{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MARD6XVQOQCBZG7EMKZQY4DD55","short_pith_number":"pith:MARD6XVQ","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"},"canonical_sha256":"60223f5eb074041c9be462b30c7063ef7c53823185b76aa6dce9fec974688170","source":{"kind":"arxiv","id":"2401.12600","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12600","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12600v1","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12600","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_12","alias_value":"MARD6XVQOQCB","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_16","alias_value":"MARD6XVQOQCBZG7E","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_8","alias_value":"MARD6XVQ","created_at":"2026-07-05T07:36:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MARD6XVQOQCBZG7EMKZQY4DD55","target":"record","payload":{"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"},"canonical_sha256":"60223f5eb074041c9be462b30c7063ef7c53823185b76aa6dce9fec974688170","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"},"source_kind":"arxiv","source_id":"2401.12600","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:36:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8tddwMhzK7bPrlv5AM5kZBu5e8p236EklnGrcTifRGeqUfsmIW9jS4bujXW7WE71V1Au+v1YdXwqoJll3nqQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:00:56.817359Z"},"content_sha256":"bf0de88b5e9f89383188fede312fb70e606544c3a3d1bcc6b1f7f37ec8249c02","schema_version":"1.0","event_id":"sha256:bf0de88b5e9f89383188fede312fb70e606544c3a3d1bcc6b1f7f37ec8249c02"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MARD6XVQOQCBZG7EMKZQY4DD55","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:36:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FoxqE+hSJ3esppnOEF2/8qIGDNPfCP2BzJCh80pFFwxpTEUNQllJrAfv0ZLCuYcG6kdDFcP072UaKmm2J14YBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:00:56.817865Z"},"content_sha256":"6578cfb43bb8162d5e017c5f4208c52096b71bc8eec66b61a12a5b6ee1b057fa","schema_version":"1.0","event_id":"sha256:6578cfb43bb8162d5e017c5f4208c52096b71bc8eec66b61a12a5b6ee1b057fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MARD6XVQOQCBZG7EMKZQY4DD55/bundle.json","state_url":"https://pith.science/pith/MARD6XVQOQCBZG7EMKZQY4DD55/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MARD6XVQOQCBZG7EMKZQY4DD55/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":"2026-08-09T18:00:56Z","links":{"resolver":"https://pith.science/pith/MARD6XVQOQCBZG7EMKZQY4DD55","bundle":"https://pith.science/pith/MARD6XVQOQCBZG7EMKZQY4DD55/bundle.json","state":"https://pith.science/pith/MARD6XVQOQCBZG7EMKZQY4DD55/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MARD6XVQOQCBZG7EMKZQY4DD55/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MARD6XVQOQCBZG7EMKZQY4DD55","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":"a81c7141cfe7963eb089a293ebefc27838ed1e39dc1bcae7e556ca1f49528a8d","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-23T09:56:59Z","title_canon_sha256":"7ec53ac09ed0db2387db7f0c805dd35fe1419d8a3fa7290fce46ea070a724806"},"schema_version":"1.0","source":{"id":"2401.12600","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12600","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12600v1","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12600","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_12","alias_value":"MARD6XVQOQCB","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_16","alias_value":"MARD6XVQOQCBZG7E","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_8","alias_value":"MARD6XVQ","created_at":"2026-07-05T07:36:33Z"}],"graph_snapshots":[{"event_id":"sha256:6578cfb43bb8162d5e017c5f4208c52096b71bc8eec66b61a12a5b6ee1b057fa","target":"graph","created_at":"2026-07-05T07:36:33Z","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/2401.12600/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Lahiru Samarakoon, Marc H\\\"ark\\\"onen, Samuel J. Broughton","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-23T09:56:59Z","title":"EEND-M2F: Masked-attention mask transformers for speaker diarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12600","kind":"arxiv","version":1},"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:bf0de88b5e9f89383188fede312fb70e606544c3a3d1bcc6b1f7f37ec8249c02","target":"record","created_at":"2026-07-05T07:36:33Z","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":"a81c7141cfe7963eb089a293ebefc27838ed1e39dc1bcae7e556ca1f49528a8d","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-23T09:56:59Z","title_canon_sha256":"7ec53ac09ed0db2387db7f0c805dd35fe1419d8a3fa7290fce46ea070a724806"},"schema_version":"1.0","source":{"id":"2401.12600","kind":"arxiv","version":1}},"canonical_sha256":"60223f5eb074041c9be462b30c7063ef7c53823185b76aa6dce9fec974688170","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60223f5eb074041c9be462b30c7063ef7c53823185b76aa6dce9fec974688170","first_computed_at":"2026-07-05T07:36:33.073272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:33.073272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZHMcDLmj/PYTM5R7jvlX4w9ZVnH+04Ese6BdwSVkUp5d6DJYUNYATXz+YJLxDlL7t0Mi2L2x9LlzfserJWR8Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:33.073731Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12600","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf0de88b5e9f89383188fede312fb70e606544c3a3d1bcc6b1f7f37ec8249c02","sha256:6578cfb43bb8162d5e017c5f4208c52096b71bc8eec66b61a12a5b6ee1b057fa"],"state_sha256":"e5904536c11a874b6998ca3cb18eb181c4f2cb5698c51c68c319465e314ae5a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K3vpb5PHcZWcLL8/ulWsrDaWRXn6CqWkbV9QH+F+lb7H7hhgXPjc4l9iUBohw+5QTMVSUpI5X4SPeXm5GNXzCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:00:56.822529Z","bundle_sha256":"5a972c0050509626cf893a07305f1b17ce96f5dd02ffe87f01f91b20d7d68602"}}