{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QXDAPKGI2YVAFGUXPFKZT5OBSM","short_pith_number":"pith:QXDAPKGI","canonical_record":{"source":{"id":"2507.20169","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-27T08:16:23Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"18097fa128e49c111891afbeb1ff03630a775e06a8c4d273fd1028273e73b9e2","abstract_canon_sha256":"3e8db650fd96a5938d4490d52d5190e781e33ced2c24f7b5aeadee139fe2c86c"},"schema_version":"1.0"},"canonical_sha256":"85c607a8c8d62a029a97795599f5c1932ebe6f844d3dcd5bb9ef254268744779","source":{"kind":"arxiv","id":"2507.20169","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20169","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20169v1","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20169","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"pith_short_12","alias_value":"QXDAPKGI2YVA","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"pith_short_16","alias_value":"QXDAPKGI2YVAFGUX","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"pith_short_8","alias_value":"QXDAPKGI","created_at":"2026-07-05T11:44:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QXDAPKGI2YVAFGUXPFKZT5OBSM","target":"record","payload":{"canonical_record":{"source":{"id":"2507.20169","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-27T08:16:23Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"18097fa128e49c111891afbeb1ff03630a775e06a8c4d273fd1028273e73b9e2","abstract_canon_sha256":"3e8db650fd96a5938d4490d52d5190e781e33ced2c24f7b5aeadee139fe2c86c"},"schema_version":"1.0"},"canonical_sha256":"85c607a8c8d62a029a97795599f5c1932ebe6f844d3dcd5bb9ef254268744779","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:14.578485Z","signature_b64":"QajPA5n5sS+6eOJE3SUBGhy1UbzYBzB13gZwf7TyVsIiiLHRH3liHin2mp0SrUQAp9dxhl0vssQih5ypfCxtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85c607a8c8d62a029a97795599f5c1932ebe6f844d3dcd5bb9ef254268744779","last_reissued_at":"2026-07-05T11:44:14.578056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:14.578056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.20169","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":"2026-07-05T11:44:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"shDrV0nD2tPEGZMQKVR3wNGb5/HPFItWaPTm5+C+DEfFI82VFl4YjJjYjw+zek889FEvkZ7lgIbQbmb8b8AcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:56:08.639944Z"},"content_sha256":"20d8c64f7197f60b8729130cea14bbdd572c873b94a86e3201d9b8efc7cf6849","schema_version":"1.0","event_id":"sha256:20d8c64f7197f60b8729130cea14bbdd572c873b94a86e3201d9b8efc7cf6849"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QXDAPKGI2YVAFGUXPFKZT5OBSM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Improvement for Audio Large Language Model using Unlabeled Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Shaowen Wang, Xinyuan Chen, Yao Xu","submitted_at":"2025-07-27T08:16:23Z","abstract_excerpt":"Recent audio LLMs have emerged rapidly, demonstrating strong generalization across various speech tasks. However, given the inherent complexity of speech signals, these models inevitably suffer from performance degradation in specific target domains. To address this, we focus on enhancing audio LLMs in target domains without any labeled data. We propose a self-improvement method called SI-SDA, leveraging the information embedded in large-model decoding to evaluate the quality of generated pseudo labels and then perform domain adaptation based on reinforcement learning optimization. Experimenta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20169","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/2507.20169/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":"2026-07-05T11:44:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OIctsOyrhskxtk+wDQpzfJNQReI30SSXr6PwkJRVEQV8yKsErrImGqa37lnKbFQJK7Yq02adBoM9udW3Bu11BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:56:08.640467Z"},"content_sha256":"45687c288efc9d3c74b804e4bba82a212a132c79b56f5f3888ee2f03c26fd3f2","schema_version":"1.0","event_id":"sha256:45687c288efc9d3c74b804e4bba82a212a132c79b56f5f3888ee2f03c26fd3f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXDAPKGI2YVAFGUXPFKZT5OBSM/bundle.json","state_url":"https://pith.