{"as_of":"2026-08-13T18:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bc6caf3edd81c6b034a8d3170342247a4cc2057785892fd94d52447ccf3fc410","coverage":[{"denominator":49,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":49,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T22:35:57.775062Z","state":"measured"},{"denominator":49,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":49,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.21440/citation-record","integrity":"/paper/2506.21440/integrity","json":"/paper/2506.21440/citation-record.json","paper":"/paper/2506.21440"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:05.751357Z","title":"Long-range acoustic detection and localization of blue whale calls in the northeast pacific ocean,","venue":null,"work_id":"a1393d83-847f-49e9-b409-35dc3b80d6a0","year":1998},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:54.760335Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:6ffdd97139bf6f928bd4ee85a0281dec375653a39bc72d408171afee145c2090","observation_id":"d8d66137-5b6c-46bd-aad6-666ca30aa8cc","resolution":{"observed_at":"2026-08-06T22:36:05.833721Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:05.532184Z","title":"ECG arrhythmia classification using STFT-based spectrogram and convolutional neural network,","venue":null,"work_id":"ecdeb9a5-a0b9-4203-a864-2341a82d0d71","year":2019},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:54.820525Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:79e4a167ec3a8946f6b56111c0ec74c88a15cec7988edb67845097820b08a2c6","observation_id":"f19c6400-66af-4aeb-ba35-70cc1396baef","resolution":{"observed_at":"2026-08-06T22:36:05.636559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:05.343144Z","title":"A multi-order probabilistic approach for instantaneous angular speed tracking debriefing of the CMMNO14 diagnosis contest,","venue":null,"work_id":"4f9d345e-441b-4c02-aa77-5ec335f99bae","year":2016},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:54.868401Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:a4d78e7bcf73269d38bd0258fc5917349e1c75d1698e9ba300d3428f76dee7fe","observation_id":"8d46ed2b-b821-418a-b8f2-a1fd8b37c895","resolution":{"observed_at":"2026-08-06T22:36:05.427035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:05.237351Z","title":"Ast: Audio spectrogram trans- former,","venue":null,"work_id":"3b6bb324-18ec-4611-82c4-61b92861428e","year":2021},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:54.906124Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:a8ebae119f8b4bb0ba56468adcc52ad719e935ec127b7444bcf69e22afcc248d","observation_id":"2ca572da-0d19-4c46-bedd-286d8e8940c7","resolution":{"observed_at":"2026-08-06T22:36:05.283344Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:05.034650Z","title":"Unsupervised speech en- hancement with diffusion-based generative models,","venue":null,"work_id":"24a2c9bc-184f-4d47-9873-ce86a4dddfa8","year":2024},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:55.005961Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:9b6fd744f665c3cc8c7f615b9f92a90b1adf53690ea73f0995b545d3975098d4","observation_id":"5d89c422-9405-42ae-a87e-2bf69ba086c4","resolution":{"observed_at":"2026-08-06T22:36:05.136679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:04.841947Z","title":"Improved musical onset detection with convolutional neural networks,","venue":null,"work_id":"4029a6e0-c383-430b-a885-c3b2adaa5ced","year":2014},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:55.105969Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:f86778c4906439deadc4d5b7bc0d908a1789a50bc4bde29f5702fba7379d34f8","observation_id":"678bfdb0-bc5e-43e6-be94-41960deee8db","resolution":{"observed_at":"2026-08-06T22:36:04.936272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:04.652906Z","title":"Specaugment: A simple data augmentation method for automatic speech recognition,","venue":null,"work_id":"af29a4c1-61d8-42c4-abb2-05b4153f7c3c","year":2019},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:55.196487Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:92687c9fd9882d9853d1cf49655691d96d74c19e057b227df8365c11b7aae9d7","observation_id":"17b83789-7e8b-4034-aad8-a1615174f904","resolution":{"observed_at":"2026-08-06T22:36:04.723944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.03600","last_updated":"2022-08-30T16:07:25Z","snapshot_observed_at":"2026-08-13T17:38:55.756474Z","submitted_at":"2021-11-05T16:37:45Z","title":"Hybrid