{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RI7PO235GUWQYYBLXKDYO2L2ND","short_pith_number":"pith:RI7PO235","canonical_record":{"source":{"id":"2406.02032","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-04T07:17:44Z","cross_cats_sorted":["cs.MM","cs.SD"],"title_canon_sha256":"db51447476655e8091b64be58456a1590844e924ff4409f3142fe82a58ca777b","abstract_canon_sha256":"795ca3a2a4d8566130aeabc8a4e807caa94d272e96817798ef0584e95fe1673d"},"schema_version":"1.0"},"canonical_sha256":"8a3ef76b7d352d0c602bba8787697a68c91fc43022b6c7f2de6be8425a174ac2","source":{"kind":"arxiv","id":"2406.02032","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02032","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02032v1","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02032","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"pith_short_12","alias_value":"RI7PO235GUWQ","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"pith_short_16","alias_value":"RI7PO235GUWQYYBL","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"pith_short_8","alias_value":"RI7PO235","created_at":"2026-07-05T08:27:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RI7PO235GUWQYYBLXKDYO2L2ND","target":"record","payload":{"canonical_record":{"source":{"id":"2406.02032","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-04T07:17:44Z","cross_cats_sorted":["cs.MM","cs.SD"],"title_canon_sha256":"db51447476655e8091b64be58456a1590844e924ff4409f3142fe82a58ca777b","abstract_canon_sha256":"795ca3a2a4d8566130aeabc8a4e807caa94d272e96817798ef0584e95fe1673d"},"schema_version":"1.0"},"canonical_sha256":"8a3ef76b7d352d0c602bba8787697a68c91fc43022b6c7f2de6be8425a174ac2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:13.496027Z","signature_b64":"+oKRCuaPL1JMY4E12qF11Lumuf/XNDSZl7SbqcgPmkvRAcuBDUVJStbzI04SqZy5cr33vnCmcon2FclbGv/aCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a3ef76b7d352d0c602bba8787697a68c91fc43022b6c7f2de6be8425a174ac2","last_reissued_at":"2026-07-05T08:27:13.495550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:13.495550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.02032","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":"2026-07-05T08:27:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/3cywf7RYjfeV8Bw0kMf21PApoKjPzr9pNIOuC1eXrlTFn39LJVbNtTgKAIJh3kn2lccJp+yk2auOANZUy0LCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:33:25.191909Z"},"content_sha256":"f0dfe62d96c83d4f9096970db402ddc7a3e4cbc381de2bf28811385fdacbc822","schema_version":"1.0","event_id":"sha256:f0dfe62d96c83d4f9096970db402ddc7a3e4cbc381de2bf28811385fdacbc822"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RI7PO235GUWQYYBLXKDYO2L2ND","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Daiki Takeuchi, Daisuke Niizumi, Keisuke Imoto, Masahiro Yasuda, Noboru Harada, Shunsuke Tsubaki, Yasunori Ohishi","submitted_at":"2024-06-04T07:17:44Z","abstract_excerpt":"Contrastive language-audio pre-training (CLAP) enables zero-shot (ZS) inference of audio and exhibits promising performance in several classification tasks. However, conventional audio representations are still crucial for many tasks where ZS is not applicable (e.g., regression problems). Here, we explore a new representation, a general-purpose audio-language representation, that performs well in both ZS and transfer learning. To do so, we propose a new method, M2D-CLAP, which combines self-supervised learning Masked Modeling Duo (M2D) and CLAP. M2D learns an effective representation to model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02032","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/2406.02032/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":"2026-07-05T08:27:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t7U/zLo0ADiHO05QGbmmn+AYJDIQRUlLH+pb6vXBLe73bFzRYzA0TKGFl1JMQBcSNkq79Uk1ivvB8orOdmPaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:33:25.193317Z"},"content_sha256":"fa8ecceffa4ec5974e27c2ad849be350ad731f3b89d67c6956d06c85b1725918","schema_version":"1.0","event_id":"sha256:fa8ecceffa4ec5974e27c2ad849be350ad731f3b89d67c6956d06c85b1725918"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RI7PO235GUWQYYBLXKDYO2L2ND/bundle.json","state_url":"https://pith.science/pith/RI7PO235GUWQYYBLXKDYO2L2ND