{"as_of":"2026-08-08T14:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:420c6181256a7795a936c13cd65109a0aee725117e792fb93a8378ae8ee0dc45","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T14:50:00.686605Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2509.23335/citation-record","integrity":"/paper/2509.23335/integrity","json":"/paper/2509.23335/citation-record.json","paper":"/paper/2509.23335"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T14:50:00.546842Z","title":"Curriculum learning","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.546842Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:d03712491f9d858f3c3a9e06ed6fbba3ae41b7a9bc5ece1c41357098b53a3277","observation_id":"971b53a8-7c32-41f1-8d03-057334587bed","resolution":{"observed_at":"2026-08-04T14:50:00.546842Z","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":"2026-08-04T14:50:00.550913Z","title":"Dark experience for general continual learning: a strong, simple baseline","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.550913Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:f2b46adaca98b10e635012bd25d66ec7c753b058eb6548a58821ba78dc8c1bff","observation_id":"9027aca4-80bf-4057-a86c-07446f622c1c","resolution":{"observed_at":"2026-08-04T14:50:00.550913Z","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":"2026-08-04T14:50:00.554335Z","title":"Rebalancing batch normalization for exemplar-based class-incremental learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.554335Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:7f83cb89555c4ce167c9a98ca4961083cd54b83c8140a201d2d8e3ad4504a7e9","observation_id":"13e9702a-235c-487d-ad40-a75d725ca069","resolution":{"observed_at":"2026-08-04T14:50:00.554335Z","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":"2026-08-04T14:50:00.558496Z","title":"Towards calibrated multi-label deep neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.558496Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:64d0fd01d915a1303aeee10ac5fe20dff37ae45c6f2f265179a82d00a34d6c7d","observation_id":"aebedace-10c0-4823-a7e8-ab54c6508884","resolution":{"observed_at":"2026-08-04T14:50:00.558496Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15633","last_updated":"2024-05-24T15:18:27Z","snapshot_observed_at":"2026-07-06T18:19:25.869339Z","submitted_at":"2024-05-24T15:18:27Z","title":"Less is more: Summarizing Patch Tokens for efficient Multi-Label Class-Incremental Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15633","snapshot_observed_at":"2026-08-04T14:50:00.562530Z","title":"Less is more: Summarizing patch tokens for efficient multi-label class-incremental learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.562530Z"},"links":{"cited_paper":"/paper/2405.15633","citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:f377c998518503868c1613919025100e86ab1b0518e52167fd627a45a2ede8d1","observation_id":"4eda4b3a-89c8-4f4d-bc86-64bc659a981c","resolution":{"observed_at":"2026-08-04T14:50:00.562530Z","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":"2026-08-04T14:50:00.566269Z","title":"Knowledge restore and transfer for multi-label class-incremental learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.566269Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:4439cc3dd39f5141f28a7d1014c0ea5b6436e318ef232d63d3a5afb289d13ead","observation_id":"70c473bf-7b8a-40ef-be8c-14672437f551","resolution":{"observed_at":"2026-08-04T14:50:00.566269Z","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":"2026-08-04T14:50:00.570580Z","title":"Podnet: Pooled outputs distillation for small-tasks incremental learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.570580Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:72f86e40f49263cb85d15a26e59f45d37e2b16d33f4ffa645a4b26b37821c0ff","observation_id":"3d462f00-ab3e-46f5-a5b3-127dc334594e","resolution":{"observed_at":"2026-08-04T14:50:00.570580Z","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":"2026-08-04T14:50:00.574362Z","title":"Multi-label continual learning using augmented graph convolutional network","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.574362Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:e68675a025cb9eadd1d1f38a3872538daa70101390d42c6346378ca0184d87d5","observation_id":"ee26a252-4df6-404e-8556-04d58871c76e","resolution":{"observed_at":"2026-08-04T14:50:00.574362Z","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":"2026-08-04T14:50:00.577514Z","title":"Confidence self-calibration for multi-label class-incremental learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.577514Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:4d8fdc0d2e29009cd20691ca764e511afb5574f0414d0fe2b1ffc3917707de6b","observation_id":"df5d108c-47b0-4249-beff-b1a05ab43b8b","resolution":{"observed_at":"2026-08-04T14:50:00.577514Z","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":"2026-08-04T14:50:00.581423Z","title":"Rebalancing