{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MARD6XVQOQCBZG7EMKZQY4DD55","short_pith_number":"pith:MARD6XVQ","schema_version":"1.0","canonical_sha256":"60223f5eb074041c9be462b30c7063ef7c53823185b76aa6dce9fec974688170","source":{"kind":"arxiv","id":"2401.12600","version":1},"attestation_state":"computed","paper":{"title":"EEND-M2F: Masked-attention mask transformers for speaker diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Lahiru Samarakoon, Marc H\\\"ark\\\"onen, Samuel J. Broughton","submitted_at":"2024-01-23T09:56:59Z","abstract_excerpt":"In this paper, we make the explicit connection between image segmentation methods and end-to-end diarization methods. From these insights, we propose a novel, fully end-to-end diarization model, EEND-M2F, based on the Mask2Former architecture. Speaker representations are computed in parallel using a stack of transformer decoders, in which irrelevant frames are explicitly masked from the cross attention using predictions from previous layers. EEND-M2F is lightweight, efficient, and truly end-to-end, as it does not require any additional diarization, speaker verification, or segmentation models "},"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":"2401.12600","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-23T09:56:59Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"7ec53ac09ed0db2387db7f0c805dd35fe1419d8a3fa7290fce46ea070a724806","abstract_canon_sha256":"a81c7141cfe7963eb089a293ebefc27838ed1e39dc1bcae7e556ca1f49528a8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:33.073731Z","signature_b64":"ZHMcDLmj/PYTM5R7jvlX4w9ZVnH+04Ese6BdwSVkUp5d6DJYUNYATXz+YJLxDlL7t0Mi2L2x9LlzfserJWR8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60223f5eb074041c9be462b30c7063ef7c53823185b76aa6dce9fec974688170","last_reissued_at":"2026-07-05T07:36:33.073272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:33.073272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EEND-M2F: Masked-attention mask transformers for speaker diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Lahiru Samarakoon, Marc H\\\"ark\\\"onen, Samuel J. Broughton","submitted_at":"2024-01-23T09:56:59Z","abstract_excerpt":"In this paper, we make the explicit connection between image segmentation methods and end-to-end diarization methods. From these insights, we propose a novel, fully end-to-end diarization model, EEND-M2F, based on the Mask2Former architecture. Speaker representations are computed in parallel using a stack of transformer decoders, in which irrelevant frames are explicitly masked from the cross attention using predictions from previous layers. EEND-M2F is lightweight, efficient, and truly end-to-end, as it does not require any additional diarization, speaker verification, or segmentation models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12600","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/2401.12600/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":"2401.12600","created_at":"2026-07-05T07:36:33.073332+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12600v1","created_at":"2026-07-05T07:36:33.073332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12600","created_at":"2026-07-05T07:36:33.073332+00:00"},{"alias_kind":"pith_short_12","alias_value":"MARD6XVQOQCB","created_at":"2026-07-05T07:36:33.073332+00:00"},{"alias_kind":"pith_short_16","alias_value":"MARD6XVQOQCBZG7E","created_at":"2026-07-05T07:36:33.073332+00:00"},{"alias_kind":"pith_short_8","alias_value":"MARD6XVQ","created_at":"2026-07-05T07:36:33.073332+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02610","citing_title":"Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MARD6XVQOQCBZG7EMKZQY4DD55","json":"https://pith.science/pith/MARD6XVQOQCBZG7EMKZQY4DD55.json","graph_json":"https://pith.science/api/pith-number/MARD6XVQOQCBZG7EMKZQY4DD55/graph.json","events_json":"https://pith.science/api/pith-number/MARD6XVQOQCBZG7EMKZQY4DD55/events.json","paper":"https://pith.science/paper/MARD6XVQ"},"agent_actions":{"view_html":"https://pith.science/pith/MARD6XVQOQCBZG7EMKZQY4DD55","download_json":"https://pith.science/pith/MARD6XVQOQCBZG7EMKZQY4DD55.json","view_paper":"https://pith.science/paper/MARD6XVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12600&json=true","fetch_graph":"https://pith.science/api/pith-number/MARD6XVQOQCBZG7EMKZQY4DD55/graph.json","fetch_events":"https://pith.science/api/pith-number/MARD6XVQOQCBZG7EMKZQY4DD55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MARD6XVQOQCBZG7EMKZQY4DD55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MARD6XVQOQCBZG7EMKZQY4DD55/action/storage_attestation","attest_author":"https://pith.science/pith/MARD6XVQOQCBZG7EMKZQY4DD55/action/author_attestation","sign_citation":"https://pith.science/pith/MARD6XVQOQCBZG7EMKZQY4DD55/action/citation_signature","submit_replication":"https://pith.science/pith/MARD6XVQOQCBZG7EMKZQY4DD55/action/replication_record"}},"created_at":"2026-07-05T07:36:33.073332+00:00","updated_at":"2026-07-05T07:36:33.073332+00:00"}