{"as_of":"2026-08-10T03:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1fb699f707e124f1e402cb37814023a67023d257356414a10392bd19b1259ab4","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":"2026-07-15T14:35:11.756852Z","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":"2026-08-09T06:31:02.800959+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/2603.05576/citation-record","integrity":"/paper/2603.05576/integrity","json":"/paper/2603.05576/citation-record.json","paper":"/paper/2603.05576"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"X-Vectors: Robust DNN Embeddings for Speaker Recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:4eec734143a6a9d75b4270cbc2d6fd3be184eecc9292cbf1dc0ce571a39ed41a","observation_id":"f17c9905-9f61-46fb-8a21-400a0fbf5e1b","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Ecapa-tdnn: Em- phasized channel attention, propagation and aggregation in tdnn based speaker verification,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:bba3352b090439418d6fa7c0cc32f18ecc67d0e03faa2dbf3ce26bc9e7547194","observation_id":"5fba192e-a6ee-4174-8cf4-f870c7831376","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Hubert: Self-supervised speech representation learning by masked prediction of hidden units,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:e0456690f514b36c2f967b18e5971e47afd40d5d7aa0ff0cd34db70ccedc31b8","observation_id":"623c63e5-3f36-458c-8090-078b96ad277e","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"WavLM: Large-Scale Self-Supervised Pre- Training for Full Stack Speech Processing,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:a8df0425557a1b5b8739e1535688d0cb3a00be748945e2d0c4beb356f6b96932","observation_id":"eeed3424-4b86-4f3d-b7e4-115b03a7708f","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Unsupervised TTS Acoustic Modeling for TTS With Conditional Disentangled Sequential V AE,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:ef8507338042a33b1d671b82459d5406f6c46ca0c0647ba4ee3b0b0f5de18493","observation_id":"5775d35d-7f31-4f4c-a8fa-921b60452382","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Disentangling Speech Representations Learning With Latent Diffusion for Speaker Verification,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:cf35f423a54237c674a9922318c784de97654c8ee261dc7fbff46187101ad8f2","observation_id":"fc511d1e-61e0-4f16-beea-83b3d6511e9c","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Rose,Forensic Speaker Identification","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:206e1af017a44c5260b1e4df1f584d60d13d73d7681bb64bca2cf65f79b3b9c3","observation_id":"67389dc9-a967-4fb7-8c5b-95c5a7ad02d4","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Disentangled Representation Learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:53b128733a91824325d9bdf181e93d6f55a4e91e9be9ee5152e4b0986cb0f06d","observation_id":"64bc1add-2d8c-4de4-a5b9-94784a6ba974","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Auto-encoding variational bayes,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:9477260c0d07d050d4e3cb1738a6aca6c2e3cc2d9c29b1971d748a401385e94d","observation_id":"1f5d34b3-ccd6-4002-983a-908f5238236b","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Challenging common assumptions in the unsupervised learning of disentangled representations,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:1617eb2a8fd71a66901f387061cc78adeac94be4a3bb8c6b9f2c4ea326fd6deb","observation_id":"b48c6a76-55fb-4884-8fed-c865134be390","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Neural discrete representation learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:560c9e164523e1f83b5a3ba69f89c144e31e606133fa2ddb40f179807601457f","observation_id":"5ac53122-99ad-4465-b7b9-4cdc15b0ab00","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Unsupervised learning of disentan- gled and interpretable representations from sequential data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:a453e98a69977e95342986cd682e530ef5791638e65f0b1007db3c63f02f41bd","observation_id":"1c975ed3-75b7-4101-ab78-f85ea1529322","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Disentangled Sequential Autoencoder,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:4ced8a8831a64c3d3d8580ee051ffa8b632784af547d0898b5051d25d6da7686","observation_id":"f23d198c-c996-4b85-8e58-7359e1c4d907","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Hamiltonian Systems and Transformation in Hilbert Space,","venue":null,"work_id":null,"year":1931},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:ea677fa5bb75f28450393c3a13072a04b80f7de2144847846f018ed1c36f69f0","observation_id":"adc47abf-2842-42d6-9ee7-6b11a4e9365e","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Spectral analysis of nonlinear flows,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:32b5b2f6e3a055fc2909d7f7ee6b1c32e010b8267c115273feb4300311ea88e9","observation_id":"7c3d4179-8a6d-4a2b-b0e7-beba6f8f9574","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1607.08022","last_updated":"2017-11-06T14:21:43Z","snapshot_observed_at":"2026-08-05T08:35:49.218794Z","submitted_at":"2016-07-27T10:23:00Z","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.08022","snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Instance Normalization: The Missing Ingredient for Fast