multi-label class-incremental learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.581423Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:b192f490bbfd3371e43fef5151e35e454f47d54e11bd0afd27317774b8d78849","observation_id":"fe7ad23a-84b6-42bd-8554-9c6f45ab02ec","resolution":{"observed_at":"2026-08-04T14:50:00.581423Z","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":"2026-08-04T14:50:00.585547Z","title":"The pascal visual object classes (voc) challenge","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.585547Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:081e41cd2f5c12ffc8e4eff097214062012b9e26b95eb59abec1d88ffab3e7d4","observation_id":"4e6f8fbd-b356-44d4-8f17-4cf3ee4c0b6e","resolution":{"observed_at":"2026-08-04T14:50:00.585547Z","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":"2026-08-04T14:50:00.589411Z","title":"Dualcoop++: Fast and effective adaptation to multi-label recognition with limited annotations","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.589411Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:ea920013044b0d64f96a15e79ff49480b32aaba1970a395922fdb24fe9233a4b","observation_id":"2246be1c-2527-4bd7-ab85-c2e3030c3088","resolution":{"observed_at":"2026-08-04T14:50:00.589411Z","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":"2026-08-04T14:50:00.592963Z","title":"Mind the gap: Preserving and compensating for the modality gap in clip-based continual learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.592963Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:1f871929de08295ab67f41794dfcca8726d9806d9194eab05078272fe5c13bd0","observation_id":"ce88d59e-322c-4275-a942-2248347236a7","resolution":{"observed_at":"2026-08-04T14:50:00.592963Z","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":"2026-08-04T14:50:00.596116Z","title":"Ovor: Oneprompt with virtual outlier regularization for rehearsal-free class-incremental learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.596116Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:2987593067a459b202d937329326a041593b45ac8e4a7e097c1ca0e181ea55e5","observation_id":"bb5609b4-2446-41b9-af5d-d04fcbda292b","resolution":{"observed_at":"2026-08-04T14:50:00.596116Z","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":"2026-08-04T14:50:00.599394Z","title":"Imbalanced continual learning with partitioning reservoir sampling","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.599394Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:cd7053b4b469a475086d9cc6249711267d744c9a43c945322e605b27873fc044","observation_id":"ca036244-81cc-4467-aed9-465f2ca837e8","resolution":{"observed_at":"2026-08-04T14:50:00.599394Z","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":"2026-08-04T14:50:00.603577Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.603577Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:6ac62110bc6c240fd888ff1fc51912e7fabaa41de6fa61b1ca4344af42c32d88","observation_id":"0380be24-5bde-4338-a268-9358bbb45244","resolution":{"observed_at":"2026-08-04T14:50:00.603577Z","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":"2026-08-04T14:50:00.606738Z","title":"Overcoming catastrophic forgetting in neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.606738Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:5ddaeff1c20327b60603baaaeea8d07c82cd42b11bde4f16ded8b9e3c8b03f50","observation_id":"f1bfb670-a682-417d-94ac-4c8abefb8633","resolution":{"observed_at":"2026-08-04T14:50:00.606738Z","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":"2026-08-04T14:50:00.609966Z","title":"Learning without forgetting","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.609966Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:a1641203c959012f191e0a35fb5eb51bb99c3038d63dfea53ae11d2683544713","observation_id":"42a07ea9-ba0a-4a99-a7a1-a34f305f1952","resolution":{"observed_at":"2026-08-04T14:50:00.609966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.11469","last_updated":"2022-09-23T08:17:25Z","snapshot_observed_at":"2026-07-06T13:55:30.810818Z","submitted_at":"2022-09-23T08:17:25Z","title":"Optimizing Class Distribution in Memory for Multi-Label Online Continual Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.11469","snapshot_observed_at":"2026-08-04T14:50:00.613209Z","title":"Optimizing class distribution in memory for multi-label online continual learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.613209Z"},"links":{"cited_paper":"/paper/2209.11469","citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:177d8180f63b73e44cf4356708d8d971b72518b05fc3f5abf241aa3da7447d5a","observation_id":"a3193732-eeda-482e-b8e2-bbc5f5a967c2","resolution":{"observed_at":"2026-08-04T14:50:00.613209Z","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":"2026-08-04T14:50:00.617045Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.617045Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:3241035771c6c09bc011b06a0aadeeffa00f901bb6953f2cfccd970ab496f3f7","observation_id":"8754f631-6b64-487a-872e-3dd9d9150d7e","resolution":{"observed_at":"2026-08-04T14:50:00.617045Z","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":"2026-08-04T14:50:00.620584Z","title":"D3former: Debiased dual distilled transformer for incremental learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.620584Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:5db3ed76143045b3b0de585a461a195bb35fd16b13b457194d44a12ff41a422a","observation_id":"f2bb24ee-30d7-4216-a736-66ed64aea08a","resolution":{"observed_at":"2026-08-04T14:50:00.620584Z","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":"2026-08-04T14:50:00.624255Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.624255Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:b0e4a223c8e6ae53b027843b2463d9bc92e2feaac701f90928f603c2f5b2fa76","observation_id":"8b21b759-288e-4d93-b77c-495f3baceea3","resolution":{"observed_at":"2026-08-04T14:50:00.624255Z","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":"2026-08-04T14:50:00.627566Z","title":"icarl: Incremental classifier and representation learning","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.627566Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:d23313fcfbba6fddb9432740776f6796036a2ef2bc4ebd0e66640e36ecbb8036","observation_id":"cf484263-9ac4-4a0e-910e-bef7e1e06562","resolution":{"observed_at":"2026-08-04T14:50:00.627566Z","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":"2026-08-04T14:50:00.631200Z","title":"Experience replay for continual learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.631200Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:291fb2b9a25aef22c3d48517020697ab1f5ee9c4187b8f448f2cc1e4822efef6","observation_id":"9e76a9d6-d050-4709-8738-8bfb9ae429d0","resolution":{"observed_at":"2026-08-04T14:50:00.631200Z","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":"2026-08-04T14:50:00.634987Z","title":"Progress & compress: A scalable framework for continual learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.634987Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:f6ff70a779b849174e3cfb6aa3e707aa00261a00f3a8fe47874909241191bfed","observation_id":"470d1e4e-64e1-41df-8647-68c8a098818d","resolution":{"observed_at":"2026-08-04T14:50:00.634987Z","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":"2026-08-04T14:50:00.639146Z","title":"Coda-prompt: Continual decomposed attention-based prompting for rehearsal-free continual learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.639146Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:15884e44e8884175ba83166231c0a11bf7b7d628952216d2e01f4dd70cf6f12a","observation_id":"b3974361-45fa-4b2c-831e-826e4cd18c56","resolution":{"observed_at":"2026-08-04T14:50:00.639146Z","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":"2026-08-04T14:50:00.643222Z","title":"Topology-preserving class-incremental learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.643222Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:9350e82f49920a6779492c23bf8736b82bc2f46aa9bc3df13ff31a54cb200943","observation_id":"51bfddcc-1b17-4182-a33e-b18e09664fa3","resolution":{"observed_at":"2026-08-04T14:50:00.643222Z","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":"2026-08-04T14:50:00.646967Z","title":"Cut out and replay: A simple yet versatile strategy for multi-label online continual learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.646967Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:794a83ab091202b353c2856841d43bd10691d0d82eca0a8dad90f3859c2de795","observation_id":"5bc98fe9-b5a5-4fda-b39f-57fd78344eef","resolution":{"observed_at":"2026-08-04T14:50:00.646967Z","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":"2026-08-04T14:50:00.651176Z","title":"Dualprompt: Complementary prompting for rehearsal-free continual learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.651176Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:cb547158e844a9c376b8a4a35892df23b79dd1a3fcf2cfc76e9d00b326f13674","observation_id":"34d7a0c0-d7e9-4d76-af82-fbc626eb6bbf","resolution":{"observed_at":"2026-08-04T14:50:00.651176Z","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":"2026-08-04T14:50:00.654679Z","title":"Learning to prompt for continual learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.654679Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:fc4cd505719fe5e720aa94687dab4b865fed10f0b84600761b12ec1488ffad5c","observation_id":"cd8003bb-f5f1-4359-89ab-caa45e697c0d","resolution":{"observed_at":"2026-08-04T14:50:00.654679Z","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":"2026-08-04T14:50:00.658320Z","title":"Large