{"as_of":"2026-08-18T04:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7da3a1020a5cb4117e5dccb157f9a86c7f797afe2f22e67f464745f2083b7f45","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":10,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":10,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":10,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":10,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T21:28:18.679903Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-18T13:41:25.344405Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.18961","last_updated":"2024-04-29T05:23:10Z","snapshot_observed_at":"2026-08-18T01:32:38.750799Z","submitted_at":"2024-04-29T05:23:10Z","title":"Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.18961","snapshot_observed_at":"2026-08-12T11:45:59.004958Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.17936","last_updated":"2026-06-30T03:40:16Z","snapshot_observed_at":"2026-08-15T17:47:15.670229Z","submitted_at":"2024-11-26T23:18:32Z","title":"Stealthy Multi-Task Adversarial Attacks","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-12T11:45:59.004958Z"},"links":{"cited_paper":"/paper/2404.18961","citing_paper":"/paper/2411.17936"},"observation_digest":"sha256:6b3b9e89ed96c816a600d04a8ed44b8734682d5fff4542558b7dc0441b880856","observation_id":"c18e216a-a7e9-4c69-b2cb-004ac878b532","resolution":{"observed_at":"2026-08-12T11:45:59.004958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.18961","last_updated":"2024-04-29T05:23:10Z","snapshot_observed_at":"2026-08-18T01:32:38.750799Z","submitted_at":"2024-04-29T05:23:10Z","title":"Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.18961","snapshot_observed_at":"2026-08-11T05:57:06.693783Z","title":"Unleashing the power of multi- task learning: A comprehensive survey spanning tra- ditional, deep, and pretrained foundation model eras","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.17023","last_updated":"2024-12-22T13:58:12Z","snapshot_observed_at":"2026-08-17T18:28:38.650229Z","submitted_at":"2024-12-22T13:58:12Z","title":"Parameter-Efficient Interventions for Enhanced Model Merging","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:06.693783Z"},"links":{"cited_paper":"/paper/2404.18961","citing_paper":"/paper/2412.17023"},"observation_digest":"sha256:bc03a643d25c0c28e5e3f8a70e20ee6f5722a7313ece1190ec091ccf68a39517","observation_id":"1120ca73-18d7-4870-ba37-2d4e6685ed1a","resolution":{"observed_at":"2026-08-11T05:57:06.693783Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.18961","last_updated":"2024-04-29T05:23:10Z","snapshot_observed_at":"2026-08-18T01:32:38.750799Z","submitted_at":"2024-04-29T05:23:10Z","title":"Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.18961","snapshot_observed_at":"2026-08-10T18:53:50.756157Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.10945","last_updated":"2025-08-06T06:47:04Z","snapshot_observed_at":"2026-08-15T00:46:03.529876Z","submitted_at":"2025-01-19T04:56:55Z","title":"Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond","version":3},"reference_index":215,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:50.756157Z"},"links":{"cited_paper":"/paper/2404.18961","citing_paper":"/paper/2501.10945"},"observation_digest":"sha256:38b83b6374310c80f0302967d3e377ebd6fc756f3b1cd11c065ac639adcbfe07","observation_id":"60ea414f-d84f-42a2-9742-aaebf73c4a3d","resolution":{"observed_at":"2026-08-10T18:53:50.756157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.18961","last_updated":"2024-04-29T05:23:10Z","snapshot_observed_at":"2026-08-18T01:32:38.750799Z","submitted_at":"2024-04-29T05:23:10Z","title":"Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.18961","snapshot_observed_at":"2026-08-09T21:34:28.373059Z","title":"Unleashing the power of multi-task learning: A comprehensive survey spanning traditional, deep, and pre-trained foundation model eras","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.19067","last_updated":"2025-05-21T12:59:55Z","snapshot_observed_at":"2026-08-15T06:06:50.004082Z","submitted_at":"2025-01-31T11:53:16Z","title":"From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T21:34:28.373059Z"},"links":{"cited_paper":"/paper/2404.18961","citing_paper":"/paper/2501.19067"},"observation_digest":"sha256:97c182bc8ddd23dc8d875ec4058248d9c50cb6290164ee2c81e94ee46cf2b3a4","observation_id":"82f123e3-0247-471d-96b6-d323c7dbe9de","resolution":{"observed_at":"2026-08-09T21:34:28.373059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.18961","last_updated":"2024-04-29T05:23:10Z","snapshot_observed_at":"2026-08-18T01:32:38.750799Z","submitted_at":"2024-04-29T05:23:10Z","title":"Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.18961","snapshot_observed_at":"2026-08-09T20:39:54.063636Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.19316","last_updated":"2025-03-21T12:51:02Z","snapshot_observed_at":"2026-08-18T01:32:51.398976Z","submitted_at":"2025-01-31T17:12:53Z","title":"Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference Resolution","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-09T20:39:54.063636Z"},"links":{"cited_paper":"/paper/2404.18961","citing_paper":"/paper/2501.19316"},"observation_digest":"sha256:487b60191be9861491ec2779425a5d3f878b10af5f56b959cdb21e5c559a6fb4","observation_id":"ef7ca6de-4c62-4626-8a12-d6d72e8974aa","resolution":{"observed_at":"2026-08-09T20:39:54.063636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.18961","last_updated":"2024-04-29T05:23:10Z","snapshot_observed_at":"2026-08-18T01:32:38.750799Z","submitted_at":"2024-04-29T05:23:10Z","title":"Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.18961","snapshot_observed_at":"2026-08-15T21:28:18.679903Z","title":"arXiv preprint arXiv:2404.18961 