{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QE3OTD3Q6NHBRLLO7DKAPDI2UL","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":"f57258734d2e043febf5fae4a715ccff669af5ad26659b254d812781cbc87c53","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-01T07:19:22Z","title_canon_sha256":"2b277c91d006c6463dd388fa70d783519595d27a0a1551a9e3923a3416285e43"},"schema_version":"1.0","source":{"id":"2606.01802","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01802","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01802v1","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01802","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"QE3OTD3Q6NHB","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"QE3OTD3Q6NHBRLLO","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"QE3OTD3Q","created_at":"2026-06-02T02:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:2e2722f50c9477591745e2ff800939c7a1e55754136f5166185701d80476080e","target":"graph","created_at":"2026-06-02T02:04:57Z","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/2606.01802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio captioning, time-aware question answering, timestamped transcription, and audio-grounded reasoning. MOSS-Audio couples a dedicated audio encoder with a modality adapter and a large language model: the encoder produces 12.5 Hz temporal representations, the adapter projects them into the decoder space, and the decoder generates autoregressive text outputs. Two design choices are central to the system: \\textbf{DeepStack cross-layer feature injection}, which exposes the decoder t","authors_text":"Chenghao Liu, Chen Yang, Chufan Yu, Hanfu Chen, Jie Zhu, Jingqi Chen, Jun Zhan, Kang Yu, Ke Chen, Kexin Huang, Mingshu Chen, Qinyuan Cheng, Ruixiao Li, Shimin Li, Songlin Wang, Wenxuan Wang, Xipeng Qiu, Yang Gao, Yang Wang, Yaozhou Jiang, Yi Jiang, Yiyang Zhang, Zhaoye Fei, Zhengyuan Lin, Ziqi Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-01T07:19:22Z","title":"MOSS-Audio Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01802","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":"sha256:8f0c9389189a9270fb9e775a99259dc10e74087eb1e6b3c39ce1851e7ccdae71","target":"record","created_at":"2026-06-02T02:04:57Z","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":"f57258734d2e043febf5fae4a715ccff669af5ad26659b254d812781cbc87c53","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-01T07:19:22Z","title_canon_sha256":"2b277c91d006c6463dd388fa70d783519595d27a0a1551a9e3923a3416285e43"},"schema_version":"1.0","source":{"id":"2606.01802","kind":"arxiv","version":1}},"canonical_sha256":"8136e98f70f34e18ad6ef8d4078d1aa2eb7b2bf18448d50e449d5ade532dfcf7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8136e98f70f34e18ad6ef8d4078d1aa2eb7b2bf18448d50e449d5ade532dfcf7","first_computed_at":"2026-06-02T02:04:57.306706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:57.306706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZpExAs54veNEoCoCdjMQLZvjZUAdhmP05E1XOV46rzh8WB1Juk/1j5vt+0ZcRMnsRFPlySdtOQ3V1lFSCdhEDQ==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:57.307130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01802","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f0c9389189a9270fb9e775a99259dc10e74087eb1e6b3c39ce1851e7ccdae71","sha256:2e2722f50c9477591745e2ff800939c7a1e55754136f5166185701d80476080e"],"state_sha256":"5ceddf39ad76253262c5acfc1fe9e028968b8367da1f53c9fd712647ab4264ec"}