{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QQJOIIPRZVHFWPYNHFFHHIED4Y","short_pith_number":"pith:QQJOIIPR","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"},"canonical_sha256":"8412e421f1cd4e5b3f0d394a73a083e61a2a4b1da832af815c7056e76efa33d4","source":{"kind":"arxiv","id":"2607.27109","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27109","created_at":"2026-07-30T01:23:36Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27109v1","created_at":"2026-07-30T01:23:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27109","created_at":"2026-07-30T01:23:36Z"},{"alias_kind":"pith_short_12","alias_value":"QQJOIIPRZVHF","created_at":"2026-07-30T01:23:36Z"},{"alias_kind":"pith_short_16","alias_value":"QQJOIIPRZVHFWPYN","created_at":"2026-07-30T01:23:36Z"},{"alias_kind":"pith_short_8","alias_value":"QQJOIIPR","created_at":"2026-07-30T01:23:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QQJOIIPRZVHFWPYNHFFHHIED4Y","target":"record","payload":{"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"},"canonical_sha256":"8412e421f1cd4e5b3f0d394a73a083e61a2a4b1da832af815c7056e76efa33d4","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"},"source_kind":"arxiv","source_id":"2607.27109","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:23:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nqRsQh78Lzbb8BWH+jP4ZLgCzKiPN6xCKyQV/Nfp/chSLf/8kPRYZcHv8Aa9ciNxKVr1oXXbXT/IDd+7s7+KAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T01:05:13.871087Z"},"content_sha256":"c237d48ed1436d4cb6a5de3bb29703d06f1ac297a6e0d51313038705a5234a6a","schema_version":"1.0","event_id":"sha256:c237d48ed1436d4cb6a5de3bb29703d06f1ac297a6e0d51313038705a5234a6a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QQJOIIPRZVHFWPYNHFFHHIED4Y","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:23:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5oaZxDRhfD9aW4eearea1y0svpTNixf8ZKpaOfEoXW7lHbMCG9CMa3E+u32ceb7kYgzOiEu4uWlYQvNuXe8NAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T01:05:13.871659Z"},"content_sha256":"5c5670ffaa78abdbc4e9b9757ee6b15ba5a4a275d8b762cf5dc8c5e44469a2a1","schema_version":"1.0","event_id":"sha256:5c5670ffaa78abdbc4e9b9757ee6b15ba5a4a275d8b762cf5dc8c5e44469a2a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y/bundle.json","state_url":"https://pith.science/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y/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":"2026-08-01T01:05:13Z","links":{"resolver":"https://pith.science/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y","bundle":"https://pith.science/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y/bundle.json","state":"https://pith.science/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QQJOIIPRZVHFWPYNHFFHHIED4Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QQJOIIPRZVHFWPYNHFFHHIED4Y","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":"663ea12a20a789d86e89a6bd5716ee8396b32393fb23ce042d2a1c948c72f950","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-29T16:38:08Z","title_canon_sha256":"0d24783f48bf36bee886dbd2cae2270b4241475d6680b36f65665d78c003ccdb"},"schema_version":"1.0","source":{"id":"2607.27109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27109","created_at":"2026-07-30T01:23:36Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27109v1","created_at":"2026-07-30T01:23:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27109","created_at":"2026-07-30T01:23:36Z"},{"alias_kind":"pith_short_12","alias_value":"QQJOIIPRZVHF","created_at":"2026-07-30T01:23:36Z"},{"alias_kind":"pith_short_16","alias_value":"QQJOIIPRZVHFWPYN","created_at":"2026-07-30T01:23:36Z"},{"alias_kind":"pith_short_8","alias_value":"QQJOIIPR","created_at":"2026-07-30T01:23:36Z"}],"graph_snapshots":[{"event_id":"sha256:5c5670ffaa78abdbc4e9b9757ee6b15ba5a4a275d8b762cf5dc8c5e44469a2a1","target":"graph","created_at":"2026-07-30T01:23:36Z","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/2607.27109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Junbo Li, Jun Fang, Lin Li, Qingyang Hong, Weijie Wu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-29T16:38:08Z","title":"MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27109","kind":"arxiv","version":1},"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:c237d48ed1436d4cb6a5de3bb29703d06f1ac297a6e0d51313038705a5234a6a","target":"record","created_at":"2026-07-30T01:23:36Z","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":"663ea12a20a789d86e89a6bd5716ee8396b32393fb23ce042d2a1c948c72f950","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-29T16:38:08Z","title_canon_sha256":"0d24783f48bf36bee886dbd2cae2270b4241475d6680b36f65665d78c003ccdb"},"schema_version":"1.0","source":{"id":"2607.27109","kind":"arxiv","version":1}},"canonical_sha256":"8412e421f1cd4e5b3f0d394a73a083e61a2a4b1da832af815c7056e76efa33d4","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8412e421f1cd4e5b3f0d394a73a083e61a2a4b1da832af815c7056e76efa33d4","first_computed_at":"2026-07-30T01:23:36.423090Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:23:36.423090Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c237d48ed1436d4cb6a5de3bb29703d06f1ac297a6e0d51313038705a5234a6a","sha256:5c5670ffaa78abdbc4e9b9757ee6b15ba5a4a275d8b762cf5dc8c5e44469a2a1"],"state_sha256":"e81df56abef2a5a10310f7616fa860081c174f64842864157843502bec9af104"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uSAtwR5DDPoXnZuDSuq14RZJ/l7WOzA7onqWZyi0hA6ZNhHj41V+b8g9y59LrXKjHE5mMzoT6AxuAAidyd7DAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T01:05:13.879610Z","bundle_sha256":"280a815212f81c863aaa25dc8577a048d11b29ba21f0eaa5c87460cd03c5ae5a"}}