science/pith/QXDAPKGI2YVAFGUXPFKZT5OBSM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXDAPKGI2YVAFGUXPFKZT5OBSM/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":"2026-08-16T23:56:08Z","links":{"resolver":"https://pith.science/pith/QXDAPKGI2YVAFGUXPFKZT5OBSM","bundle":"https://pith.science/pith/QXDAPKGI2YVAFGUXPFKZT5OBSM/bundle.json","state":"https://pith.science/pith/QXDAPKGI2YVAFGUXPFKZT5OBSM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXDAPKGI2YVAFGUXPFKZT5OBSM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QXDAPKGI2YVAFGUXPFKZT5OBSM","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":"3e8db650fd96a5938d4490d52d5190e781e33ced2c24f7b5aeadee139fe2c86c","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-27T08:16:23Z","title_canon_sha256":"18097fa128e49c111891afbeb1ff03630a775e06a8c4d273fd1028273e73b9e2"},"schema_version":"1.0","source":{"id":"2507.20169","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20169","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20169v1","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20169","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"pith_short_12","alias_value":"QXDAPKGI2YVA","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"pith_short_16","alias_value":"QXDAPKGI2YVAFGUX","created_at":"2026-07-05T11:44:14Z"},{"alias_kind":"pith_short_8","alias_value":"QXDAPKGI","created_at":"2026-07-05T11:44:14Z"}],"graph_snapshots":[{"event_id":"sha256:45687c288efc9d3c74b804e4bba82a212a132c79b56f5f3888ee2f03c26fd3f2","target":"graph","created_at":"2026-07-05T11:44:14Z","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/2507.20169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent audio LLMs have emerged rapidly, demonstrating strong generalization across various speech tasks. However, given the inherent complexity of speech signals, these models inevitably suffer from performance degradation in specific target domains. To address this, we focus on enhancing audio LLMs in target domains without any labeled data. We propose a self-improvement method called SI-SDA, leveraging the information embedded in large-model decoding to evaluate the quality of generated pseudo labels and then perform domain adaptation based on reinforcement learning optimization. Experimenta","authors_text":"Shaowen Wang, Xinyuan Chen, Yao Xu","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-27T08:16:23Z","title":"Self-Improvement for Audio Large Language Model using Unlabeled Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20169","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":"sha256:20d8c64f7197f60b8729130cea14bbdd572c873b94a86e3201d9b8efc7cf6849","target":"record","created_at":"2026-07-05T11:44:14Z","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":"3e8db650fd96a5938d4490d52d5190e781e33ced2c24f7b5aeadee139fe2c86c","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-27T08:16:23Z","title_canon_sha256":"18097fa128e49c111891afbeb1ff03630a775e06a8c4d273fd1028273e73b9e2"},"schema_version":"1.0","source":{"id":"2507.20169","kind":"arxiv","version":1}},"canonical_sha256":"85c607a8c8d62a029a97795599f5c1932ebe6f844d3dcd5bb9ef254268744779","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85c607a8c8d62a029a97795599f5c1932ebe6f844d3dcd5bb9ef254268744779","first_computed_at":"2026-07-05T11:44:14.578056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:14.578056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QajPA5n5sS+6eOJE3SUBGhy1UbzYBzB13gZwf7TyVsIiiLHRH3liHin2mp0SrUQAp9dxhl0vssQih5ypfCxtBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:14.578485Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.20169","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20d8c64f7197f60b8729130cea14bbdd572c873b94a86e3201d9b8efc7cf6849","sha256:45687c288efc9d3c74b804e4bba82a212a132c79b56f5f3888ee2f03c26fd3f2"],"state_sha256":"cfc7b4e4606378073c8a4c0b25f8356a49146394dae2658d19c3411096430773"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5M7EwAPZzLve7z599giYijoo3EQXuoxjo7PAi09FhdoninqMffEL+2Ta0lKj01GhN1x+QpSxNEOh8zm8iiPADw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T23:56:08.644369Z","bundle_sha256":"7a085938a08dd5036d429e1cde50f064527855a04d23895c920002d1aabe5ab2"}}