{"as_of":"2026-08-16T13:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1c76fdd291a2596bd9672ba30cd228055b6b4f4b109479188f3665d763ec8e93","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T16:54:58.364510Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T16:54:58.198856Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-15T16:54:58.429613Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"cited_work":{"arxiv_id":"2508.19528","doi":null,"metadata_source":"pith","pith_arxiv_id":"2508.19528","snapshot_observed_at":"2026-08-15T16:54:58.429613Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","venue":"eess.AS","work_id":"9fa95545-34d6-4c01-80fc-ea6dba2281e5","year":2025},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.198856Z"},"links":{"cited_paper":"/paper/2508.19528","citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:fdbf65f1b22ca4408a30be5d1005f4370e2663977849beda13a415dad997374f","observation_id":"12e02a36-ccc5-4eaf-a8a4-8935b858b96a","resolution":{"observed_at":"2026-08-15T16:54:58.436921Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2508.19528/citation-record","integrity":"/paper/2508.19528/integrity","json":"/paper/2508.19528/citation-record.json","paper":"/paper/2508.19528"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.952664Z","title":null,"venue":null,"work_id":"af480036-df17-4ce9-8436-8108771764b7","year":null},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.193524Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:cf685b56bd92bff51c38eb6822fd2dee34eef1ce8382b2d1aa4afc4cab288e34","observation_id":"ea797d80-d26f-4d82-914f-33a1798655b0","resolution":{"observed_at":"2026-08-15T16:54:58.957311Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"cited_work":{"arxiv_id":"2508.19528","doi":null,"metadata_source":"pith","pith_arxiv_id":"2508.19528","snapshot_observed_at":"2026-08-15T16:54:58.429613Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","venue":"eess.AS","work_id":"9fa95545-34d6-4c01-80fc-ea6dba2281e5","year":2025},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.198856Z"},"links":{"cited_paper":"/paper/2508.19528","citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:fdbf65f1b22ca4408a30be5d1005f4370e2663977849beda13a415dad997374f","observation_id":"12e02a36-ccc5-4eaf-a8a4-8935b858b96a","resolution":{"observed_at":"2026-08-15T16:54:58.436921Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.937458Z","title":"Dataset We validate our model’s performance using four popular speech separation datasets: WSJ0-2Mix [3], WHAM! [28], WHAMR! [29], and Libri2Mix [30]","venue":null,"work_id":"08c4eabe-2462-4821-a930-d8c93b22bfcd","year":null},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.203927Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:3d195c0cd7951fadd69c9f91e70bbb8f32c7f8a0640aa28492116b38e9d4cad2","observation_id":"4cefdc36-616b-4ddc-9389-326458bc72d3","resolution":{"observed_at":"2026-08-15T16:54:58.942593Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.922392Z","title":"Comparison with previous models We use SI-SNR improvement (SI-SNRi) and SDR improve- ment (SDRi) [33] to evaluate model performance","venue":null,"work_id":"3288f90e-aca3-4026-9c33-6a439ce7e7a1","year":null},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.208752Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:10e89ac033236f62f7c8c4dde50e4d29f1d2f53fd3cf0e941cf02f9dec9dbbb4","observation_id":"a418bfc5-f90e-4351-8141-48cf8bd730d4","resolution":{"observed_at":"2026-08-15T16:54:58.927582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.906103Z","title":"Although previous meth- ods use STFT and downsampling to reduce speech sequence length, the attention module in those still has O(N 2) time complexity","venue":null,"work_id":"8a7d81fd-0249-4816-a0ed-65f77e7ee6f8","year":null},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.213772Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:db4cddfd8b5a23bb3ea14fe442c5fef2f648751b2a5a6fc534106f7bd865a105","observation_id":"18982a38-3d91-44cd-8c3f-bedd5809382a","resolution":{"observed_at":"2026-08-15T16:54:58.912027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.891209Z","title":"Some experiments on the recognition of speech, with one and with two