{"as_of":"2026-08-13T14:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:26eaa0d5e3f902ffb2b853e8a8c51e9c6b9d00767506bfca394aa24692469900","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T13:40:52.992114Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"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/2411.16064/citation-record","integrity":"/paper/2411.16064/integrity","json":"/paper/2411.16064/citation-record.json","paper":"/paper/2411.16064"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T13:40:54.458551Z","title":"Learning to transfer examples for partial domain adaptation","venue":null,"work_id":"086c4c73-893a-498e-a9ec-846b44b420ff","year":2019},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.611358Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:87360d09e953e2e8d42c578de69993699545b9f32abea8495297a37dcc6b4a2a","observation_id":"6d3ceae3-43bd-4e12-81f2-c385ae182dd2","resolution":{"observed_at":"2026-08-12T13:40:54.471286Z","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":"2026-08-12T13:40:54.434086Z","title":null,"venue":null,"work_id":"8c9fbedd-a955-426c-ac3f-2ca724420d26","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.619650Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:5768132c3e96df3b7dcd70fb8b99ba20b5d2c778d899965043a50743bb2738bf","observation_id":"539d097a-df74-496e-a0ec-6206da53a1fe","resolution":{"observed_at":"2026-08-12T13:40:54.441014Z","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":"2026-08-12T13:40:54.409187Z","title":"A continual learning survey: Defying for- getting in classification tasks","venue":null,"work_id":"0130ec78-d037-46ee-8a32-b4a2cbc92307","year":2021},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.631231Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:833aaecd1f7b5c529c2315dbf63695cff788840059f2261267bc4b11fca4d0df","observation_id":"f0999999-108b-4965-a2cd-207233c67045","resolution":{"observed_at":"2026-08-12T13:40:54.415753Z","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":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-13T02:40:23.887636Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-12T13:40:52.638105Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.638105Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:3c22d9d8ea8c8133f2b9895559e171284f6c0d3756f2800ea1c9169e188c02d9","observation_id":"0a194911-40d7-4b42-aded-ca6301d08453","resolution":{"observed_at":"2026-08-12T13:40:52.638105Z","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":"2026-08-12T13:40:54.377537Z","title":"Caltech-256 object category dataset, 2007","venue":null,"work_id":"31357e56-ba16-4aca-a091-716d44211e9d","year":2007},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.644849Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:9747b2860fa5d72026f5d24b9e7abb40be748d1f58b614efcae11a54f9d275f7","observation_id":"5c728b6e-3288-4f00-9e12-fff045b056c4","resolution":{"observed_at":"2026-08-12T13:40:54.387904Z","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":"2026-08-12T13:40:54.355336Z","title":"Gradient reweighting: Towards imbalanced class-incremental learning","venue":null,"work_id":"a48707cd-3d59-4716-b447-6feda528f14a","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.651587Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:6dd6ad5831e35a0d9568141f0696c8f83fbbd02c7ae9823b67a07cdf587316c9","observation_id":"04b99511-d477-46f6-94bc-dc67f4f47bb9","resolution":{"observed_at":"2026-08-12T13:40:54.361335Z","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":"2026-08-12T13:40:54.329127Z","title":"Class-incremental learning with clip: Adaptive representa- tion adjustment and parameter fusion","venue":null,"work_id":"2d3eadc8-ce20-4961-96c0-f3e7b0df0bfd","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.669999Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:e035360a72dfef91dd62d70a8feab42a90e59be9748ed8fc6687cc61cc0fbd0d","observation_id":"3bd46485-85ef-40e3-8b5e-c801c9e11808","resolution":{"observed_at":"2026-08-12T13:40:54.335517Z","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":"2402.04129","last_updated":"2025-07-09T19:07:40Z","snapshot_observed_at":"2026-08-13T04:25:02.123430Z","submitted_at":"2024-02-06T16:31:11Z","title":"OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04129","snapshot_observed_at":"2026-08-12T13:40:52.675579Z","title":"Ovor: Oneprompt with virtual outlier regularization for rehearsal-free class-incremental learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.675579Z"},"links":{"cited_paper":"/paper/2402.04129","citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:25f6f22c840da75aa200f35ee50a4641c34e9a17accde05ec58563769b2e97d6","observation_id":"2690f810-ce48-46c4-9e3c-85ce1b0553a6","resolution":{"observed_at":"2026-08-12T13:40:52.675579Z","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":"2026-08-12T13:40:54.299571Z","title":"Improved cross-corpus speech emotion recognition using deep local domain adaptation","venue":null,"work_id":"f6ef96a9-8b6d-445b-a2f3-428436eeab5f","year":2023},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.681526Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:21ce8ae8319430a23cd5a8851c6b4dc30fc0f06f2471aaee0d68c25c5614c6f5","observation_id":"0e0f54f4-b199-44c4-91ff-ff50091f76f2","resolution":{"observed_at":"2026-08-12T13:40:54.308593Z","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":"2026-08-12T13:40:52.688153Z","title":"Class- incremental learning by knowledge distillation with adaptive feature consolidation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.688153Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:212f7617ab271ad4e0083a5fa34a07080d92805234c6ca4fe2242599f17da332","observation_id":"1f87a227-943b-425b-946a-6a3c91e10535","resolution":{"observed_at":"2026-08-12T13:40:52.688153Z","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":"2026-08-12T13:40:54.248807Z","title":"C-sfda: A curriculum learning aided self- training framework for efficient source free domain adapta- tion","venue":null,"work_id":"c845bffa-55cd-4927-9d05-8e60d5c7c20d","year":null},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.694062Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:f3b1c756ab9b2e3208c59c7bc8a6974d479830e6e735724218f29cc9c9a8ec45","observation_id":"a556682f-09b5-4fe8-9899-3252099f17fe","resolution":{"observed_at":"2026-08-12T13:40:54.257621Z","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":"2026-08-12T13:40:54.216400Z","title":"Supervised contrastive learning","venue":null,"work_id":"2c082e95-e881-4fd8-b581-f60667833959","year":null},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.702035Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:f537edb183af721d9c927c3ab65887876521c73a21e8d68fe6e3e2b056839e88","observation_id":"ac0f1b23-c640-4374-b6d5-0dd78a0c0199","resolution":{"observed_at":"2026-08-12T13:40:54.223494Z","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":"2026-08-12T13:40:54.169914Z","title":"Class- incremental domain adaptation","venue":null,"work_id":"4f991fc0-5468-4a2d-b575-70c355c44423","year":2020},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.708261Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:5041e74e224b972d3f572445b01c699f3f1481f6583b0084c33d25e498ed5839","observation_id":"792983e1-8773-4350-99fe-312bb5fc6ece","resolution":{"observed_at":"2026-08-12T13:40:54.177304Z","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":"2026-08-12T13:40:54.143164Z","title":"Effective decision boundary learning for class incremen- tal learning","venue":null,"work_id":"7fec5d20-be8d-443e-b605-0f347874161a","year":2023},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.713449Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:25f5e00385defa7060eaa30f8996fca48aa7ac523aaf6fe5350b95c3f8a700e6","observation_id":"00d214f5-2120-4001-b3d3-638b1cc6b9c9","resolution":{"observed_at":"2026-08-12T13:40:54.150137Z","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":"2026-08-12T13:40:54.112804Z","title":"Principal properties attention matching for par- tial domain adaptation in fault