{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4VB2TWEKQZ6ANIT4O2O2FABEGK","short_pith_number":"pith:4VB2TWEK","canonical_record":{"source":{"id":"2406.06992","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-11T06:44:54Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d965ac78309aa3ec21eec9d81706d663e656969e43a7a34cf0783db9ad35dc32","abstract_canon_sha256":"3f89fa9ccc22fd32d969934dc4af901794bd6d6c28177192077d74dae2848532"},"schema_version":"1.0"},"canonical_sha256":"e543a9d88a867c06a27c769da2802432896f6d4b17090c368c2874490c49ef92","source":{"kind":"arxiv","id":"2406.06992","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06992","created_at":"2026-07-05T08:31:16Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06992v2","created_at":"2026-07-05T08:31:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06992","created_at":"2026-07-05T08:31:16Z"},{"alias_kind":"pith_short_12","alias_value":"4VB2TWEKQZ6A","created_at":"2026-07-05T08:31:16Z"},{"alias_kind":"pith_short_16","alias_value":"4VB2TWEKQZ6ANIT4","created_at":"2026-07-05T08:31:16Z"},{"alias_kind":"pith_short_8","alias_value":"4VB2TWEK","created_at":"2026-07-05T08:31:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4VB2TWEKQZ6ANIT4O2O2FABEGK","target":"record","payload":{"canonical_record":{"source":{"id":"2406.06992","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-11T06:44:54Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d965ac78309aa3ec21eec9d81706d663e656969e43a7a34cf0783db9ad35dc32","abstract_canon_sha256":"3f89fa9ccc22fd32d969934dc4af901794bd6d6c28177192077d74dae2848532"},"schema_version":"1.0"},"canonical_sha256":"e543a9d88a867c06a27c769da2802432896f6d4b17090c368c2874490c49ef92","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:16.690794Z","signature_b64":"PIGfbwTQD28gFohKs0TKPLaS9qovbWbf1lRIC4GlR+NM4thePk5zN0uvJjSc9gbnFhOEYZB5yp6tJpktW6BbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e543a9d88a867c06a27c769da2802432896f6d4b17090c368c2874490c49ef92","last_reissued_at":"2026-07-05T08:31:16.690228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:16.690228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.06992","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":"2026-07-05T08:31:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9EFWnxhrUz4BMqpvR7ZQMD+R+LgWuwlAtk2PJ5ZIDqyVDLospfRaVZxT6Q0uBJPebEpexdWvGd3UKzcn9WfxAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T22:31:23.979867Z"},"content_sha256":"fa645ab4d2134e36d94afa9f93e11bbc81c234b22dcffc980f24ef7f079dc308","schema_version":"1.0","event_id":"sha256:fa645ab4d2134e36d94afa9f93e11bbc81c234b22dcffc980f24ef7f079dc308"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4VB2TWEKQZ6ANIT4O2O2FABEGK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling up masked audio encoder learning for general audio classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Wang, Heinrich Dinkel, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","submitted_at":"2024-06-11T06:44:54Z","abstract_excerpt":"Despite progress in audio classification, a generalization gap remains between speech and other sound domains, such as environmental sounds and music. Models trained for speech tasks often fail to perform well on environmental or musical audio tasks, and vice versa. While self-supervised (SSL) audio representations offer an alternative, there has been limited exploration of scaling both model and dataset sizes for SSL-based general audio classification. We introduce Dasheng, a simple SSL audio encoder, based on the efficient masked autoencoder framework. Trained with 1.2 billion parameters