scale incremental learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.658320Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:148e6da693caec03a060903469e7f1539548481da80e067783e36926821687d4","observation_id":"e537517d-7c9d-47db-99ab-53c4fd9bac8b","resolution":{"observed_at":"2026-08-04T14:50:00.658320Z","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":"2026-08-04T14:50:00.661602Z","title":"Specifying what you know or not for multi-label class-incremental learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.661602Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:ea12f1a523e91b623c58c1d067d281d3ab0570966f8cce91059eb84d6693c91a","observation_id":"b1516dcb-02b8-4da5-800e-5ec89596f6df","resolution":{"observed_at":"2026-08-04T14:50:00.661602Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.00340","last_updated":"2025-01-03T03:22:32Z","snapshot_observed_at":"2026-07-06T20:15:03.658292Z","submitted_at":"2024-12-31T08:23:45Z","title":"Dynamic Prompt Adjustment for Multi-Label Class-Incremental Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.00340","snapshot_observed_at":"2026-08-04T14:50:00.664698Z","title":"Dynamic prompt adjustment for multi-label class-incremental learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.664698Z"},"links":{"cited_paper":"/paper/2501.00340","citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:ee0f97d3ecbac0cbfc2fa09d72c89685664e450db4dc09d00614f6a31dc588a5","observation_id":"c3d6efd3-a54b-4c4a-aca5-2d3e862d13ee","resolution":{"observed_at":"2026-08-04T14:50:00.664698Z","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":"2026-08-04T14:50:00.668170Z","title":"Few-shot class-incremental learning via class-aware bilateral distillation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.668170Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:7c3de45cc79a5a341b3bae79e36393f2fb3e5888b1b2e7fd3facf7bf5d26dc10","observation_id":"ddd1f744-5af6-4fd1-bf8e-455fb289e72d","resolution":{"observed_at":"2026-08-04T14:50:00.668170Z","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":"2026-08-04T14:50:00.671360Z","title":"Few-shot class-incremental learning by sampling multi-phase tasks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.671360Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:2d5a1c747087ffe9581f2154dfc749081124a98a6abf61b0196443952cb299c3","observation_id":"36806599-e544-4493-82f5-debb0b0cad8e","resolution":{"observed_at":"2026-08-04T14:50:00.671360Z","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":"2026-08-04T14:50:00.674675Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.674675Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:634e565ab126470cfed263fb5fbaf67b497ef4e7754b7d054c383f212dd0da71","observation_id":"cd4cba41-e77e-4b06-ac77-0f60e09254a6","resolution":{"observed_at":"2026-08-04T14:50:00.674675Z","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":"2026-08-04T14:50:00.679378Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.679378Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:1ff9703faec96451a5a1ac6a4e8124a3031d905c7804d95430f8200130707068","observation_id":"9813b4b1-11ab-4916-924d-3bda5a9385f5","resolution":{"observed_at":"2026-08-04T14:50:00.679378Z","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":"2026-08-04T14:50:00.683075Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.683075Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:d8f45a1cacd115201bf70f5d76b116293b30d97d83fa199b5681f1671a1e1e42","observation_id":"8ad7b49e-7714-4dfa-917b-a9301c3b9c9a","resolution":{"observed_at":"2026-08-04T14:50:00.683075Z","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":"2026-08-04T14:50:00.686605Z","title":"=5' 7&o6ؒv 9 Ӵe ̙ ͸0k 5;|H݇d VRR R8u!5uU n 5 eQJnr /- Գ[P ? X>Z 1W^ M@nl t!->NteUZ I R 﫰:3 skQ Tx","venue":null,"work_id":null,"year":2046},"citing_paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","version":3},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-04T14:50:00.686605Z"},"links":{"citing_paper":"/paper/2509.23335"},"observation_digest":"sha256:c3ae538bbff43b75205b19686c5ca4cd6509d23d2ac89174cf43af5f1d637d35","observation_id":"f0d7f097-cc89-46a3-a59f-47bb47461c4e","resolution":{"observed_at":"2026-08-04T14:50:00.686605Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.23335","last_updated":"2026-08-03T07:54:22Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T23:28:16.959828Z","submitted_at":"2025-09-27T14:39:43Z","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":38,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":39},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2509.23335."}