{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EZNTATJCLFVUM47MQW3MXKLJXQ","short_pith_number":"pith:EZNTATJC","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"},"canonical_sha256":"265b304d22596b4673ec85b6cba969bc1dd9210d63a563148a324bc1e7926517","source":{"kind":"arxiv","id":"2306.04186","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04186","created_at":"2026-07-05T07:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04186v2","created_at":"2026-07-05T07:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04186","created_at":"2026-07-05T07:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"EZNTATJCLFVU","created_at":"2026-07-05T07:09:49Z"},{"alias_kind":"pith_short_16","alias_value":"EZNTATJCLFVUM47M","created_at":"2026-07-05T07:09:49Z"},{"alias_kind":"pith_short_8","alias_value":"EZNTATJC","created_at":"2026-07-05T07:09:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EZNTATJCLFVUM47MQW3MXKLJXQ","target":"record","payload":{"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"},"canonical_sha256":"265b304d22596b4673ec85b6cba969bc1dd9210d63a563148a324bc1e7926517","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"},"source_kind":"arxiv","source_id":"2306.04186","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:09:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qo5/EVmxnraHYl2GnVHy8FOPXxEiTRKGLm+emU3knOoXILhWwM9vFqbX2MREw5/wcc+rDqQ/Eb5aJbj4ZAA+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:46:27.422693Z"},"content_sha256":"3866c980306f6c4ce183492f88057d4bc760343a7e4bcd7d1a0ecffccd1e2154","schema_version":"1.0","event_id":"sha256:3866c980306f6c4ce183492f88057d4bc760343a7e4bcd7d1a0ecffccd1e2154"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EZNTATJCLFVUM47MQW3MXKLJXQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:09:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YNXTp8ID7tUh34c5JzrnHcxPvEW4/bJXBpKEppdPIrEhoYyOGoCIrWlLJYnhuSWOsBHghFL8BSgakLcawTlEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:46:27.423180Z"},"content_sha256":"e04afc87fce97ec96dd945b3fab3eea11a621d3041f3fe449283246ed0da0a68","schema_version":"1.0","event_id":"sha256:e04afc87fce97ec96dd945b3fab3eea11a621d3041f3fe449283246ed0da0a68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EZNTATJCLFVUM47MQW3MXKLJXQ/bundle.json","state_url":"https://pith.science/pith/EZNTATJCLFVUM47MQW3MXKLJXQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EZNTATJCLFVUM47MQW3MXKLJXQ/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":"2026-08-09T17:46:27Z","links":{"resolver":"https://pith.science/pith/EZNTATJCLFVUM47MQW3MXKLJXQ","bundle":"https://pith.science/pith/EZNTATJCLFVUM47MQW3MXKLJXQ/bundle.json","state":"https://pith.science/pith/EZNTATJCLFVUM47MQW3MXKLJXQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EZNTATJCLFVUM47MQW3MXKLJXQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EZNTATJCLFVUM47MQW3MXKLJXQ","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":"10477f97d937007f16789f85c7f197ed811ee70310f9af54e9fe1ab03455b742","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-07T06:42:07Z","title_canon_sha256":"600814d05ec12b5ef68096d072d74c222232c935796725a0ec0c294fd1397947"},"schema_version":"1.0","source":{"id":"2306.04186","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04186","created_at":"2026-07-05T07:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04186v2","created_at":"2026-07-05T07:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04186","created_at":"2026-07-05T07:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"EZNTATJCLFVU","created_at":"2026-07-05T07:09:49Z"},{"alias_kind":"pith_short_16","alias_value":"EZNTATJCLFVUM47M","created_at":"2026-07-05T07:09:49Z"},{"alias_kind":"pith_short_8","alias_value":"EZNTATJC","created_at":"2026-07-05T07:09:49Z"}],"graph_snapshots":[{"event_id":"sha256:e04afc87fce97ec96dd945b3fab3eea11a621d3041f3fe449283246ed0da0a68","target":"graph","created_at":"2026-07-05T07:09:49Z","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/2306.04186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Nian Shao, Xian Li, Xiaofei Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-07T06:42:07Z","title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04186","kind":"arxiv","version":2},"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":"sha256:3866c980306f6c4ce183492f88057d4bc760343a7e4bcd7d1a0ecffccd1e2154","target":"record","created_at":"2026-07-05T07:09:49Z","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":"10477f97d937007f16789f85c7f197ed811ee70310f9af54e9fe1ab03455b742","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-07T06:42:07Z","title_canon_sha256":"600814d05ec12b5ef68096d072d74c222232c935796725a0ec0c294fd1397947"},"schema_version":"1.0","source":{"id":"2306.04186","kind":"arxiv","version":2}},"canonical_sha256":"265b304d22596b4673ec85b6cba969bc1dd9210d63a563148a324bc1e7926517","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"265b304d22596b4673ec85b6cba969bc1dd9210d63a563148a324bc1e7926517","first_computed_at":"2026-07-05T07:09:49.417414Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:49.417414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"89hs02yimwhQupzHgBX2MiyLfyuxF5Mw7MU2JUfjkTZ/nvr4FKkz4YO5+LUrcUqEe7IRl5bMeOJcJDEWRtyvDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:49.417864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.04186","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3866c980306f6c4ce183492f88057d4bc760343a7e4bcd7d1a0ecffccd1e2154","sha256:e04afc87fce97ec96dd945b3fab3eea11a621d3041f3fe449283246ed0da0a68"],"state_sha256":"b883bed95c0f3895eb3ad2de94cbc7937020c098aead47e02b7bbada58dc76d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0HWw8sD97w6WqFvH1eFNF7MgGsBvrON2AEIr0SrJS/mocZuwxDhYImsPdPKeP3XwJ/8MYsAwjX6DHWo3KJAAAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:46:27.426848Z","bundle_sha256":"ff083c79bf834572d9c4ea31b499eb3f74f0ab53d236a62bf089d603e7834a99"}}