Spectrogram and Waveform Source Separation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.03600","snapshot_observed_at":"2026-08-06T22:35:55.277373Z","title":"Hybrid spectrogram and waveform source separation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:55.277373Z"},"links":{"cited_paper":"/paper/2111.03600","citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:112f6eaf39f3209a2232e0e66ae2c0cfb1b600c1e6e0625224c42be87b08b8d3","observation_id":"a5fd26cf-af15-4a80-8015-0be482e44190","resolution":{"observed_at":"2026-08-06T22:35:55.277373Z","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":"2026-08-06T22:36:04.361035Z","title":"Introduction to digital speech processing,","venue":null,"work_id":"e947e100-e99c-46a9-a487-4bf263f5fbeb","year":2007},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:55.350557Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:95810e445fb7d33eb375133e3dbe244e5baf457f8752d57e980b79c35708e6bb","observation_id":"d8e7eee8-1dd5-4911-bd4d-0e657e70d315","resolution":{"observed_at":"2026-08-06T22:36:04.506356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:04.189627Z","title":"The role of window length and shift in complex-domain DNN-based speech enhancement,","venue":null,"work_id":"6c64d973-e4d7-4fd6-b15f-c5670c3a13eb","year":2022},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:55.399261Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:12b50c803242f088f01d5c8a268a712f3e376cd3365de637fd99e8fa03f91396","observation_id":"1e47fd29-faac-4a74-94fb-7ef45da07147","resolution":{"observed_at":"2026-08-06T22:36:04.284190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:04.008355Z","title":"An empirical study on analysis window functions for text-independent speaker recognition,","venue":null,"work_id":"6f8a2f12-f94e-4a25-80c3-365096906bdc","year":2023},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:55.486121Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:f132560eee1efb02abe1b06ebd08a1ca1874dcc769e66029c7a43e0fd27f07e0","observation_id":"4b49cfb5-eac5-4069-8460-5ded91a69121","resolution":{"observed_at":"2026-08-06T22:36:04.105290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:03.892739Z","title":"Deep learning: Methods and applications,","venue":null,"work_id":"fd1a097c-55af-48bf-872d-9e42c4d775cf","year":2014},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:55.544541Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:b544f06db1df63bd0074b13e815752a25cac22744d6466b1a67ed793d481b5a2","observation_id":"9e531a25-6433-4768-a70c-7f75df162ceb","resolution":{"observed_at":"2026-08-06T22:36:03.955580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:03.733919Z","title":null,"venue":null,"work_id":"7363ce7c-c065-4d21-a9f2-358b5d459cdc","year":2014},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:55.629391Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:8679def1c80ca440211b11d7e183c76223ab30a8fa1c9fc39bfaf146b1b27810","observation_id":"eb1923b0-4e19-4a68-a864-00aa5fbc663a","resolution":{"observed_at":"2026-08-06T22:36:03.815133Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:03.473597Z","title":"Havin and B","venue":null,"work_id":"419ab6cf-2ce0-451c-b402-487e13f8e632","year":2012},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:55.718466Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:2b80d3f1ebc1a9474dd7ea906998eaa36727a82563657d9fa27a3ff9627d2c21","observation_id":"315911f8-694d-4339-8ea5-5b358ee69c9d","resolution":{"observed_at":"2026-08-06T22:36:03.627731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:03.284808Z","title":"A differentiable short-time Fourier transform with respect to the window length,","venue":null,"work_id":"f1bb8f9d-de7a-4490-906b-60bdf377af78","year":2022},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:55.789007Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:bb696bfb52da45f9a78fcdb1202cf03ae6cac3a992a25712360f9f68903b08cf","observation_id":"bbebbdcb-6ff9-45d2-bc0d-00e2afeecc02","resolution":{"observed_at":"2026-08-06T22:36:03.377531Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:03.136201Z","title":"Differentiable adaptive short-time Fourier transform with respect to the window