{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YC2R5E6BKCTN7GLLOC56HM2KWY","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":"8f7288f4fb74416e82126be28c17dfcd1ca27f938ee5739d958575dd690006d9","cross_cats_sorted":["cs.SD","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-20T03:34:53Z","title_canon_sha256":"d472ed5e75ca66dc85b9572980afd280ccfc955437c7744512b08ff50528ce3b"},"schema_version":"1.0","source":{"id":"2505.13880","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13880","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13880v3","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13880","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"YC2R5E6BKCTN","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"YC2R5E6BKCTN7GLL","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"YC2R5E6B","created_at":"2026-07-05T11:10:08Z"}],"graph_snapshots":[{"event_id":"sha256:9c411afdaa6993e7d5338bee0995948e9ba9d63b8ff3cea50ba50491503f9e5a","target":"graph","created_at":"2026-07-05T11:10:08Z","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/2505.13880/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The text generation paradigm for audio tasks has opened new possibilities for unified audio understanding. However, existing models face significant challenges in achieving a comprehensive understanding across diverse audio types, such as speech, general audio events, and music. Furthermore, their exclusive reliance on cross-entropy loss for alignment often falls short, as it treats all tokens equally and fails to account for redundant audio features, leading to weaker cross-modal alignment. To deal with the above challenges, this paper introduces U-SAM, an advanced audio language model that i","authors_text":"Lei Xie, Xianjun Xia, Xinfa Zhu, Ziqian Wang","cross_cats":["cs.SD","eess.SP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-20T03:34:53Z","title":"U-SAM: An audio language Model for Unified Speech, Audio, and Music Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13880","kind":"arxiv","version":3},"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:c7cc5446137fbf6a966ad5c669419b8740c7db03bfb35c3aa3f4f971cd6dda60","target":"record","created_at":"2026-07-05T11:10:08Z","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":"8f7288f4fb74416e82126be28c17dfcd1ca27f938ee5739d958575dd690006d9","cross_cats_sorted":["cs.SD","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-20T03:34:53Z","title_canon_sha256":"d472ed5e75ca66dc85b9572980afd280ccfc955437c7744512b08ff50528ce3b"},"schema_version":"1.0","source":{"id":"2505.13880","kind":"arxiv","version":3}},"canonical_sha256":"c0b51e93c150a6df996b70bbe3b34ab62c4b1e979ef28852043bf7d5d45dce97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0b51e93c150a6df996b70bbe3b34ab62c4b1e979ef28852043bf7d5d45dce97","first_computed_at":"2026-07-05T11:10:08.795051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:08.795051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ONNHy8CU7cGH8417P4X9UqAhcJFniVsmnMTPIQRnBOSHeAiHtvNhWXReu18KNuGZU4R2y9hO4dkMRrIm290RDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:08.795600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13880","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7cc5446137fbf6a966ad5c669419b8740c7db03bfb35c3aa3f4f971cd6dda60","sha256:9c411afdaa6993e7d5338bee0995948e9ba9d63b8ff3cea50ba50491503f9e5a"],"state_sha256":"d3a3f8bb7a71725ad641547412594fa616385e5ed1337758c28da75bbe80ca2c"}