Stylization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"cited_paper":"/paper/1607.08022","citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:b2e2acbf14e99ab695355711ebe9b1ff0c1f3df9d1279b92cabdef27af753680","observation_id":"bc19f7d5-db05-4d79-b3a5-f835fceeb9c5","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"One-shot voice conversion by separating speaker and content representations with instance normalization,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:f748ff6152f353ee8b224f1760764bd8d084a709b50e71cba20a59c7e4512a5e","observation_id":"0e275bc6-7a01-4bb1-b834-83b40292cd6e","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Again-vc: A one- shot voice conversion using activation guidance and adaptive instance normalization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:f4764bf78278458778ffc1a2e44b1d2221b9bed122f76a3b56c22ad47bff4a2c","observation_id":"b99db861-6465-418b-abf4-b83c1ea063bb","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Unsupervised Representation Disentanglement Using Cross Domain Features and Adversarial Learning in Variational Au- toencoder Based V oice Conversion,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:ae53e5841aaa4d5a6cbfd0729a84c318f8eb69614e1e7434e5038967cd7a9ed7","observation_id":"f7737f2b-74b3-46e0-9bd1-91f5a3aeb97b","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"SpeechTripleNet: End-to-End Disentangled Speech Representation Learning for Content, Timbre and Prosody,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:86989014a1641e2923b51da9fb37503728ef5191d4b3ba73250942704a7f93a9","observation_id":"43c97271-79ed-485a-87d0-d70da681a6b3","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Disentangling prosody and timbre embeddings via voice conversion,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:5f6e910d5c4e821586197fd6fee5532396a805f0ec745fef32eb5d304beaa1d3","observation_id":"be26720b-2f1a-4ee6-8e05-f5dd5a9efaf6","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Robust Disentangled Variational Speech Representation Learning for Zero-Shot V oice Conversion,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:90f1f16b6836a8f6cec4ae083e359ef99906e564f0e596a107ad7760ae8b012e","observation_id":"ffe8eef6-99ef-402c-8f5a-91540a892168","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Contrastively Disentangled Sequential Variational Autoencoder,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:a80aa31228c68c965b48dcec5e145cd653a780101b8ba8ab9771a629befdf16a","observation_id":"df8e660c-b5be-4d99-8e77-8c9047eecd73","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Unifying One-Shot V oice Conversion and Cloning with Disentangled Speech Representations,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:0eddd66536409fe4b70d57987d4dd029d4ec29691b897d3c7b24b57c204b53d3","observation_id":"ecbc9515-f0c9-481f-892f-395a9681a5f8","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Dynamic mode decomposition of numerical and experi- mental data,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:ed751d0035ac30d3af6ceb410a7d7cc35ded80fed9ca2b44e84eed62ca086e03","observation_id":"85d0dec8-5dff-4801-847a-e85fb8acada1","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"A Data–Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:1ec342d411b748e583b23e28922c2e3481c308a27a8d1c1b2280a4d9e56accb3","observation_id":"22bb37bd-60a4-4e91-998c-8881cee8671d","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Characterizing and correcting for the effect of sensor noise in the dynamic mode decomposition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:196f4ffddf2b02493ffa8ef634c82eb084a28211c16f209b7330cd412484bf82","observation_id":"c2f48d12-f73b-4068-a823-9f1535ff9e3c","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Modern koopman theory for dynamical systems,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:c9efdb5ba7db18a72e8fcc1f8310fa33134fa1a16fe88b2c05f099715f1ddd34","observation_id":"31f6e844-2167-4de3-b0ef-572f1802b466","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Learning Koopman invariant subspaces for dynamic mode decomposition,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:203299664c33ca111d12e80a67884735da189dfd9e624072cdd780cc6441d106","observation_id":"3490f646-3ae2-441f-b465-6dbf8ecac51c","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Deep learning for universal linear embeddings of nonlinear dynamics,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:41429a2341cda6aacf64ccca6324d982701eaa50b21ec1ceae0718d321b91c78","observation_id":"0d154e1d-0367-4289-8ec5-218567a3752e","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Forecasting sequential data using consistent koopman autoencoders,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:0bc371896a214a7db232b0efb7063ae355db31e2aa926ff2667a03543e1e93cb","observation_id":"ee7c9db0-da4c-4801-8f3b-37d7704cd249","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Transformers for Modeling Physical Sys- tems,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:47185640029146774a76e7575dd5282add9bd77dbdaf2984a9c024c823fcc511","observation_id":"4f7f68f4-cb2e-458a-ae1c-1722be1c2809","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:11dac1edde146409d297fbf66390c35212a3bf8bb893a2846e7ae7d00f46fdb1","observation_id":"1d95c038-8f33-4e3a-9f57-d21164184e5f","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Multifactor