWPYNHFFHHIED4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/QQJOIIPRZVHFWPYNHFFHHIED4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y/action/storage_attestation","attest_author":"https://pith.science/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y/action/author_attestation","sign_citation":"https://pith.science/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y/action/citation_signature","submit_replication":"https://pith.science/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y/action/replication_record"}},"created_at":"2026-07-30T01:23:36.428088+00:00","updated_at":"2026-07-30T01:23:36.428088+00:00"}