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.09829","last_updated":"2025-05-14T22:15:41Z","snapshot_observed_at":"2026-08-15T21:20:59.540878Z","submitted_at":"2025-05-14T22:15:41Z","title":"BoundarySeg:An Embarrassingly Simple Method To Boost Medical Image Segmentation Performance for Low Data Regimes","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T21:28:18.679903Z"},"links":{"cited_paper":"/paper/2404.18961","citing_paper":"/paper/2505.09829"},"observation_digest":"sha256:975506fd52bd10eaec712d3f77aed05c60ea7905c09a5440526fe49cc50ba74b","observation_id":"655b9283-b192-4ed8-8b5e-90796d5fa81b","resolution":{"observed_at":"2026-08-15T21:28:18.679903Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.18961","last_updated":"2024-04-29T05:23:10Z","snapshot_observed_at":"2026-08-18T01:32:38.750799Z","submitted_at":"2024-04-29T05:23:10Z","title":"Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.18961","snapshot_observed_at":"2026-08-06T18:35:19.042575Z","title":"Unleashing the power of multi- task learning: A comprehensive survey spanning traditional, deep, and pretrained foundation model eras","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07883","last_updated":"2025-07-15T22:07:45Z","snapshot_observed_at":"2026-08-17T06:02:44.551345Z","submitted_at":"2025-07-10T16:06:02Z","title":"SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T18:35:19.042575Z"},"links":{"cited_paper":"/paper/2404.18961","citing_paper":"/paper/2507.07883"},"observation_digest":"sha256:e630caafda554c59155fc6726d3d82d961f13b3363c8fa31777a3a319b5415dd","observation_id":"8ef62c0a-4e19-4369-8c3a-cd2f698647d9","resolution":{"observed_at":"2026-08-06T18:35:19.042575Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.18961","last_updated":"2024-04-29T05:23:10Z","snapshot_observed_at":"2026-08-18T01:32:38.750799Z","submitted_at":"2024-04-29T05:23:10Z","title":"Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras","version":1},"cited_work":{"arxiv_id":"2404.18961","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.18961","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unleashing the power of multi- task learning: A comprehensive survey spanning traditional, deep, and pretrained foundation model eras","venue":null,"work_id":"a2e18da9-24df-4dc0-8bf4-e6a5b8e49739","year":2024},"citing_paper":{"arxiv_id":"2509.19602","last_updated":"2026-04-25T01:29:24Z","snapshot_observed_at":"2026-08-12T23:41:29.324027Z","submitted_at":"2025-09-23T21:51:04Z","title":"Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-18T13:41:05.981163Z"},"links":{"cited_paper":"/paper/2404.18961","citing_paper":"/paper/2509.19602"},"observation_digest":"sha256:27686fb3373fcce30689869d62c4408d90c60d08cc79c37b6dca4f61b349fb82","observation_id":"0c82c02b-2987-4871-a904-3b09477e5c5a","resolution":{"observed_at":"2026-05-18T13:41:25.348027Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.18961","last_updated":"2024-04-29T05:23:10Z","snapshot_observed_at":"2026-08-18T01:32:38.750799Z","submitted_at":"2024-04-29T05:23:10Z","title":"Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras","version":1},"cited_work":{"arxiv_id":"2404.18961","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.18961","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unleashing the power of multi- task learning: A comprehensive survey spanning traditional, deep, and pretrained foundation model eras","venue":null,"work_id":"a2e18da9-24df-4dc0-8bf4-e6a5b8e49739","year":2024},"citing_paper":{"arxiv_id":"2511.10834","last_updated":"2026-04-18T05:36:05Z","snapshot_observed_at":"2026-08-17T17:34:19.788398Z","submitted_at":"2025-11-13T22:36:20Z","title":"EarthSight: A Distributed Framework for Low-Latency Satellite Intelligence","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-17T21:50:17.098331Z"},"links":{"cited_paper":"/paper/2404.18961","citing_paper":"/paper/2511.10834"},"observation_digest":"sha256:fa92a26f6adbf9a2cf54e8444b9d2f1767d534fb4fbaaa5870944e6e6693e8c8","observation_id":"b2bf6144-67a4-4d12-8896-0a8a62e8b1b6","resolution":{"observed_at":"2026-05-17T21:50:19.383592Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.18961","last_updated":"2024-04-29T05:23:10Z","snapshot_observed_at":"2026-08-18T01:32:38.750799Z","submitted_at":"2024-04-29T05:23:10Z","title":"Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras","version":1},"cited_work":{"arxiv_id":"2404.18961","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.18961","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unleashing the power of multi- task learning: A comprehensive survey spanning traditional, deep, and pretrained foundation model eras","venue":null,"work_id":"a2e18da9-24df-4dc0-8bf4-e6a5b8e49739","year":2024},"citing_paper":{"arxiv_id":"2605.09355","last_updated":"2026-05-10T06:09:32Z","snapshot_observed_at":"2026-08-17T03:28:42.939335Z","submitted_at":"2026-05-10T06:09:32Z","title":"FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-05-12T04:14:04.151375Z"},"links":{"cited_paper":"/paper/2404.18961","citing_paper":"/paper/2605.09355"},"observation_digest":"sha256:4814f062af0bd82779827edf5f7438948f91daf806bd87d2ed3ac10964aa31f8","observation_id":"5daba6f5-a624-4255-a9ad-63b846591a0d","resolution":{"observed_at":"2026-05-12T06:31:25.513883Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2404.18961/citation-record","integrity":"/paper/2404.18961/integrity","json":"/paper/2404.18961/citation-record.json","paper":"/paper/2404.18961"},"outbound":[],"paper":{"arxiv_id":"2404.18961","last_updated":"2024-04-29T05:23:10Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T01:32:38.750799Z","submitted_at":"2024-04-29T05:23:10Z","title":"Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 10 inbound Pith citation observations for arXiv:2404.18961."}