{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:USTVYRFEWSOAWSJVGDSNIRADGL","short_pith_number":"pith:USTVYRFE","schema_version":"1.0","canonical_sha256":"a4a75c44a4b49c0b493530e4d4440332d06356e1a1e2c2243038300106d5916f","source":{"kind":"arxiv","id":"2507.14129","version":1},"attestation_state":"computed","paper":{"title":"OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hye-Jin Shim, Kwanghee Choi, Samuele Cornell, Satoru Fukayama, Shikhar Bharadwaj, Shinji Watanabe, Soham Deshmukh","submitted_at":"2025-07-18T17:57:46Z","abstract_excerpt":"Masked token prediction has emerged as a powerful pre-training objective across language, vision, and speech, offering the potential to unify these diverse modalities through a single pre-training task. However, its application for general audio understanding remains underexplored, with BEATs being the only notable example. BEATs has seen limited modifications due to the absence of open-source pre-training code. Furthermore, BEATs was trained only on AudioSet, restricting its broader downstream applicability. To address these gaps, we present OpenBEATs, an open-source framework that extends BE"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.14129","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-18T17:57:46Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f2a005993887a9bf95412f30598a91b68fb2957b7a51e9e4757bcddff42d07f2","abstract_canon_sha256":"d49c698b0327293e2edbc33a9945b33b8d5cdfdf8710fbab0ae550e9cf1f6339"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:29.230093Z","signature_b64":"cosJFEvi3PF1DlPPhDVloRyvir8iIkWgcuvvhmU+G0xGJ5t/RW6jBBi6oVOSQXt+k+ICxw+guuy1YNgAoMaLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4a75c44a4b49c0b493530e4d4440332d06356e1a1e2c2243038300106d5916f","last_reissued_at":"2026-07-05T11:39:29.229604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:29.229604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hye-Jin Shim, Kwanghee Choi, Samuele Cornell, Satoru Fukayama, Shikhar Bharadwaj, Shinji Watanabe, Soham Deshmukh","submitted_at":"2025-07-18T17:57:46Z","abstract_excerpt":"Masked token prediction has emerged as a powerful pre-training objective across language, vision, and speech, offering the potential to unify these diverse modalities through a single pre-training task. However, its application for general audio understanding remains underexplored, with BEATs being the only notable example. BEATs has seen limited modifications due to the absence of open-source pre-training code. Furthermore, BEATs was trained only on AudioSet, restricting its broader downstream applicability. To address these gaps, we present OpenBEATs, an open-source framework that extends BE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14129","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/2507.14129/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.14129","created_at":"2026-07-05T11:39:29.229660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14129v1","created_at":"2026-07-05T11:39:29.229660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14129","created_at":"2026-07-05T11:39:29.229660+00:00"},{"alias_kind":"pith_short_12","alias_value":"USTVYRFEWSOA","created_at":"2026-07-05T11:39:29.229660+00:00"},{"alias_kind":"pith_short_16","alias_value":"USTVYRFEWSOAWSJV","created_at":"2026-07-05T11:39:29.229660+00:00"},{"alias_kind":"pith_short_8","alias_value":"USTVYRFE","created_at":"2026-07-05T11:39:29.229660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":200,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/USTVYRFEWSOAWSJVGDSNIRADGL","json":"https://pith.science/pith/USTVYRFEWSOAWSJVGDSNIRADGL.json","graph_json":"https://pith.science/api/pith-number/USTVYRFEWSOAWSJVGDSNIRADGL/graph.json","events_json":"https://pith.science/api/pith-number/USTVYRFEWSOAWSJVGDSNIRADGL/events.json","paper":"https://pith.science/paper/USTVYRFE"},"agent_actions":{"view_html":"https://pith.science/pith/USTVYRFEWSOAWSJVGDSNIRADGL","download_json":"https://pith.science/pith/USTVYRFEWSOAWSJVGDSNIRADGL.json","view_paper":"https://pith.science/paper/USTVYRFE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14129&json=true","fetch_graph":"https://pith.science/api/pith-number/USTVYRFEWSOAWSJVGDSNIRADGL/graph.json","fetch_events":"https://pith.science/api/pith-number/USTVYRFEWSOAWSJVGDSNIRADGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/USTVYRFEWSOAWSJVGDSNIRADGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/USTVYRFEWSOAWSJVGDSNIRADGL/action/storage_attestation","attest_author":"https://pith.science/pith/USTVYRFEWSOAWSJVGDSNIRADGL/action/author_attestation","sign_citation":"https://pith.science/pith/USTVYRFEWSOAWSJVGDSNIRADGL/action/citation_signature","submit_replication":"https://pith.science/pith/USTVYRFEWSOAWSJVGDSNIRADGL/action/replication_record"}},"created_at":"2026-07-05T11:39:29.229660+00:00","updated_at":"2026-07-05T11:39:29.229660+00:00"}