length,","venue":null,"work_id":"85adbfe7-e934-4016-9c5b-a7c35ba3be48","year":2023},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:55.841542Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:7cf0d7d2d6d27190e48338941d7c8cd43208dbf0794370e3dadcdb4a670f7e00","observation_id":"a74981e7-e25f-4126-b310-41252360ae0c","resolution":{"observed_at":"2026-08-06T22:36:03.208901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:02.963268Z","title":"Differentiable short-time Fourier transform with respect to the hop length,","venue":null,"work_id":"1d880eb3-c1f9-41bc-99ba-3c1d0a8e7e88","year":2023},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:55.931116Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:26096812d8d747252a44c75b0d3f7922d7c59e8e9ecdec6d555ca012e359b4b3","observation_id":"1bafa9cc-5a1c-4e09-a4dd-35290a367d00","resolution":{"observed_at":"2026-08-06T22:36:03.041232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:02.823589Z","title":"The backpropagation algorithm,","venue":null,"work_id":"c3934eb3-fd91-4a9b-9699-50ba07a58927","year":1996},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:55.977804Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:751a9a64d64dfccce3b67948f3e7c5a29e89372251817abf906c418a5fab72d7","observation_id":"e565c8c3-b4c8-4f69-b886-285943f1ee2f","resolution":{"observed_at":"2026-08-06T22:36:02.853203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:02.672433Z","title":"Backpropagation neural networks: a tutorial,","venue":null,"work_id":"2a4c99e7-1e32-4f97-b791-e902c6df4f49","year":1993},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.080947Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:4ab44831d9cb49ec85f3b9fdb49c8c54b4f97be9883a61df39187bafb4022716","observation_id":"7e9a5b32-23a9-4581-b7c3-b2f48792c3b5","resolution":{"observed_at":"2026-08-06T22:36:02.753472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:56.148274Z","title":"Deep learning,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.148274Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:475fdd91655a834f086bb938a0e61a7f60e65bed18dba74f8087df30ada7d009","observation_id":"fcbde913-7eea-47bd-8c70-69a8955af852","resolution":{"observed_at":"2026-08-06T22:35:56.148274Z","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":"2026-08-06T22:36:02.461162Z","title":"Adaptive short-time Fourier analy- sis,","venue":null,"work_id":"485e4d81-24eb-40e0-a511-776491730d7d","year":1997},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.205482Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:9fe0c70a53ccd40b226db6f37b559bebc40de82679c37c5b5383d2ee39cef38c","observation_id":"5b692e09-5c36-46c5-940d-a11f72d39a17","resolution":{"observed_at":"2026-08-06T22:36:02.537580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:02.303152Z","title":"Variable short-time Fourier transform for vibration signals with transients,","venue":null,"work_id":"32c7a738-90e3-48e6-a417-b4f2bbe5c260","year":2015},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.262361Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:46bceeaf7887c41aeb7cd724cfd2b4e8fac3344f954dc500bc07bce306b6ca28","observation_id":"400433fd-8060-4d44-80dc-fbf1c0714e2a","resolution":{"observed_at":"2026-08-06T22:36:02.386644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:02.140509Z","title":"Improved instantaneous frequency estimation using an adaptive short-time Fourier transform,","venue":null,"work_id":"a11e98b2-f3ff-4be4-9631-058ab93e4a92","year":2000},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.320182Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:895b9c9bd532fcae139a6c3a70a0aedc7282af1151dae010cf7d0bff186f9c91","observation_id":"ed81cf3e-8266-4837-a5d4-6da8c53cf7ca","resolution":{"observed_at":"2026-08-06T22:36:02.224627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:01.984026Z","title":"Time-frequency representation based on an adaptive short-time Fourier transform,","venue":null,"work_id":"65129c49-853d-400f-b3a4-f6681dae1553","year":2010},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.404020Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:9c692ea285312a72f0b28cf84b635e0406c0263afb6ad8b4c0cf1f343297ed7b","observation_id":"3b4d1597-8a0d-4376-81fe-6c4f7cdd733c","resolution":{"observed_at":"2026-08-06T22:36:02.059532Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:01.803244Z","title":"STFT with adaptive window width based on the chirp