diagnosis","venue":null,"work_id":"86bfdd25-9892-48b2-b4f6-56bb2627a6c7","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.718388Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:636d65db664c088495737f2994deede91f67105e907166a97e38ec0f83b6b0e9","observation_id":"dc0c6329-14c0-458f-95f5-9bb9e355e6fe","resolution":{"observed_at":"2026-08-12T13:40:54.122026Z","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":"2026-08-12T13:40:54.089488Z","title":"Prototype- guided continual adaptation for class-incremental unsuper- vised domain adaptation","venue":null,"work_id":"fd61f159-0498-4043-a64a-1736c24ebf23","year":2022},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.726154Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:f06ae3077ce19d78bdd61ad13257f38221ccee9a329e088beb53e6900234a255","observation_id":"95f7a33d-0844-4f1f-aa3d-b36bb8c6651d","resolution":{"observed_at":"2026-08-12T13:40:54.096388Z","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":"2309.15048","last_updated":"2024-03-13T14:24:28Z","snapshot_observed_at":"2026-08-13T10:04:34.709902Z","submitted_at":"2023-09-26T16:25:57Z","title":"Class Incremental Learning via Likelihood Ratio Based Task Prediction","version":4},"cited_work":{"arxiv_id":"2309.15048","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.15048","snapshot_observed_at":"2026-08-12T13:40:53.186591Z","title":"Class Incremental Learning via Likelihood Ratio Based Task Prediction","venue":"cs.LG","work_id":"698cc013-174f-4e98-8bf0-00bf9e908ef5","year":2023},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.737671Z"},"links":{"cited_paper":"/paper/2309.15048","citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:fb097d40205a4cfda43b721ade506f327a57238dc73afa82e5713dc90ae24cea","observation_id":"cf3cec00-95a6-48cc-855e-648d9b08276f","resolution":{"observed_at":"2026-08-12T13:40:53.194174Z","resolver_source":"local_arxiv","status":"verified_exact"},"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":"2026-08-12T13:40:54.066531Z","title":"Guid- ing pseudo-labels with uncertainty estimation for source- free unsupervised domain adaptation","venue":null,"work_id":"325e674b-eaa7-4937-81d3-17244855e3fa","year":2023},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.749098Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:4a25bada4dc8801595ee15c5b07cc02d7e66e33d3ab6c44455e76688c858ae5a","observation_id":"f9239010-c4c7-4726-8221-508bbf3bf772","resolution":{"observed_at":"2026-08-12T13:40:54.074482Z","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":"2408.10046","last_updated":"2024-08-19T14:38:27Z","snapshot_observed_at":"2026-08-12T23:01:23.550451Z","submitted_at":"2024-08-19T14:38:27Z","title":"Exploiting Fine-Grained Prototype Distribution for Boosting Unsupervised Class Incremental Learning","version":1},"cited_work":{"arxiv_id":"2408.10046","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.10046","snapshot_observed_at":"2026-08-12T13:40:53.145730Z","title":"Exploiting Fine-Grained Prototype Distribution for Boosting Unsupervised Class Incremental Learning","venue":"cs.LG","work_id":"c1c6c3d5-37a3-4598-981c-f1d7238784c8","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.766875Z"},"links":{"cited_paper":"/paper/2408.10046","citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:d57afb5585d7adf1fc2d3751165828181aa97b8f44166d203d489466b4a991d9","observation_id":"9c9c8690-7510-4aab-bdce-618a7e1f0f19","resolution":{"observed_at":"2026-08-12T13:40:53.155533Z","resolver_source":"local_arxiv","status":"verified_exact"},"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":"2026-08-12T13:40:54.037031Z","title":"Entity-enhanced adaptive re- construction network for weakly supervised referring expres- sion grounding","venue":null,"work_id":"4fe8b3da-6578-459e-9ea6-57707c53c698","year":2022},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.774202Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:88d8f5018af762f245945a8a8e07091fe663c4a518d79f057e90fdd800efc633","observation_id":"e3c938b9-6827-4895-98cf-4203a6b709e1","resolution":{"observed_at":"2026-08-12T13:40:54.048140Z","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":"2026-08-12T13:40:52.780534Z","title":"Model behavior preserving for class-incremental learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.780534Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:27fc947b154c51608b3c501e23a59cbe2e88ebaee932119d84723a5247354788","observation_id":"febbdc84-ae2c-4e46-aeb1-2c7d009c58cf","resolution":{"observed_at":"2026-08-12T13:40:52.780534Z","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":"2026-08-12T13:40:53.975289Z","title":"Source-free domain adap- tation with domain generalized pretraining for face anti- spoofing","venue":null,"work_id":"49b7369a-872a-481e-9a02-3bab56a21905","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.786690Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:626ec7da22720c9d792f0dcfe889fa6e849eb31455a4aa5976a6d5d61dada142","observation_id":"bf493580-0932-4fee-b48f-cd97f9285319","resolution":{"observed_at":"2026-08-12T13:40:53.985911Z","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":"2026-08-12T13:40:53.949173Z","title":"Diffclass: Diffusion-based class incremental learning","venue":null,"work_id":"028710ae-d0f6-4758-b13b-2e2cc4fdd8fd","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.795323Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:c8fcbb37d23c815917a44f21b567217e8c151743cad4f1d155e3ac820cb9552b","observation_id":"a113b4ff-1246-4eca-888a-4d0fe8d3d71d","resolution":{"observed_at":"2026-08-12T13:40:53.958293Z","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":"2026-08-12T13:40:53.926132Z","title":"Un- derstanding and improving source-free domain adaptation from a theoretical perspective","venue":null,"work_id":"084e3a6b-a1d4-475c-be76-7c09b771e6c7","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.800900Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:d8007e860af0e80cea0b008229c68878f7c9f2a3e52640af33e6c8146eeb1be0","observation_id":"4fc7b50b-b7f3-410d-b257-219252516aae","resolution":{"observed_at":"2026-08-12T13:40:53.932290Z","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":"2026-08-12T13:40:53.895923Z","title":"Efficient test-time model adaptation without forgetting","venue":null,"work_id":"d6e4e00a-a9d1-4c00-9452-effdc1166687","year":2022},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.813874Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:c03d667ddc8dcd0c3b17621e97692c186655b5d217f3b7f08df1058cc5669b39","observation_id":"0b4909cd-25f3-407d-b70c-d80e4b908ed8","resolution":{"observed_at":"2026-08-12T13:40:53.910888Z","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":"2026-08-12T13:40:53.868898Z","title":"Bmd: A general class-balanced multicen- tric dynamic prototype strategy for source-free domain adap- tation","venue":null,"work_id":"05ec3b23-4a98-4449-862e-a307bb215a59","year":2022},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.820713Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:d416de85a3ed232b5d3af187d752faed1a3472fe37bbd1f5797187c42bc30d69","observation_id":"cb14b57a-704a-4bb6-a902-4d286df95f96","resolution":{"observed_at":"2026-08-12T13:40:53.877737Z","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":"2026-08-12T13:40:53.843227Z","title":"Upcycling models under domain and category shift","venue":null,"work_id":"4ad915bf-9479-45f3-9619-d0b5ad81aaff","year":2023},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.826244Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:100b8ea7bc492fc21f9ecca3464f11c38714749f53e2e92e3eb6c6b8357d0b23","observation_id":"c5e75aea-0c6d-4a43-8281-0656ad8672ad","resolution":{"observed_at":"2026-08-12T13:40:53.849984Z","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":"2026-08-12T13:40:53.808834Z","title":"Lead: Learn- ing decomposition for source-free universal domain adapta- tion","venue":null,"work_id":"db411590-e945-45d0-b2f6-83b96386aa27","year":null},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.832096Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:d754c64b2f1521a8cf1f03965feb2f9076d4c9876fcf56ccc9487bf0f3f1ab41","observation_id":"81205774-c024-43b1-bfee-15ae41a0bab8","resolution":{"observed_at":"2026-08-12T13:40:53.816841Z","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":"2026-08-12T13:40:53.777684Z","title":"Fscil-eaca: Few-shot class-incremental