{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TYJUF6V4BZ2DZQWRJJRIVXLSJ3","short_pith_number":"pith:TYJUF6V4","canonical_record":{"source":{"id":"2606.14591","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-12T16:09:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ddd122d3f1ebf43acd5a9d70c8cb3993ef5f110cfefdfeaddd44672f3fbce15d","abstract_canon_sha256":"d0e35993ea2111a764ed6ac085b7c0ca96910604f18e5fa5cc8982d576c13ddb"},"schema_version":"1.0"},"canonical_sha256":"9e1342fabc0e743cc2d14a628add724ee7caeef8e82685a6a169ac010b1f9fdd","source":{"kind":"arxiv","id":"2606.14591","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TYJUF6V4BZ2DZQWRJJRIVXLSJ3","target":"record","payload":{"canonical_record":{"source":{"id":"2606.14591","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-12T16:09:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ddd122d3f1ebf43acd5a9d70c8cb3993ef5f110cfefdfeaddd44672f3fbce15d","abstract_canon_sha256":"d0e35993ea2111a764ed6ac085b7c0ca96910604f18e5fa5cc8982d576c13ddb"},"schema_version":"1.0"},"canonical_sha256":"9e1342fabc0e743cc2d14a628add724ee7caeef8e82685a6a169ac010b1f9fdd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:40:36.770183Z","signature_b64":"Ml1i+VGRoFGUgnmNcTr5MacP6XfPAun7uDiaSLVXFSRyGYvkLjQRgU3GBpHRlbMFM1fqmK39v2uGe9tfeExMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e1342fabc0e743cc2d14a628add724ee7caeef8e82685a6a169ac010b1f9fdd","last_reissued_at":"2026-08-06T01:40:36.768780Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:40:36.768780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.14591","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-06T01:40:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DCVFAGPVmb7av9BuBZ9regm+WWF/9xKujhF67nO6+anojA0SsNZtQZc+/0SFcTRm++RSNx8c21VLq3lRRGQrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:55:42.236911Z"},"content_sha256":"d8367a2d2bb33e089aabc875cda6ccb85caf65d991cd69d7b4d5f2d168ccebea","schema_version":"1.0","event_id":"sha256:d8367a2d2bb33e089aabc875cda6ccb85caf65d991cd69d7b4d5f2d168ccebea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TYJUF6V4BZ2DZQWRJJRIVXLSJ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Hengzhu Liu, Hui Geng, Jiaxin Chen, Kele Xu, Qisheng Xu, Tianjiao Wan, Yi Su, Zijian Gao","submitted_at":"2026-06-12T16:09:49Z","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. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.14591","kind":"arxiv","version":2},"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/2606.14591/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":"2026-08-06T01:40:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AuXgM03Oc7J048nJsJ8IQdO163cO3jf3+0Er4UmTUszKmCKV3UnErqrX4sAFWcCaj0VQOEE4PMv0kH8Joe/GDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:55:42.237420Z"},"content_sha256":"20126ddb602ece6701bbc8321a68076041a3c115861af500bc39ab96c0bdf152","schema_version":"1.0","event_id":"sha256:20126ddb602ece6701bbc8321a68076041a3c115861af500bc39ab96c0bdf152"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TYJUF6V4BZ2DZQWRJJRIVXLSJ3/bundle.json","state_url":"https://pith.science/pith/TYJUF6V4BZ2DZQWRJJRIVXLSJ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TYJUF6V4BZ2DZQWRJJRIVXLSJ3/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":"2026-08-07T10:55:42Z","links":{"resolver":"https://pith.science/pith/TYJUF6V4BZ2DZQWRJJRIVXLSJ3","bundle":"https://pith.science/pith/TYJUF6V4BZ2DZQWRJJRIVXLSJ3/bundle.json","state":"https://pith.science/pith/TYJUF6V4BZ2DZQWRJJRIVXLSJ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TYJUF6V4BZ2DZQWRJJRIVXLSJ3/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PwZeIAYOuEiEQ6MnKL01zWn9e7cgIVbybGjjdb6AQ5bmQ2dTjX7s4ZFdXBRK22wZ0TXXx3YNfAIEruM1/spXBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:55:42.241415Z","bundle_sha256":"9b71bb7217c5c3b8871e69f4ce5aff064f95cbc4c21a730d2df9efd98640afe0"}}