ears,","venue":null,"work_id":"e7a8cf5f-2f20-468a-a7d5-2d89a8a0f48e","year":1953},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.218241Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:5b3094693b050e847d4447658c751cf48213112f0ab94a0e3c52026844fc0703","observation_id":"4d2147b0-c582-4586-b718-ec14f38904b1","resolution":{"observed_at":"2026-08-15T16:54:58.896074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.876361Z","title":null,"venue":null,"work_id":"280b5557-e583-4537-9657-eb3536c3c0ed","year":1994},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.223119Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:2befc668d248386221e66a8927d380795591c23205bef173407328613f59d9e6","observation_id":"ddf76e5c-3b96-4c8d-bb5e-3828714608bf","resolution":{"observed_at":"2026-08-15T16:54:58.880958Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.861440Z","title":"Deep clus- tering: Discriminative embeddings for segmentation and separa- tion,","venue":null,"work_id":"1fee8192-5e8d-4bff-b6c7-7493a24d62ad","year":2016},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.227724Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:d32bf032c47c94fdab818fb943127ce2964e1cb44e6b9c9bf867ed807552acab","observation_id":"b330cdec-5eed-4331-a68d-24d90eef39e3","resolution":{"observed_at":"2026-08-15T16:54:58.866280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.845590Z","title":"Multitalker speech separation with utterance-level permutation invariant training of deep recurrent neural networks,","venue":null,"work_id":"e54a6b8c-e400-439b-9c71-9bf15097ef96","year":1901},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.232547Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:ad3d6435136360e11622977c4ec64521c9d9348ccace0829ca29b73a9a38c084","observation_id":"22ea9c41-9e1c-4b52-a553-9f14027f4920","resolution":{"observed_at":"2026-08-15T16:54:58.850838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.829852Z","title":"Attention Is All You Need In Speech Separation,","venue":null,"work_id":"f06a5fc4-6f82-4065-abb5-e1a069c5c939","year":2021},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.237024Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:31cf720f70d0a60698789c7d012b7b87310b15229dec6a03684c192dead7ac5d","observation_id":"43b3e2a2-3248-44f9-a8ce-f43c77a05e99","resolution":{"observed_at":"2026-08-15T16:54:58.834306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.815049Z","title":"TF-GRIDNET: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation,","venue":null,"work_id":"68b8a859-ed9a-40f0-87b8-2f8cf34a0647","year":2023},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.241904Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:618d475ba6cb37fed69667c5a209d60ff1b182260efc27ccc8460516a8948c15","observation_id":"aecafd82-c8c9-4637-9e02-3eacf2eb4021","resolution":{"observed_at":"2026-08-15T16:54:58.819780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.799955Z","title":"TF-Locoformer: Transformer with Local Modeling by Convo- lution for Speech Separation and Enhancement,","venue":null,"work_id":"5f88ab80-7e07-492e-a33d-5ea5c59f103b","year":2024},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.246271Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:80ebd98541c38ed9ed286051cc9b270d60094655413e96f01f7e23600b1f0977","observation_id":"528127be-dbbd-438d-8ce5-fef6a08500bb","resolution":{"observed_at":"2026-08-15T16:54:58.804947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.785472Z","title":"Conv-tasnet: Surpassing ideal time– frequency magnitude masking for speech separation,","venue":null,"work_id":"8b435a3b-c466-4700-b343-ea011d5322a1","year":2019},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.250754Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:52fef54fa53abb60424999fd19339f6d9a7dda3b8039c5ba6c5c2e0e5bbd94a2","observation_id":"5f427243-2999-4976-9673-a9a1d93a37c4","resolution":{"observed_at":"2026-08-15T16:54:58.790142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.770779Z","title":"Dual-Path RNN: Effi- cient Long Sequence Modeling for Time-Domain Single-Channel Speech Separation,","venue":null,"work_id":"9d97f5e3-0b2b-40c8-91fd-28056525e099","year":2020},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.255201Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:d922ab5c5375d8e8af76203edb763bdbd44346bbda47bbc5c0daec321d465a94","observation_id":"3d0488c6-864e-471d-aad9-0eae342379da","resolution":{"observed_at":"2026-08-15T16:54:58.775646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.259476Z","title":"Long Short-term