on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06992","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/2406.06992/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":"2026-07-05T08:31:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h87/s97fbmOBsHqx+y6E//ZnDLMJv5mE4xUkjeJxCtM5HH8+B3btUfJbikjGmGp+wNfyhc76/hVVszKK9vaNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T22:31:23.980243Z"},"content_sha256":"47d8b8f01d7b437a84513f3015a85ef04e23da976d5bf3edd0c4da349823b69a","schema_version":"1.0","event_id":"sha256:47d8b8f01d7b437a84513f3015a85ef04e23da976d5bf3edd0c4da349823b69a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK/bundle.json","state_url":"https://pith.science/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK/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":"2026-07-09T22:31:23Z","links":{"resolver":"https://pith.science/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK","bundle":"https://pith.science/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK/bundle.json","state":"https://pith.science/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4VB2TWEKQZ6ANIT4O2O2FABEGK","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":"3f89fa9ccc22fd32d969934dc4af901794bd6d6c28177192077d74dae2848532","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-11T06:44:54Z","title_canon_sha256":"d965ac78309aa3ec21eec9d81706d663e656969e43a7a34cf0783db9ad35dc32"},"schema_version":"1.0","source":{"id":"2406.06992","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06992","created_at":"2026-07-05T08:31:16Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06992v2","created_at":"2026-07-05T08:31:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06992","created_at":"2026-07-05T08:31:16Z"},{"alias_kind":"pith_short_12","alias_value":"4VB2TWEKQZ6A","created_at":"2026-07-05T08:31:16Z"},{"alias_kind":"pith_short_16","alias_value":"4VB2TWEKQZ6ANIT4","created_at":"2026-07-05T08:31:16Z"},{"alias_kind":"pith_short_8","alias_value":"4VB2TWEK","created_at":"2026-07-05T08:31:16Z"}],"graph_snapshots":[{"event_id":"sha256:47d8b8f01d7b437a84513f3015a85ef04e23da976d5bf3edd0c4da349823b69a","target":"graph","created_at":"2026-07-05T08:31:16Z","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/2406.06992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite progress in audio classification, a generalization gap remains between speech and other sound domains, such as environmental sounds and music. Models trained for speech tasks often fail to perform well on environmental or musical audio tasks, and vice versa. While self-supervised (SSL) audio representations offer an alternative, there has been limited exploration of scaling both model and dataset sizes for SSL-based general audio classification. We introduce Dasheng, a simple SSL audio encoder, based on the efficient masked autoencoder framework. Trained with 1.2 billion parameters on ","authors_text":"Bin Wang, Heinrich Dinkel, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-11T06:44:54Z","title":"Scaling up masked audio encoder learning for general audio classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06992","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:fa645ab4d2134e36d94afa9f93e11bbc81c234b22dcffc980f24ef7f079dc308","target":"record","created_at":"2026-07-05T08:31:16Z","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":"3f89fa9ccc22fd32d969934dc4af901794bd6d6c28177192077d74dae2848532","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-11T06:44:54Z","title_canon_sha256":"d965ac78309aa3ec21eec9d81706d663e656969e43a7a34cf0783db9ad35dc32"},"schema_version":"1.0","source":{"id":"2406.06992","kind":"arxiv","version":2}},"canonical_sha256":"e543a9d88a867c06a27c769da2802432896f6d4b17090c368c2874490c49ef92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e543a9d88a867c06a27c769da2802432896f6d4b17090c368c2874490c49ef92","first_computed_at":"2026-07-05T08:31:16.690228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:16.690228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PIGfbwTQD28gFohKs0TKPLaS9qovbWbf1lRIC4GlR+NM4thePk5zN0uvJjSc9gbnFhOEYZB5yp6tJpktW6BbAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:16.690794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06992","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa645ab4d2134e36d94afa9f93e11bbc81c234b22dcffc980f24ef7f079dc308","sha256:47d8b8f01d7b437a84513f3015a85ef04e23da976d5bf3edd0c4da349823b69a"],"state_sha256":"9282de7b105f059939bc87c1722cb68aa71b570dad48d66a9e8e8613287f8a23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WmBwFUheY5V90N73U14Xwp5RmrMExyiQ7m7YcPpA6TdYOsYRTjDSVmsqteZ7h7yEzB5YUEDqJ2Yl2OPKSsy7DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T22:31:23.982327Z","bundle_sha256":"9c272954a70a4ae3070577b298af235fe01f48cbdac10945a3145369f8be85ea"}}