{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K3ZWHBQKR2QE2WY6M33OYDNKYP","short_pith_number":"pith:K3ZWHBQK","schema_version":"1.0","canonical_sha256":"56f363860a8ea04d5b1e66f6ec0daac3cd456baf79a6421b036b336cc92a1fa5","source":{"kind":"arxiv","id":"2506.12222","version":1},"attestation_state":"computed","paper":{"title":"SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Armin Mustafa, Muhammad Awais, Philip JB Jackson, Sara Ahmed, Tony Alex","submitted_at":"2025-06-13T20:48:46Z","abstract_excerpt":"Self-supervised pre-trained audio networks have seen widespread adoption in real-world systems, particularly in multi-modal large language models. These networks are often employed in a frozen state, under the assumption that the SSL pre-training has sufficiently equipped them to handle real-world audio. However, a critical question remains: how well do these models actually perform in real-world conditions, where audio is typically polyphonic and complex, involving multiple overlapping sound sources? Current audio SSL methods are often benchmarked on datasets predominantly featuring monophoni"},"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":"2506.12222","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T20:48:46Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"5545d530afacae9ec0af2eae2760e0ec8a10c553c262937cb3c6e6197dce0634","abstract_canon_sha256":"934af4f13128bce6d7345637d420d81a2cd4f113435a08e0b2d0d4d13a5af650"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:23.488878Z","signature_b64":"H5n4GmEwCSn8rZ3Mt1DjRX//5oWGhoo8sMYxzWHUFr2zPHur0j62tnNKHBwwyFR8wuUj8aXSziEL1UZrthjgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56f363860a8ea04d5b1e66f6ec0daac3cd456baf79a6421b036b336cc92a1fa5","last_reissued_at":"2026-07-05T11:21:23.488401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:23.488401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Armin Mustafa, Muhammad Awais, Philip JB Jackson, Sara Ahmed, Tony Alex","submitted_at":"2025-06-13T20:48:46Z","abstract_excerpt":"Self-supervised pre-trained audio networks have seen widespread adoption in real-world systems, particularly in multi-modal large language models. These networks are often employed in a frozen state, under the assumption that the SSL pre-training has sufficiently equipped them to handle real-world audio. However, a critical question remains: how well do these models actually perform in real-world conditions, where audio is typically polyphonic and complex, involving multiple overlapping sound sources? Current audio SSL methods are often benchmarked on datasets predominantly featuring monophoni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12222","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/2506.12222/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":"2506.12222","created_at":"2026-07-05T11:21:23.488459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12222v1","created_at":"2026-07-05T11:21:23.488459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12222","created_at":"2026-07-05T11:21:23.488459+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3ZWHBQKR2QE","created_at":"2026-07-05T11:21:23.488459+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3ZWHBQKR2QE2WY6","created_at":"2026-07-05T11:21:23.488459+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3ZWHBQK","created_at":"2026-07-05T11:21:23.488459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00387","citing_title":"From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18409","citing_title":"EnvTriCascade: An Environment-Aware Tri-Stage Cascaded Framework for ESDD2 2026 Challenge","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K3ZWHBQKR2QE2WY6M33OYDNKYP","json":"https://pith.science/pith/K3ZWHBQKR2QE2WY6M33OYDNKYP.json","graph_json":"https://pith.science/api/pith-number/K3ZWHBQKR2QE2WY6M33OYDNKYP/graph.json","events_json":"https://pith.science/api/pith-number/K3ZWHBQKR2QE2WY6M33OYDNKYP/events.json","paper":"https://pith.science/paper/K3ZWHBQK"},"agent_actions":{"view_html":"https://pith.science/pith/K3ZWHBQKR2QE2WY6M33OYDNKYP","download_json":"https://pith.science/pith/K3ZWHBQKR2QE2WY6M33OYDNKYP.json","view_paper":"https://pith.science/paper/K3ZWHBQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12222&json=true","fetch_graph":"https://pith.science/api/pith-number/K3ZWHBQKR2QE2WY6M33OYDNKYP/graph.json","fetch_events":"https://pith.science/api/pith-number/K3ZWHBQKR2QE2WY6M33OYDNKYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3ZWHBQKR2QE2WY6M33OYDNKYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3ZWHBQKR2QE2WY6M33OYDNKYP/action/storage_attestation","attest_author":"https://pith.science/pith/K3ZWHBQKR2QE2WY6M33OYDNKYP/action/author_attestation","sign_citation":"https://pith.science/pith/K3ZWHBQKR2QE2WY6M33OYDNKYP/action/citation_signature","submit_replication":"https://pith.science/pith/K3ZWHBQKR2QE2WY6M33OYDNKYP/action/replication_record"}},"created_at":"2026-07-05T11:21:23.488459+00:00","updated_at":"2026-07-05T11:21:23.488459+00:00"}