learning network based on em- bedding augmentation and classifier adaptation for image classification","venue":null,"work_id":"966a3212-9957-4302-a18c-2c061392a655","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.838257Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:483381e8d0d24391458dc13180449a3bb4a224867512be5e6e325d1ccb25a593","observation_id":"d4897445-edd2-4d46-ad9b-990f5eb3e099","resolution":{"observed_at":"2026-08-12T13:40:53.788527Z","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":"2026-08-12T13:40:52.844774Z","title":"Imagenet large scale visual recognition challenge","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.844774Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:8d7ab2920c233e3ba8998b827d970afba347e91c8b655d31d55d30660abd021b","observation_id":"b3567d28-70dc-4c5d-ad9e-e9dcb572c564","resolution":{"observed_at":"2026-08-12T13:40:52.844774Z","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":"2026-08-12T13:40:53.726546Z","title":"Adapting visual category models to new domains","venue":null,"work_id":"86dfc5f7-1990-45fe-97d0-79e395107ab0","year":2010},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.853214Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:bcfc886b36c8ba773d3af97131d5d698ebc9d8cef87ee468a0d9eeed554ff53d","observation_id":"38e79ff5-7a16-470b-8a0b-ed67f61cc490","resolution":{"observed_at":"2026-08-12T13:40:53.735693Z","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":"2026-08-12T13:40:53.689047Z","title":"A survey on image data augmentation for deep learning","venue":null,"work_id":"fa853c27-572c-4063-8245-2cade1820837","year":2019},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.860838Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:c1ee2b29c1667e8d87662b69553afd1a971fa262817b9ff39cc8b4d73867f4dd","observation_id":"b1900a1b-1913-4be1-b5ba-161cfcfb7f34","resolution":{"observed_at":"2026-08-12T13:40:53.695529Z","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":"2026-08-12T13:40:53.664943Z","title":"Source-free domain adaptation via target prediction distribution searching","venue":null,"work_id":"b3bec3e2-17e0-4f65-82d4-6c9443006f43","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.870231Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:a784db21b72f8f54f8b60edcaeb18d9c4006aecb4cfe272765868746cdb58c45","observation_id":"dc20aa94-424b-480e-b8d8-96c15e01d7b9","resolution":{"observed_at":"2026-08-12T13:40:53.671546Z","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":"2026-08-12T13:40:52.875705Z","title":"Unified source-free domain adaptation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.875705Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:05814fe151ec92b5886dd5746f1c11dd37401d599099a56f01101b07def56f5e","observation_id":"faa0cc57-f421-4a2e-bd6a-1153a06cdbb8","resolution":{"observed_at":"2026-08-12T13:40:52.875705Z","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":"2026-08-12T13:40:53.636309Z","title":"Source- free domain adaptation with frozen multimodal foundation model, 2024","venue":null,"work_id":"1a99a713-54df-471d-a55b-bdc685c64367","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.884567Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:3c1e6e1191d9f9a35d0c93abefcbf96ac252c15b892cfac24e1aa66c1d3e0cb3","observation_id":"7c774acc-931c-4b10-8344-e68793712998","resolution":{"observed_at":"2026-08-12T13:40:53.644267Z","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":"2026-08-12T13:40:53.610879Z","title":"A prototype-oriented framework for unsupervised domain adaptation","venue":null,"work_id":"62784393-9d42-4c98-8436-6c26516e38b5","year":2021},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.898049Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:e6553529838546b77ec7183214152fd5afc15f8e7d22d6f26b8a0ce421315d36","observation_id":"85d25c05-5160-4992-95b4-a0e2307b60bd","resolution":{"observed_at":"2026-08-12T13:40:53.619800Z","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":"2026-08-12T13:40:53.583422Z","title":"Topology-preserving class-incremental