{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:36LQKUXLSYTX66UKS2MZGOSWIN","short_pith_number":"pith:36LQKUXL","canonical_record":{"source":{"id":"2404.06095","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-09T07:57:08Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b87ab4e88b0349c1715397c13e08fdd94e8efb3ac6b4e34b5c7ae247fff3eb69","abstract_canon_sha256":"fbb89c130f215b953d3704b08705b6f49991c77a639838cde11b1b7c9cd20531"},"schema_version":"1.0"},"canonical_sha256":"df970552eb96277f7a8a9699933a56434458b6d9a30aca37b2f23842920c280e","source":{"kind":"arxiv","id":"2404.06095","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06095","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06095v1","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06095","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"pith_short_12","alias_value":"36LQKUXLSYTX","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"pith_short_16","alias_value":"36LQKUXLSYTX66UK","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"pith_short_8","alias_value":"36LQKUXL","created_at":"2026-07-05T08:06:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:36LQKUXLSYTX66UKS2MZGOSWIN","target":"record","payload":{"canonical_record":{"source":{"id":"2404.06095","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-09T07:57:08Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b87ab4e88b0349c1715397c13e08fdd94e8efb3ac6b4e34b5c7ae247fff3eb69","abstract_canon_sha256":"fbb89c130f215b953d3704b08705b6f49991c77a639838cde11b1b7c9cd20531"},"schema_version":"1.0"},"canonical_sha256":"df970552eb96277f7a8a9699933a56434458b6d9a30aca37b2f23842920c280e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:03.680165Z","signature_b64":"s3lmjq6p/juYS0G8YPk96fW0AZXn4YQGr/o27jbrmPvNSqmmx3IOvwmZmEebBqUoSlMw6j/6hE2PKZmLYnUHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df970552eb96277f7a8a9699933a56434458b6d9a30aca37b2f23842920c280e","last_reissued_at":"2026-07-05T08:06:03.679695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:03.679695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.06095","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":"2026-07-05T08:06:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"enIOJUDX2Ob9GLXsEcs2DJw+uJC0PHv8jlaym/bZJu7gxlnnO7l0QV6amlecR8360oBBUWKEpfbZLqOfsnjUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:33:52.653795Z"},"content_sha256":"19bbcca6ba99b71c9600ae80ee8bbbbb1ba25997d045f04475b9e1b1f9c8968d","schema_version":"1.0","event_id":"sha256:19bbcca6ba99b71c9600ae80ee8bbbbb1ba25997d045f04475b9e1b1f9c8968d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:36LQKUXLSYTX66UKS2MZGOSWIN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daiki Takeuchi, Daisuke Niizumi, Kunio Kashino, Noboru Harada, Yasunori Ohishi","submitted_at":"2024-04-09T07:57:08Z","abstract_excerpt":"Self-supervised learning (SSL) using masked prediction has made great strides in general-purpose audio representation. This study proposes Masked Modeling Duo (M2D), an improved masked prediction SSL, which learns by predicting representations of masked input signals that serve as training signals. Unlike conventional methods, M2D obtains a training signal by encoding only the masked part, encouraging the two networks in M2D to model the input. While M2D improves general-purpose audio representations, a specialized representation is essential for real-world applications, such as in industrial "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06095","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/2404.06095/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":"2026-07-05T08:06:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q40jRDEqkMFmNwkXk2SQlCIxQSZBqTy9UQ6uuSviA8g81iWoMeCuXN2mohMD0Rlj7ez0y03BXBfdndHBr+84BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:33:52.654419Z"},"content_sha256":"8c66524695a30f8590824840db9c0630335a9b49fa52e30c99e4a1df2a544f03","schema_version":"1.0","event_id":"sha256:8c66524695a30f8590824840db9c0630335a9b49fa52e30c99e4a1df2a544f03"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/36LQKUXLSYTX66UKS2MZGOSWIN/bundle.json","state_url":"https://pith.science/pith/36