Sequential Disen- tanglement via Structured Koopman Autoencoders,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:fa4c381d2045984f1babc717186c8266c7333e7e91084929c573948ebbffe60e","observation_id":"652aa5a3-a932-40f7-92f1-4132881a0309","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:3cf460d1727d6a3936ba8883ad7c197fc9b376378fea1d8a931ce586f7924722","observation_id":"99aa1075-d47c-4753-902e-9d6f35847311","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Koopman Neural Forecaster for Time Series With Temporal Distribution Shifts,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:c9c6ee1cdd2dc42f37923f3807d075a9833a070d9feda85df0234cc6f405e969","observation_id":"1ba7fff0-501e-4c99-a9d3-806a1447677d","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Linearly recurrent autoencoder networks for learning dynamics,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:2251d624aab21ab71b399b7efe78ce06805fbe4190ee77b6ce4ca12af44eec01","observation_id":"d521d101-8e58-48eb-8249-236e40733d21","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Compressed dynamic mode decomposition for background modeling,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:01e165955a8a1f6246892441c4a42f7e16976c8c6a1cea2c62c7bacd1f580df2","observation_id":"f1b6f2ac-f9d1-42a3-894f-27f404b13d6e","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Long Short-Term Memory,","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:e752ea94d025e5bdd9024fa741160bbe5ba662cedc422193fd387405003b1a76","observation_id":"cfae428b-7b0e-4054-8c05-bc570058d1e4","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Deep Residual Learning for Image Recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:3adca88128656bb4d7edbadba1dffda4a85829cfd3f22f88dd22f1d7c98daea8","observation_id":"14d7c903-e290-4fe6-9a97-f91ec6dc1476","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.02304","last_updated":"2017-05-05T17:10:16Z","snapshot_observed_at":"2026-07-06T05:41:28.253263Z","submitted_at":"2017-05-05T17:10:16Z","title":"Deep Speaker: an End-to-End Neural Speaker Embedding System","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.02304","snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Deep Speaker: an End-to-End Neural Speaker Embedding System,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"cited_paper":"/paper/1705.02304","citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:d68bc27d275c893464117e0b189f0942f799ae29fc386f12e1a8b37d93cc5b68","observation_id":"8840aeb3-9015-4d16-b448-11505e7e4622","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Instance-based temporal normalization for speaker Verification,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:6d5951c38c1cfb023a70eaf435269a589702e407c52cf4913d12c753c9bea0c7","observation_id":"f5f6caf4-d0fa-426e-9389-717888fe2560","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:8395f90b065cdde1006d91153163027cef83a1e8221720f2d63d5b717fd992a7","observation_id":"fef5723d-b356-4373-b057-7197c4836731","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Decoupled Weight Decay Regularization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:999db2b656c6c0648d3054b4083dad9ce87c2d551fe3abb2a3742a3f8ccd5e85","observation_id":"073545da-2087-45a8-96c5-b63d62eb0099","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR V oice Cloning Toolkit (version 0.92),","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:cb57fd3ec25b6a5845cd7a694dbe28039d2e849eb9d34e37ce9851c45049a7dc","observation_id":"dccba8d7-687b-47b1-99ea-5b15541ed272","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"TIMIT Acoustic-Phonetic Continuous Speech Corpus,","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:f5df22e2b9d12e5983b3432ef8f12b7f73bf85ae7e21c47bbf352bc17700e5fe","observation_id":"b0f7bf02-0220-49d6-8bae-032a71e54986","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"WebRTC voice activity detection,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:99209fb2c6c2d15efeae3ef274a47ec034203cd636e1502c6c99f8c4c6843b1e","observation_id":"aee7ec53-e770-4c7b-b872-0b4fa1044c8f","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Visualizing Data using t-SNE,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:213b368d914eefd3d8ee0470a0dc1bef64e80207889a2e403d186b381e87abde","observation_id":"7b9a4587-d357-4db0-84e1-6b749f2258bc","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T14:35:11.756852Z","title":"Transformers in speech processing: Over- coming challenges and paving the future,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-15T14:35:11.756852Z"},"links":{"citing_paper":"/paper/2603.05576"},"observation_digest":"sha256:1cc95855c8d7dc14ed5680d408949c56e0cc426ac67be56e13cb3b6431196669","observation_id":"46b1a4e3-5260-4688-9ce7-16aa4ee514aa","resolution":{"observed_at":"2026-07-15T14:35:11.756852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.05576","last_updated":"2026-07-13T14:32:23Z","latest_version":3,"primary_category":"cs.RO","snapshot_observed_at":"2026-07-16T23:19:33.351648Z","submitted_at":"2026-03-05T17:14:10Z","title":"Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":49,"verified_exact":0,"verified_fuzzy":0},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:2603.05576."}