rate,","venue":null,"work_id":"e14844ef-0430-469f-901f-a5f1202975c3","year":2012},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.457241Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:a34c1281ac21483e5dad722e6e8833bd37baf3c212d4e9a66ba7c9c31d851310","observation_id":"448f36f6-2cff-4adc-9dda-03c707d48b81","resolution":{"observed_at":"2026-08-06T22:36:01.905377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:01.651322Z","title":"The- ory, implementation and applications of nonstationary Gabor frames,","venue":null,"work_id":"7f9c257b-eb35-469b-87d0-1a5f2c2a62c8","year":2011},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.519568Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:23e4b12b64a3197d6695e7ba20d0a49839f3774561e3621408f6fef56be761e5","observation_id":"46d90514-f17e-4081-8fa0-face7e527a54","resolution":{"observed_at":"2026-08-06T22:36:01.733345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:01.506478Z","title":"Optimizing short-time Fourier transform parameters via gradient descent,","venue":null,"work_id":"7e58f718-6e36-40e4-ab6c-13f102c5a027","year":2021},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.550650Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:e4acf2a00046492651c627c666baf2a4bfc976a50f82cf907cb032b0a256af70","observation_id":"9591660a-5571-495f-8d4d-f11a2a330330","resolution":{"observed_at":"2026-08-06T22:36:01.586427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:01.252195Z","title":"Differentiable short-time Fourier transform window length selection driven by cyclo-stationarity,","venue":null,"work_id":"044d7314-84c8-4d12-92f4-630778d96e00","year":2023},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.633436Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:ffca33bb4f89d13ad046e578e9f1825245fd4dc22a6ad922c84326d327434796","observation_id":"e241df2a-2e39-4c59-b120-e8835dd36f10","resolution":{"observed_at":"2026-08-06T22:36:01.414396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:01.102208Z","title":"Idsn: A one-stage interpretable and dif- ferentiable stft domain adaptation network for traction motor of high- speed trains cross-machine diagnosis,","venue":null,"work_id":"72167ac9-eb9a-4e36-998d-298ffaf86cee","year":2023},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.685499Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:6a49b3f1ef26c8acadf41b45fa18084a5c03bb767b73efd9d0ef8f00f78bb9db","observation_id":"e2dd33db-7c50-4e71-a247-4207172c50b8","resolution":{"observed_at":"2026-08-06T22:36:01.169750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:00.900796Z","title":"A new method for the numerical analysis of non-stationary signals,","venue":null,"work_id":"87803041-f177-40cb-88ea-66cb872e1501","year":1976},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.759420Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:d4bc149757d0700a0fdf1a7ff36a7d0ab6f6dc9bd966ecb6a53d558d6f619403","observation_id":"0376b890-6832-48e7-a3d4-eefa3eb3d34f","resolution":{"observed_at":"2026-08-06T22:36:00.999442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:00.696432Z","title":"Analysis of time-varying signals with small BT values,","venue":null,"work_id":"1eb36c76-f4c0-4003-b0ab-bb44e04dacad","year":1978},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.804806Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:03c56dd2b8224e870e43496c84191912d1a93407cbbc7785e9a5266cbe54e043","observation_id":"9b4f5039-c8f3-42d7-9745-68401cba8b08","resolution":{"observed_at":"2026-08-06T22:36:00.795987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:00.212349Z","title":"Time frequency reas- signment: from principles to algorithms,","venue":null,"work_id":"9a7b9dc7-0eb5-427d-9d61-acdd5dca962a","year":2018},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.926265Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:c64354196c42fa95a104768e9c3708b267e5a10ef29cd34f54501f8a19be1d33","observation_id":"43bc1212-524b-4791-9fa2-dcd440c36e3f","resolution":{"observed_at":"2026-08-06T22:36:00.345255Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:36:00.426903Z","title":"Improving the readability of time-frequency and time-scale representations by the reassignment method,","venue":null,"work_id":"0e810c57-bff4-4101-a827-434ba95d6247","year":1995},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:56.955275Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:28759ff11c2db1b9cbe90e3fb9afe94faa80b02e98acad8608e8a14a8b322b48","observation_id":"bbf28343-e2e8-4111-a296-a1f0e67dfbd9","resolution":{"observed_at":"2026-08-06T22:36:00.538627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:59.967702Z","title":"Time-frequency