LQKUXLSYTX66UKS2MZGOSWIN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/36LQKUXLSYTX66UKS2MZGOSWIN/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":"2026-08-07T22:33:52Z","links":{"resolver":"https://pith.science/pith/36LQKUXLSYTX66UKS2MZGOSWIN","bundle":"https://pith.science/pith/36LQKUXLSYTX66UKS2MZGOSWIN/bundle.json","state":"https://pith.science/pith/36LQKUXLSYTX66UKS2MZGOSWIN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/36LQKUXLSYTX66UKS2MZGOSWIN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:36LQKUXLSYTX66UKS2MZGOSWIN","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":"fbb89c130f215b953d3704b08705b6f49991c77a639838cde11b1b7c9cd20531","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-09T07:57:08Z","title_canon_sha256":"b87ab4e88b0349c1715397c13e08fdd94e8efb3ac6b4e34b5c7ae247fff3eb69"},"schema_version":"1.0","source":{"id":"2404.06095","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06095","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06095v1","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06095","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"pith_short_12","alias_value":"36LQKUXLSYTX","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"pith_short_16","alias_value":"36LQKUXLSYTX66UK","created_at":"2026-07-05T08:06:03Z"},{"alias_kind":"pith_short_8","alias_value":"36LQKUXL","created_at":"2026-07-05T08:06:03Z"}],"graph_snapshots":[{"event_id":"sha256:8c66524695a30f8590824840db9c0630335a9b49fa52e30c99e4a1df2a544f03","target":"graph","created_at":"2026-07-05T08:06:03Z","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/2404.06095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised learning (SSL) using masked prediction has made great strides in general-purpose audio representation. This study proposes Masked Modeling Duo (M2D), an improved masked prediction SSL, which learns by predicting representations of masked input signals that serve as training signals. Unlike conventional methods, M2D obtains a training signal by encoding only the masked part, encouraging the two networks in M2D to model the input. While M2D improves general-purpose audio representations, a specialized representation is essential for real-world applications, such as in industrial ","authors_text":"Daiki Takeuchi, Daisuke Niizumi, Kunio Kashino, Noboru Harada, Yasunori Ohishi","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-09T07:57:08Z","title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06095","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":"sha256:19bbcca6ba99b71c9600ae80ee8bbbbb1ba25997d045f04475b9e1b1f9c8968d","target":"record","created_at":"2026-07-05T08:06:03Z","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":"fbb89c130f215b953d3704b08705b6f49991c77a639838cde11b1b7c9cd20531","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-09T07:57:08Z","title_canon_sha256":"b87ab4e88b0349c1715397c13e08fdd94e8efb3ac6b4e34b5c7ae247fff3eb69"},"schema_version":"1.0","source":{"id":"2404.06095","kind":"arxiv","version":1}},"canonical_sha256":"df970552eb96277f7a8a9699933a56434458b6d9a30aca37b2f23842920c280e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df970552eb96277f7a8a9699933a56434458b6d9a30aca37b2f23842920c280e","first_computed_at":"2026-07-05T08:06:03.679695Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:03.679695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s3lmjq6p/juYS0G8YPk96fW0AZXn4YQGr/o27jbrmPvNSqmmx3IOvwmZmEebBqUoSlMw6j/6hE2PKZmLYnUHCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:03.680165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06095","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19bbcca6ba99b71c9600ae80ee8bbbbb1ba25997d045f04475b9e1b1f9c8968d","sha256:8c66524695a30f8590824840db9c0630335a9b49fa52e30c99e4a1df2a544f03"],"state_sha256":"1bef81d9a7629cd86696a74eb21e5a37b1a22ac3503f984a0959568e4aa144f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a4PyltHcrCDnhawGfYHkeQV5O95987NndreGlBkPSgP4qH5iJlIdHhsFjR6ux6XNxj2U2ItyfFNuSq/heUbMCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:33:52.658724Z","bundle_sha256":"5e023dcf1c868a597ea9561a9f5e040f9ac2631106e0386deb1ee86e8e40c0ac"}}