/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RI7PO235GUWQYYBLXKDYO2L2ND/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":"2026-08-04T02:33:25Z","links":{"resolver":"https://pith.science/pith/RI7PO235GUWQYYBLXKDYO2L2ND","bundle":"https://pith.science/pith/RI7PO235GUWQYYBLXKDYO2L2ND/bundle.json","state":"https://pith.science/pith/RI7PO235GUWQYYBLXKDYO2L2ND/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RI7PO235GUWQYYBLXKDYO2L2ND/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RI7PO235GUWQYYBLXKDYO2L2ND","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":"795ca3a2a4d8566130aeabc8a4e807caa94d272e96817798ef0584e95fe1673d","cross_cats_sorted":["cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-04T07:17:44Z","title_canon_sha256":"db51447476655e8091b64be58456a1590844e924ff4409f3142fe82a58ca777b"},"schema_version":"1.0","source":{"id":"2406.02032","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02032","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02032v1","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02032","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"pith_short_12","alias_value":"RI7PO235GUWQ","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"pith_short_16","alias_value":"RI7PO235GUWQYYBL","created_at":"2026-07-05T08:27:13Z"},{"alias_kind":"pith_short_8","alias_value":"RI7PO235","created_at":"2026-07-05T08:27:13Z"}],"graph_snapshots":[{"event_id":"sha256:fa8ecceffa4ec5974e27c2ad849be350ad731f3b89d67c6956d06c85b1725918","target":"graph","created_at":"2026-07-05T08:27:13Z","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/2406.02032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive language-audio pre-training (CLAP) enables zero-shot (ZS) inference of audio and exhibits promising performance in several classification tasks. However, conventional audio representations are still crucial for many tasks where ZS is not applicable (e.g., regression problems). Here, we explore a new representation, a general-purpose audio-language representation, that performs well in both ZS and transfer learning. To do so, we propose a new method, M2D-CLAP, which combines self-supervised learning Masked Modeling Duo (M2D) and CLAP. M2D learns an effective representation to model ","authors_text":"Daiki Takeuchi, Daisuke Niizumi, Keisuke Imoto, Masahiro Yasuda, Noboru Harada, Shunsuke Tsubaki, Yasunori Ohishi","cross_cats":["cs.MM","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-04T07:17:44Z","title":"M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02032","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:f0dfe62d96c83d4f9096970db402ddc7a3e4cbc381de2bf28811385fdacbc822","target":"record","created_at":"2026-07-05T08:27:13Z","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":"795ca3a2a4d8566130aeabc8a4e807caa94d272e96817798ef0584e95fe1673d","cross_cats_sorted":["cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-04T07:17:44Z","title_canon_sha256":"db51447476655e8091b64be58456a1590844e924ff4409f3142fe82a58ca777b"},"schema_version":"1.0","source":{"id":"2406.02032","kind":"arxiv","version":1}},"canonical_sha256":"8a3ef76b7d352d0c602bba8787697a68c91fc43022b6c7f2de6be8425a174ac2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a3ef76b7d352d0c602bba8787697a68c91fc43022b6c7f2de6be8425a174ac2","first_computed_at":"2026-07-05T08:27:13.495550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:13.495550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+oKRCuaPL1JMY4E12qF11Lumuf/XNDSZl7SbqcgPmkvRAcuBDUVJStbzI04SqZy5cr33vnCmcon2FclbGv/aCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:13.496027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02032","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0dfe62d96c83d4f9096970db402ddc7a3e4cbc381de2bf28811385fdacbc822","sha256:fa8ecceffa4ec5974e27c2ad849be350ad731f3b89d67c6956d06c85b1725918"],"state_sha256":"5664566c795d0fbec39347a07ae2d2c5865669dfe9a13ee57864e9fb55dd570a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mfNU2SxRFo8sV42/Vnvwo2ONduXX4cZCA0gyPTO2QorTFPut7n0YXzy2UBVwR3m7CjH0vcJhWeRXQHEd9RC6Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T02:33:25.201902Z","bundle_sha256":"d02ba2c7e27a501c43d6eedc9fdcd804bb906c08770ee14167f7ea147040fc9e"}}