{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GXYI32H7TV5N6B4GSMN4QZ3ZP5","short_pith_number":"pith:GXYI32H7","schema_version":"1.0","canonical_sha256":"35f08de8ff9d7adf0786931bc867797f76ed2318e188487c1a3d5091ec9e425d","source":{"kind":"arxiv","id":"2501.15302","version":1},"attestation_state":"computed","paper":{"title":"The ICME 2025 Audio Encoder Capability Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heinrich Dinkel, Helen Wang, Jian Luan, Junbo Zhang, Ke Li, Qiong Song, Si Cheng, Wenwu Wang, Xiaofeng Xin, Yadong Niu, Yujun Wang","submitted_at":"2025-01-25T18:56:40Z","abstract_excerpt":"This challenge aims to evaluate the capabilities of audio encoders, especially in the context of multi-task learning and real-world applications. Participants are invited to submit pre-trained audio encoders that map raw waveforms to continuous embeddings. These encoders will be tested across diverse tasks including speech, environmental sounds, and music, with a focus on real-world usability. The challenge features two tracks: Track A for parameterized evaluation, and Track B for parameter-free evaluation. This challenge provides a platform for evaluating and advancing the state-of-the-art in"},"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":"2501.15302","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-25T18:56:40Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"a33cb51c20349cafd5a38d150ca3f84aff7c024fd6b327f2f09c09749d6256db","abstract_canon_sha256":"1f68c42c233352ffc395e6cb7928735f9d7c654a23ff966afe9e5e9ad4a2487a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:27.098777Z","signature_b64":"UjH+NQq4GloPUGlpRieSV9YxEiy79aVcZ/4R7uxklxeiMYd/EJomVeU9MCI+ATqTpQj4l8XhE+ojJtbQJr7AAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35f08de8ff9d7adf0786931bc867797f76ed2318e188487c1a3d5091ec9e425d","last_reissued_at":"2026-07-05T10:05:27.098089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:27.098089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The ICME 2025 Audio Encoder Capability Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heinrich Dinkel, Helen Wang, Jian Luan, Junbo Zhang, Ke Li, Qiong Song, Si Cheng, Wenwu Wang, Xiaofeng Xin, Yadong Niu, Yujun Wang","submitted_at":"2025-01-25T18:56:40Z","abstract_excerpt":"This challenge aims to evaluate the capabilities of audio encoders, especially in the context of multi-task learning and real-world applications. Participants are invited to submit pre-trained audio encoders that map raw waveforms to continuous embeddings. These encoders will be tested across diverse tasks including speech, environmental sounds, and music, with a focus on real-world usability. The challenge features two tracks: Track A for parameterized evaluation, and Track B for parameter-free evaluation. This challenge provides a platform for evaluating and advancing the state-of-the-art in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15302","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/2501.15302/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":"2501.15302","created_at":"2026-07-05T10:05:27.098209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15302v1","created_at":"2026-07-05T10:05:27.098209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15302","created_at":"2026-07-05T10:05:27.098209+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXYI32H7TV5N","created_at":"2026-07-05T10:05:27.098209+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXYI32H7TV5N6B4G","created_at":"2026-07-05T10:05:27.098209+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXYI32H7","created_at":"2026-07-05T10:05:27.098209+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14129","citing_title":"OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GXYI32H7TV5N6B4GSMN4QZ3ZP5","json":"https://pith.science/pith/GXYI32H7TV5N6B4GSMN4QZ3ZP5.json","graph_json":"https://pith.science/api/pith-number/GXYI32H7TV5N6B4GSMN4QZ3ZP5/graph.json","events_json":"https://pith.science/api/pith-number/GXYI32H7TV5N6B4GSMN4QZ3ZP5/events.json","paper":"https://pith.science/paper/GXYI32H7"},"agent_actions":{"view_html":"https://pith.science/pith/GXYI32H7TV5N6B4GSMN4QZ3ZP5","download_json":"https://pith.science/pith/GXYI32H7TV5N6B4GSMN4QZ3ZP5.json","view_paper":"https://pith.science/paper/GXYI32H7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15302&json=true","fetch_graph":"https://pith.science/api/pith-number/GXYI32H7TV5N6B4GSMN4QZ3ZP5/graph.json","fetch_events":"https://pith.science/api/pith-number/GXYI32H7TV5N6B4GSMN4QZ3ZP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXYI32H7TV5N6B4GSMN4QZ3ZP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXYI32H7TV5N6B4GSMN4QZ3ZP5/action/storage_attestation","attest_author":"https://pith.science/pith/GXYI32H7TV5N6B4GSMN4QZ3ZP5/action/author_attestation","sign_citation":"https://pith.science/pith/GXYI32H7TV5N6B4GSMN4QZ3ZP5/action/citation_signature","submit_replication":"https://pith.science/pith/GXYI32H7TV5N6B4GSMN4QZ3ZP5/action/replication_record"}},"created_at":"2026-07-05T10:05:27.098209+00:00","updated_at":"2026-07-05T10:05:27.098209+00:00"}