Memory,","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.259476Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:f7a40a0b1bb02a300b37ad4afd31154fa57db400a91f2a2592246d4028298c77","observation_id":"b3ffafa9-a8b0-409c-9f4e-ff436faa18d8","resolution":{"observed_at":"2026-08-15T16:54:58.259476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.746650Z","title":"Dual-Path Transformer Net- work: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation,","venue":null,"work_id":"4044a8d6-36fa-4dbf-87c9-7154a4181cd0","year":2020},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.263755Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:9e53d9d5acde8d60167aa0c38792740979f836cdd1d69f037b347edd268f2bc9","observation_id":"ad8cbc50-fba6-4ad4-a4c5-42016dca1dcb","resolution":{"observed_at":"2026-08-15T16:54:58.751359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.733261Z","title":"Attention Is All You Need,","venue":null,"work_id":"9a730fc0-d83b-406f-90bb-428b822b0439","year":2017},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.267939Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:ef3ac2319b01b63019daf17ccc8c69eccdea980f7f22b81a38709749c147461d","observation_id":"2b112eac-8883-41e9-ba7c-c98cf5c5a3cf","resolution":{"observed_at":"2026-08-15T16:54:58.737610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.718986Z","title":"Sudo RM -RF: Effi- cient Networks for Universal Audio Source Separation,","venue":null,"work_id":"e63b76eb-87d4-40a0-a90c-7af9ada8c0e1","year":2020},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.272234Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:fb389d5ca2daa77069540bbcf79fecfb0f8465b6113d2e36b5c31725ed3dffd5","observation_id":"6a119972-82c4-4c93-aefe-ca524615d8b4","resolution":{"observed_at":"2026-08-15T16:54:58.723433Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.705269Z","title":"Sandglasset: A Light Multi-Granularity Self-Attentive Network for Time- Domain Speech Separation,","venue":null,"work_id":"bbb0f691-5a68-41c0-9198-05be58552d36","year":2021},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.276493Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:bea5e4c051d381e0d06f16ca119a8dd33867811e936f696f6c0e894f63598a71","observation_id":"a20c7ec9-fef7-4c78-afeb-0529fec98603","resolution":{"observed_at":"2026-08-15T16:54:58.709829Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.691383Z","title":"An efficient encoder-decoder archi- tecture with top-down attention for speech separation,","venue":null,"work_id":"6191658c-5f10-4246-823e-ebb6da1b3f2d","year":2023},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.280734Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:80f8093b529cec802ac10f503c952c686fff3c7c9e272c1010094181dc5b8dff","observation_id":"40506afc-3fb9-41d5-bb5e-188ae755ebe5","resolution":{"observed_at":"2026-08-15T16:54:58.696033Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.677568Z","title":"TIGER: Time-frequency In- terleaved Gain Extraction and Reconstruction for Efficient Speech Separation,","venue":null,"work_id":"c0520246-7c52-4833-8143-827a9479461d","year":2025},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.285321Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:b9e63a3feb534a7bc519e5a837b68c2f788e3fddfa938efae29e56991bbcbd2f","observation_id":"a0b061fb-0f5c-41c5-8113-3b1ffae07187","resolution":{"observed_at":"2026-08-15T16:54:58.682253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.663406Z","title":"ZipEnhancer: Dual-Path Down-Up Sampling-based Zipformer for Monaural Speech Enhancement,","venue":null,"work_id":"569ccf10-863d-4e76-a5ba-11f3b48601aa","year":2025},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.289695Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:28b7e00dfae4c2fe7e5940387394a231ab003bd04b62999d1abe98954a9e5bfd","observation_id":"47a5c179-95ae-4f24-a45b-9b5dfa35addc","resolution":{"observed_at":"2026-08-15T16:54:58.668088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.648912Z","title":"MossFormer: Pushing the Performance Limit of Monaural Speech Separation Using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions,","venue":null,"work_id":"e2445f86-85c3-418e-ab7f-c882f494145b","year":2023},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.293989Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:74f12acb3bdb1a820bb8101bd530a44d3051a38cc6a73c122c27314cf9b4bcf8","observation_id":"021ef93d-9609-4899-80d2-a90e355dc113","resolution":{"observed_at":"2026-08-15T16:54:58.653699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.634830Z","title":"MossFormer2: Combin- ing Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation,","venue":null,"work_id":"b08f0a0f-7b75-47a0-a9dd-fe62fba50a5c","year":2024},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.298362Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:2678e5d8ae87a1ccd74ca1a576fb9903338ca755fe428b2e3c03d030c3bedd10","observation_id":"c9f02299-3837-4b44-941e-0ec5f2cafb5e","resolution":{"observed_at":"2026-08-15T16:54:58.639408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.620480Z","title":"Transformer Quality in Linear Time,","venue":null,"work_id":"14c7244c-8bf9-4f47-ace6-66524f15cf59","year":2022},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.302761Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:4bb8729a2aad214ff9efbd98c6d4e5af29b02271dd498d3909b4d83f922daee6","observation_id":"9a72620f-9b1c-4cda-8066-b4c5d7a8a205","resolution":{"observed_at":"2026-08-15T16:54:58.625296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.605629Z","title":"Trans- formers are RNNs: Fast Autoregressive Transformers with Linear Attention,","venue":null,"work_id":"e07795ee-0190-4699-9aa6-3d7e25941f06","year":2020},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.307016Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:38cea39676b33ada48adb91e9186203a105e55eaecd86ffc78f2728f72b1a382","observation_id":"b8f77adc-a200-4ea8-91bb-2d76088b8a5c","resolution":{"observed_at":"2026-08-15T16:54:58.610412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.591331Z","title":"FLatten Trans- former: Vision Transformer using Focused Linear Attention,","venue":null,"work_id":"432e17cc-5f64-4c56-898d-f4e56e7be1c5","year":2023},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.311766Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:477c28daa8080ce5ece6448ec09b1ef2051331fd5ab1bef87c99220eb94a26d0","observation_id":"4d1b3817-a6d0-4997-82bb-9f8596be92c0","resolution":{"observed_at":"2026-08-15T16:54:58.595946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.577371Z","title":"Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation,","venue":null,"work_id":"b636b177-68ba-468b-a906-f252848cf22e","year":2024},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.315977Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:c95fccd5e290933bc5eb9910c754fc4ad0094b69e2fe761fcbcd32a7e77e8f33","observation_id":"02ef7c37-7747-46f1-b220-26dbde15d2ae","resolution":{"observed_at":"2026-08-15T16:54:58.582199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.561795Z","title":"EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction,","venue":null,"work_id":"b96b7065-87e7-4f37-a480-5a47d10675ab","year":2023},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.320547Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:3183c73668992f1f8b36bfee4f74b59c306630d20e1937e6b96e3bbc4fe094bf","observation_id":"3d5369c3-f721-430a-8e46-87f92048504c","resolution":{"observed_at":"2026-08-15T16:54:58.567050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.546358Z","title":"Rethink- ing Attention with Performers,","venue":null,"work_id":"a76119b3-3e0c-43f8-bb2a-dce4097e5f32","year":2021},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.324909Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:194abf19c0e60656faa08292a80cb4cfc3f18309328068f2bdfc0a0b67dd1b42","observation_id":"84f0e625-1e05-430f-8c1b-8e3f80cf51dc","resolution":{"observed_at":"2026-08-15T16:54:58.550957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.530787Z","title":"A Neural State-Space Modeling Approach to Efficient Speech Separation,","venue":null,"work_id":"b8e86854-7299-4531-8d84-b32eb71533c0","year":2023},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.329253Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:c84c27edea46c159eaf61ca34a7f0e513310518093e23d288c49c5964d944b59","observation_id":"bc822c87-c3c2-4ae3-8cc1-087e2e936a2d","resolution":{"observed_at":"2026-08-15T16:54:58.535785Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.09732","last_updated":"2024-07-13T00:35:21Z","snapshot_observed_at":"2026-08-16T13:34:35.558554Z","submitted_at":"2024-07-13T00:35:21Z","title":"Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.09732","snapshot_observed_at":"2026-08-15T16:54:58.333703Z","title":"Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.333703Z"},"links":{"cited_paper":"/paper/2407.09732","citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:d5592bdfe01826fe9822a87dd15a38b4ebe601c61f2821e667aeafb2cafb84a1","observation_id":"329d0df9-0a19-4e1a-b777-719c675facc6","resolution":{"observed_at":"2026-08-15T16:54:58.333703Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.516231Z","title":"WHAM!: Extending Speech Separation to Noisy Environments,","venue":null,"work_id":"1210f094-788a-4aa1-b8f8-e56b3afe9bbd","year":2019},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.338259Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:592619f2afa21653c2874a27a3ac24a1abe5d1110c39770f8730271914d92837","observation_id":"5ce1d1de-2730-4ce9-84be-8cd86ccd0d7d","resolution":{"observed_at":"2026-08-15T16:54:58.520759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.502136Z","title":"WHAMR!: Noisy and Reverberant Single-Channel Speech Sep- aration,","venue":null,"work_id":"2f220fe5-d793-4f0c-b5ac-f0ae072d363e","year":2020},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.342329Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:c5e10f2c7a4402d89adf8a8343d29f4920b755b2436ebd7c8fc05f99a3666256","observation_id":"b36f8ee8-a4a5-4bca-a23c-dad1f5c0a84c","resolution":{"observed_at":"2026-08-15T16:54:58.507070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.488006Z","title":"LibriMix: An Open-Source Dataset for Generalizable Speech Separation,","venue":null,"work_id":"47fe146b-c045-477c-b1ae-d5742a2a3767","year":2020},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.346540Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:afe9c695b31aedf8041292ec6964652ad9ff04a52c1c6dfa4f751a8ddd66927a","observation_id":"befb543d-3f02-4973-8908-cbba79a5d595","resolution":{"observed_at":"2026-08-15T16:54:58.492699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.350954Z","title":"Lib- rispeech: An ASR corpus based on public domain audio books,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.350954Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:93a96c66b4e064575f0b05872c476d88d6311c853167b9adba3d6697d8534785","observation_id":"8bd4d01e-91b0-415d-90e3-29d0acfd55de","resolution":{"observed_at":"2026-08-15T16:54:58.350954Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.463543Z","title":"ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding,","venue":null,"work_id":"8668a4c7-aff8-4d49-ad05-2dc913f886f7","year":2022},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.355404Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:ae6d1fdb931fb035c95a275012b4e277133228b79d39fb8bce1cd6779dc00fc0","observation_id":"644b40f6-7e5a-4f95-b2e8-edca56eeeb70","resolution":{"observed_at":"2026-08-15T16:54:58.468333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:54:58.447256Z","title":"SDR – Half-baked or Well Done?","venue":null,"work_id":"6b93a9cb-a77d-4894-a54e-a358806da5ef","year":2019},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.360094Z"},"links":{"citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:1bc7bd4711cbf7e42283b8be58646f838ddf952a84a83ffa0bd8224e0f0d6db5","observation_id":"dda4ec6f-4397-45e8-aa41-c336bc277205","resolution":{"observed_at":"2026-08-15T16:54:58.452564Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.05682","last_updated":"2022-10-10T16:36:47Z","snapshot_observed_at":"2026-08-16T12:32:22.985108Z","submitted_at":"2021-12-10T17:25:07Z","title":"Self-attention Does Not Need $O(n^2)$ Memory","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.05682","snapshot_observed_at":"2026-08-15T16:54:58.364510Z","title":"Self-attention Does Not Need O(n 2) Memory,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T16:54:58.364510Z"},"links":{"cited_paper":"/paper/2112.05682","citing_paper":"/paper/2508.19528"},"observation_digest":"sha256:7247eb95d24f5dfcf306db13c24d7a04d9f67dac9c25420c8f9c5ee804313a5a","observation_id":"db3ac104-9294-442e-b71d-195739111adc","resolution":{"observed_at":"2026-08-15T16:54:58.364510Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2508.19528","last_updated":"2025-08-27T02:47:26Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-15T16:48:32.951736Z","submitted_at":"2025-08-27T02:47:26Z","title":"FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":1,"verified_fuzzy":32},"total_outbound_references":39},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2508.19528."}