{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TYJUF6V4BZ2DZQWRJJRIVXLSJ3","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":"d0e35993ea2111a764ed6ac085b7c0ca96910604f18e5fa5cc8982d576c13ddb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-12T16:09:49Z","title_canon_sha256":"ddd122d3f1ebf43acd5a9d70c8cb3993ef5f110cfefdfeaddd44672f3fbce15d"},"schema_version":"1.0","source":{"id":"2606.14591","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.14591","created_at":"2026-08-06T01:40:36Z"},{"alias_kind":"arxiv_version","alias_value":"2606.14591v2","created_at":"2026-08-06T01:40:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.14591","created_at":"2026-08-06T01:40:36Z"},{"alias_kind":"pith_short_12","alias_value":"TYJUF6V4BZ2D","created_at":"2026-08-06T01:40:36Z"},{"alias_kind":"pith_short_16","alias_value":"TYJUF6V4BZ2DZQWR","created_at":"2026-08-06T01:40:36Z"},{"alias_kind":"pith_short_8","alias_value":"TYJUF6V4","created_at":"2026-08-06T01:40:36Z"}],"graph_snapshots":[{"event_id":"sha256:20126ddb602ece6701bbc8321a68076041a3c115861af500bc39ab96c0bdf152","target":"graph","created_at":"2026-08-06T01:40:36Z","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/2606.14591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in pretrained large audio-language models (LALMs) have demonstrated strong capabilities across speech, sound, and music. To adapt these models to downstream tasks without the cost of pretraining from scratch, post-training has become a widely adopted paradigm. However, the effectiveness of post-training depends critically on the quality of the training corpus. We observe that existing post-training corpora, often constructed by aggregating public audio datasets, suffer from substantial acoustic redundancy, as many of these datasets are sourced from overlapping media platforms. ","authors_text":"Hengzhu Liu, Hui Geng, Jiaxin Chen, Kele Xu, Qisheng Xu, Tianjiao Wan, Yi Su, Zijian Gao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-12T16:09:49Z","title":"AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.14591","kind":"arxiv","version":2},"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:d8367a2d2bb33e089aabc875cda6ccb85caf65d991cd69d7b4d5f2d168ccebea","target":"record","created_at":"2026-08-06T01:40:36Z","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":"d0e35993ea2111a764ed6ac085b7c0ca96910604f18e5fa5cc8982d576c13ddb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-12T16:09:49Z","title_canon_sha256":"ddd122d3f1ebf43acd5a9d70c8cb3993ef5f110cfefdfeaddd44672f3fbce15d"},"schema_version":"1.0","source":{"id":"2606.14591","kind":"arxiv","version":2}},"canonical_sha256":"9e1342fabc0e743cc2d14a628add724ee7caeef8e82685a6a169ac010b1f9fdd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e1342fabc0e743cc2d14a628add724ee7caeef8e82685a6a169ac010b1f9fdd","first_computed_at":"2026-08-06T01:40:36.768780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:40:36.768780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ml1i+VGRoFGUgnmNcTr5MacP6XfPAun7uDiaSLVXFSRyGYvkLjQRgU3GBpHRlbMFM1fqmK39v2uGe9tfeExMBQ==","signature_status":"signed_v1","signed_at":"2026-08-06T01:40:36.770183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.14591","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8367a2d2bb33e089aabc875cda6ccb85caf65d991cd69d7b4d5f2d168ccebea","sha256:20126ddb602ece6701bbc8321a68076041a3c115861af500bc39ab96c0bdf152"],"state_sha256":"4381b63c5fffedd432d780c0e5dae75df4baff67b43e68570ea93d97cd1ebc52"}