learning","venue":null,"work_id":"1f695bfe-4806-4912-a249-303ed396d742","year":2020},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.904348Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:eacd12fc36f8800cbc6949d6ae822bffa0634fbb4dc2888fcee9fb7a4081d387","observation_id":"ebc6c159-1b4e-41b3-981b-9d9ace645024","resolution":{"observed_at":"2026-08-12T13:40:53.589811Z","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":"2026-08-12T13:40:52.910718Z","title":"Transformer-based under- sampled single-pixel imaging","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.910718Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:103669bd2c45cd4235c37b86a846a6fc3d2779664344895cb92d345a6ea65d33","observation_id":"db37bb2d-2ac9-4e92-a773-98f38af8d219","resolution":{"observed_at":"2026-08-12T13:40:52.910718Z","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":"2026-08-12T13:40:53.535694Z","title":"SMART: Syntax-Calibrated Multi-Aspect Relation Transformer for Change Captioning","venue":null,"work_id":"6501d896-49f0-4571-9897-7a7c9b32ba40","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.917207Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:a33c374838187252c694f678837e9482883cc6365cb65cf0629065d9b63a979b","observation_id":"91079f81-fbb6-43a7-896d-e625fc3b11b5","resolution":{"observed_at":"2026-08-12T13:40:53.543491Z","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":"2026-08-12T13:40:53.512850Z","title":"Deep hashing network for unsupervised domain adaptation","venue":null,"work_id":"4efcaee7-f694-4315-ba0c-b79996c5b188","year":2017},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.922348Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:ceffe5635f761d5958f43a64dd3725ad4697b495002942c19664d50814727172","observation_id":"017f8fb9-1ddc-49bf-be51-29be90adeeea","resolution":{"observed_at":"2026-08-12T13:40:53.520133Z","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":"2026-08-12T13:40:53.493377Z","title":"Large scale incre- mental learning","venue":null,"work_id":"d87fe6fc-5426-4aa4-ad33-fc13b423e410","year":null},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.928493Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:fb50274205f767aaf4b8b37e79347ac9c6e19833be520f46267cd21528b2311d","observation_id":"d9e59caf-d563-4749-b20e-bf55f763aa12","resolution":{"observed_at":"2026-08-12T13:40:53.498869Z","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":"2026-08-12T13:40:53.471477Z","title":"Unraveling the mysteries of label noise in source-free domain adaptation: Theory and practice","venue":null,"work_id":"0e7768e4-a6f0-4cd7-9a32-8d8dbd8a57d7","year":2025},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.934399Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:dd1ba4702b710bc83cfeff629b7dc33b0a8dd32def159754d61559f37d66fdc1","observation_id":"f0c4987d-8c4c-4dcd-a5ae-b7cbac0d55d8","resolution":{"observed_at":"2026-08-12T13:40:53.478968Z","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":"2026-08-12T13:40:52.941048Z","title":"Unsupervised cross-media hashing learning via knowledge graph","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.941048Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:aefa7c8a81203f59f078695587fd8d34ac8fe86b667731df805dd9b58b6edd69","observation_id":"0f59d74e-7983-4887-99c6-3829bbaeb363","resolution":{"observed_at":"2026-08-12T13:40:52.941048Z","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":"2026-08-12T13:40:53.427982Z","title":"Inductive state- relabeling adversarial active learning with heuristic clique rescaling","venue":null,"work_id":"421c91ed-7619-408f-8ba2-e4f23ed2ee50","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.946442Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:c8a08d54a1de9eeceb4577c90640c1ba13904b067e8425a4c906670961bf2dae","observation_id":"c0ba3aca-bdf4-4f46-a391-2287acad9a33","resolution":{"observed_at":"2026-08-12T13:40:53.433660Z","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":"2026-08-12T13:40:53.405383Z","title":"Monocular depth estimation on adverse weath- ers with curriculum domain distribution