reassignment and synchrosqueezing: An overview,","venue":null,"work_id":"60659132-c906-411f-90ba-1f470f56fef2","year":2013},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.014775Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:c1a93e4413bf897b96e5dd2993829279221d1a7623fc3eba52dcca4c5d64e531","observation_id":"095e04a9-8105-4d34-91fa-a0bbfc35213c","resolution":{"observed_at":"2026-08-06T22:36:00.057990Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:59.776961Z","title":"Synchrosqueezing-based recovery of in- stantaneous frequency from nonuniform samples,","venue":null,"work_id":"8aaf61f8-91c3-40c8-b673-5b87de9b9d06","year":2011},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.063374Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:dca0d10fe66a6ab7076303ca5c1a3705392396dd76e949708ead1d30d1be395d","observation_id":"cade316b-1057-4e60-8416-0f79489108b5","resolution":{"observed_at":"2026-08-06T22:35:59.879382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:59.594384Z","title":"The Fourier-based syn- chrosqueezing transform,","venue":null,"work_id":"f5199b3a-7a61-4ae8-974c-acbd566d9fdb","year":2014},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.095478Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:e64177e1271421534a4c5300a8d8c0825d942eed1314cbea9c624bb9b2dbb5f4","observation_id":"284ddf13-a548-4331-bc53-e72c569d8c7e","resolution":{"observed_at":"2026-08-06T22:35:59.697437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:59.465952Z","title":"The synchrosqueez- ing algorithm for time-varying spectral analysis: Robustness properties and new paleoclimate applications,","venue":null,"work_id":"ce3ed1c0-d93f-4d6b-af4b-544573ba2834","year":2013},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.157411Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:22af28117c4c1f4b240e88e66c6814c00068f483ca914d22ee7a629c660efa70","observation_id":"904b1724-fb27-4eb3-b798-5bfa467bf493","resolution":{"observed_at":"2026-08-06T22:35:59.520059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:59.288743Z","title":"Second-order synchrosqueezing transform or invertible reassignment? towards ideal time-frequency representations,","venue":null,"work_id":"5b0edebb-44dc-48b9-8036-bd8d2773b70e","year":2015},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.218072Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:fc110d95c3f42063bdf51a213d31b44d71776717bfa2a10a9198303909c25446","observation_id":"a383aa52-a8a5-4c6e-88f2-e105c72716cb","resolution":{"observed_at":"2026-08-06T22:35:59.368553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:59.102146Z","title":"Theoretical analysis of the second-order synchrosqueezing transform,","venue":null,"work_id":"ca7e1c72-667f-4288-a266-0e42c7c846cb","year":2018},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.265210Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:9af866d640d82df2525ac0957fe7749792ca4f182e8e13b16b7a39567ee00945","observation_id":"a460f62c-5e59-4f88-99e1-d22b2d3eaa4a","resolution":{"observed_at":"2026-08-06T22:35:59.167541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:58.941673Z","title":"Adaptive short-time Fourier transform and synchrosqueezing transform for non-stationary signal separation,","venue":null,"work_id":"111a081a-308f-4f55-9f4a-bc1a45cc5bd7","year":2020},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.311515Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:a82187b7e504e032462a73189397aa7823218859805a6596b58b08010fae6e70","observation_id":"29068388-8deb-4e55-b4ce-564007e16c3c","resolution":{"observed_at":"2026-08-06T22:35:59.008708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:58.725331Z","title":"Recursive versions of the Levenberg-Marquardt reassigned spectrogram and of the syn- chrosqueezed STFT,","venue":null,"work_id":"b1b9b55f-f99c-4d83-a737-f1c9d11c3f76","year":2016},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.364426Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:29323f78ff1bd8d5ab2e5680bbf9408538454953fd73e76598452d57fa0b162e","observation_id":"68d44049-fbf1-4843-9edf-095924d99f0c","resolution":{"observed_at":"2026-08-06T22:35:58.789446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:58.557452Z","title":"Adaptive synchrosqueezing transform with a time-varying parameter for