{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EZNTATJCLFVUM47MQW3MXKLJXQ","short_pith_number":"pith:EZNTATJC","schema_version":"1.0","canonical_sha256":"265b304d22596b4673ec85b6cba969bc1dd9210d63a563148a324bc1e7926517","source":{"kind":"arxiv","id":"2306.04186","version":2},"attestation_state":"computed","paper":{"title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Nian Shao, Xian Li, Xiaofei Li","submitted_at":"2023-06-07T06:42:07Z","abstract_excerpt":"Self-supervised learning (SSL) has emerged as a popular approach for learning audio representations. One goal of audio self-supervised pre-training is to transfer knowledge to downstream audio tasks, generally including clip-level and frame-level tasks. While frame-level tasks are important for fine-grained acoustic scene/event understanding, prior studies primarily evaluate on clip-level downstream tasks. In order to tackle both clip-level and frame-level tasks, this paper proposes Audio Teacher-Student Transformer (ATST), with a clip-level version (named ATST-Clip) and a frame-level version "},"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":"2306.04186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-07T06:42:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"600814d05ec12b5ef68096d072d74c222232c935796725a0ec0c294fd1397947","abstract_canon_sha256":"10477f97d937007f16789f85c7f197ed811ee70310f9af54e9fe1ab03455b742"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:49.417864Z","signature_b64":"89hs02yimwhQupzHgBX2MiyLfyuxF5Mw7MU2JUfjkTZ/nvr4FKkz4YO5+LUrcUqEe7IRl5bMeOJcJDEWRtyvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"265b304d22596b4673ec85b6cba969bc1dd9210d63a563148a324bc1e7926517","last_reissued_at":"2026-07-05T07:09:49.417414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:49.417414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Nian Shao, Xian Li, Xiaofei Li","submitted_at":"2023-06-07T06:42:07Z","abstract_excerpt":"Self-supervised learning (SSL) has emerged as a popular approach for learning audio representations. One goal of audio self-supervised pre-training is to transfer knowledge to downstream audio tasks, generally including clip-level and frame-level tasks. While frame-level tasks are important for fine-grained acoustic scene/event understanding, prior studies primarily evaluate on clip-level downstream tasks. In order to tackle both clip-level and frame-level tasks, this paper proposes Audio Teacher-Student Transformer (ATST), with a clip-level version (named ATST-Clip) and a frame-level version "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04186","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/2306.04186/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":"2306.04186","created_at":"2026-07-05T07:09:49.417471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04186v2","created_at":"2026-07-05T07:09:49.417471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04186","created_at":"2026-07-05T07:09:49.417471+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZNTATJCLFVU","created_at":"2026-07-05T07:09:49.417471+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZNTATJCLFVUM47M","created_at":"2026-07-05T07:09:49.417471+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZNTATJC","created_at":"2026-07-05T07:09:49.417471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00475","citing_title":"AudioBERTScore: Objective Evaluation of Environmental Sound Synthesis Based on Similarity of Audio embedding Sequences","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZNTATJCLFVUM47MQW3MXKLJXQ","json":"https://pith.science/pith/EZNTATJCLFVUM47MQW3MXKLJXQ.json","graph_json":"https://pith.science/api/pith-number/EZNTATJCLFVUM47MQW3MXKLJXQ/graph.json","events_json":"https://pith.science/api/pith-number/EZNTATJCLFVUM47MQW3MXKLJXQ/events.json","paper":"https://pith.science/paper/EZNTATJC"},"agent_actions":{"view_html":"https://pith.science/pith/EZNTATJCLFVUM47MQW3MXKLJXQ","download_json":"https://pith.science/pith/EZNTATJCLFVUM47MQW3MXKLJXQ.json","view_paper":"https://pith.science/paper/EZNTATJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04186&json=true","fetch_graph":"https://pith.science/api/pith-number/EZNTATJCLFVUM47MQW3MXKLJXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/EZNTATJCLFVUM47MQW3MXKLJXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZNTATJCLFVUM47MQW3MXKLJXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZNTATJCLFVUM47MQW3MXKLJXQ/action/storage_attestation","attest_author":"https://pith.science/pith/EZNTATJCLFVUM47MQW3MXKLJXQ/action/author_attestation","sign_citation":"https://pith.science/pith/EZNTATJCLFVUM47MQW3MXKLJXQ/action/citation_signature","submit_replication":"https://pith.science/pith/EZNTATJCLFVUM47MQW3MXKLJXQ/action/replication_record"}},"created_at":"2026-07-05T07:09:49.417471+00:00","updated_at":"2026-07-05T07:09:49.417471+00:00"}