alignment","venue":null,"work_id":"1cb8f276-434b-4600-a917-31468604e60b","year":null},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.953094Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:708ed8bfaa27eee2ba7db73a76b999de2a7a20496c0a02a8b9f4117628082898","observation_id":"77940652-3a1d-4f6a-b932-81d8d7bc1509","resolution":{"observed_at":"2026-08-12T13:40:53.412616Z","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":"2026-08-12T13:40:53.385927Z","title":"Deep guided attention network for joint denoising and demosaicing in real image","venue":null,"work_id":"46dc6437-9c85-408c-9ae9-30ebb8c363ed","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.959419Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:2ef325c7243d6ad016163c1e3613153884da4ac0107cbfe5643b1d76fc8e5634","observation_id":"509a1f35-e6aa-46c3-bb40-86be1b1a85b8","resolution":{"observed_at":"2026-08-12T13:40:53.391521Z","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":"2026-08-12T13:40:53.365516Z","title":"From speaker to dubber: movie dubbing with prosody and duration consistency learning","venue":null,"work_id":"9bc63c78-6a6f-4a9d-90a9-c77f73b6a8ae","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.966227Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:623af8ab2e64a6235ae9c7cc3aef18a05120b876f5a849968226806bd75a9fd2","observation_id":"440df2c9-1e1f-4011-b29d-3f8591cff6f0","resolution":{"observed_at":"2026-08-12T13:40:53.372748Z","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":"2026-08-12T13:40:53.346849Z","title":"Comparing proba- bility distributions with conditional transport","venue":null,"work_id":"720426de-8a89-4f82-87ff-e178c723a1a8","year":null},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.974179Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:4c77c16226c7fcab64f6c8643be26ec89966f48219672f2bf1e9cfbac2d20d29","observation_id":"49b25c8d-9314-4db0-ab13-48fefb0e0364","resolution":{"observed_at":"2026-08-12T13:40:53.351814Z","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":"2026-08-12T13:40:53.320801Z","title":"Gait recognition in the wild with dense 3d representations and A benchmark","venue":null,"work_id":"3b7658e1-9069-4385-812f-f7f1c4a11b88","year":2022},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.980480Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:c7597a4debe113e17f8af6b876d679cbc2702567243007270a75c628aa93f74d","observation_id":"000ca9a4-b1ab-4c99-a266-3e5db01c764e","resolution":{"observed_at":"2026-08-12T13:40:53.328080Z","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":"2026-08-12T13:40:53.292135Z","title":"Source-free domain adaptation with class prototype discovery","venue":null,"work_id":"2d4c1fff-50b1-4fc6-8db0-cfe6df825792","year":2024},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.986058Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:6f4e924f436afe8a65f780ec4c09bddd6674b4d4e3b17a4b1d333c99c324814f","observation_id":"3f3c0051-326d-4b3b-9256-5a0cd992741d","resolution":{"observed_at":"2026-08-12T13:40:53.298396Z","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":"2026-08-12T13:40:53.271883Z","title":"Unsupervised domain adaption harnessing vision-language pre-training","venue":null,"work_id":"479fd552-b73a-40a6-8025-9ff62371ffbc","year":null},"citing_paper":{"arxiv_id":"2411.16064","last_updated":"2025-05-27T12:46:03Z","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation","version":4},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T13:40:52.992114Z"},"links":{"citing_paper":"/paper/2411.16064"},"observation_digest":"sha256:c06cd792b87602a57b687a8429ff49e5ab6bc84ef2f767bd4055000d8a8d8275","observation_id":"51df04b4-7f93-43a2-bf24-41bad207ddea","resolution":{"observed_at":"2026-08-12T13:40:53.277572Z","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":"2411.16064","last_updated":"2025-05-27T12:46:03Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T13:32:53.538867Z","submitted_at":"2024-11-25T03:28:09Z","title":"Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":2,"verified_fuzzy":40},"total_outbound_references":51},"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 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2411.16064."}