non-stationary signal separation,","venue":null,"work_id":"719e7a3b-145e-43f8-b984-ce70a5b37dd5","year":2020},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.416071Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:be0bffd79e8681dc5ea001a99b325ce6af22f183568ce747bfcd37ffb98a18b5","observation_id":"f40a7aba-d1ae-45fd-a2e0-242abc45ce33","resolution":{"observed_at":"2026-08-06T22:35:58.671870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:58.434951Z","title":"Novel short-time fractional Fourier transform: Theory, implementation, and applications,","venue":null,"work_id":"b8542ad2-de0c-4147-806a-0b69864dbd77","year":2020},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.478126Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:5cc44057299278c42f66f9eb19b648e11670d9e6e281d3753af99c4d2b4e1b0c","observation_id":"662dfdcb-ef0e-4799-8c65-74aa3b6c4c91","resolution":{"observed_at":"2026-08-06T22:35:58.499159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:58.290077Z","title":"Synchrosqueezing-based short-time fractional Fourier transform,","venue":null,"work_id":"66875096-ac60-4394-ba3e-b76db2e9cf23","year":2023},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.520315Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:95aab58fe797455dd20cfa74fa520827c1ab8ae13b95da35848e68ade7dc91c8","observation_id":"a5266c94-efdd-4b30-978e-d85c852d33a1","resolution":{"observed_at":"2026-08-06T22:35:58.339643Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:57.569953Z","title":"Backpropagation through time: what it does and how to do it,","venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.569953Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:cb0e66a4eb4617a839d3065ea043e535533945ab0f52a10250fc9692556ed032","observation_id":"2e517e34-2afc-48ce-8572-dd085cfdacb6","resolution":{"observed_at":"2026-08-06T22:35:57.569953Z","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":"2026-08-06T22:35:58.175983Z","title":"Measuring time-frequency information content using the R ´enyi entropies,","venue":null,"work_id":"7635e881-eb71-4270-8d70-a0c0a7c091ca","year":2002},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.627540Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:d1dd610d9fd2025622265b6c5b9fbf49977cf5990c88d2e9a159ea32a48bd4e8","observation_id":"caa6bd3e-fb18-4b0d-a224-0ff3f55a05bd","resolution":{"observed_at":"2026-08-06T22:35:58.204933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:58.059087Z","title":"On the use of R ´enyi entropy for optimal window size computation in the short-time Fourier transform,","venue":null,"work_id":"b8659dc6-795a-49a5-a2fe-a61bbe1ff28a","year":2020},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.668598Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:4e5e4a8de41e80d00da96006b1038385378fbe6b22163d071d2682e59bfa84f0","observation_id":"f9d78cd1-00ab-4301-8ff8-abc60ee73f6a","resolution":{"observed_at":"2026-08-06T22:35:58.107214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:57.985753Z","title":"Nonlocal operators with applications to image processing,","venue":null,"work_id":"1bb979e4-94ce-4728-81a6-9e5051a62c07","year":2009},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.736623Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:3070e3369fc965a3efb057c5e4e7578659fe1203e2a65082ce6532b8d598ef7d","observation_id":"afc5ad08-9e92-4098-a021-e139de2b9055","resolution":{"observed_at":"2026-08-06T22:35:58.039061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-06T22:35:57.883083Z","title":"Speech emotion recognition from spectrograms with deep convolutional neural network,","venue":null,"work_id":"bc9e2651-2d74-4d28-880f-84773ac8a326","year":2017},"citing_paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T22:35:57.775062Z"},"links":{"citing_paper":"/paper/2506.21440"},"observation_digest":"sha256:fb0f8e15d3f04617525971d3db16a43c3fce5f53b0089f1728891b2a40736c24","observation_id":"04453969-dab3-4f6c-a0f2-6b10a94d6742","resolution":{"observed_at":"2026-08-06T22:35:57.923376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.21440","last_updated":"2025-06-26T16:24:27Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-06T22:22:43.101765Z","submitted_at":"2025-06-26T16:24:27Z","title":"Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":0,"verified_fuzzy":45},"total_outbound_references":49},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:2506.21440."}