{"as_of":"2026-08-09T19:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:379a149d9d9d8edbf1b99896408717636d1469ee5a2c7323f0d13f549c13bc02","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T15:55:33.530330Z","state":"measured"},{"denominator":54,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":54,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.14725/citation-record","integrity":"/paper/2507.14725/integrity","json":"/paper/2507.14725/citation-record.json","paper":"/paper/2507.14725"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1908.04742","last_updated":"2019-10-29T18:45:10Z","snapshot_observed_at":"2026-08-09T16:46:22.940536Z","submitted_at":"2019-08-11T21:16:44Z","title":"Online Continual Learning with Maximally Interfered Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.04742","snapshot_observed_at":"2026-08-06T15:55:28.085440Z","title":"Online continual learning with maximally interfered retrieval, 2019 a","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:28.085440Z"},"links":{"cited_paper":"/paper/1908.04742","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:3b1f4a68e620628957bc9cec08cac418635e8890fbfff9d674556960d6c685a6","observation_id":"aaf4e3bc-b302-44ce-8ff0-90b97b8340a5","resolution":{"observed_at":"2026-08-06T15:55:28.085440Z","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":"2026-08-06T15:55:39.356615Z","title":"Gradient based sample selection for online continual learning","venue":null,"work_id":"b10f6824-d475-413c-bd8c-d432a95f5817","year":2019},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:28.148286Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:39d3b54332713f806fe57e96b33effd61815d1c8fa60d2a3fbb2b12e4c6817c3","observation_id":"7abaae1b-7e97-403c-9dfb-79c21248690c","resolution":{"observed_at":"2026-08-06T15:55:39.385143Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:39.184662Z","title":"Rainbow memory: Continual learning with a memory of diverse samples","venue":null,"work_id":"6bc7b35d-47fb-4748-9acb-e5098473781c","year":2021},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:28.222995Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:35b992fc3884c39ce4cad7f292ea3a10b896773c56b3dcf482ff7707e148ac5f","observation_id":"3de7c274-7350-4da9-90e9-8085b9943cda","resolution":{"observed_at":"2026-08-06T15:55:39.258314Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:38.963042Z","title":"Selecting representative data sets","venue":null,"work_id":"f507442a-944f-4467-9c95-1cb4f8344558","year":2012},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:28.293392Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:72bfcf1129cc14b4e374776923ce74bd384599197726fc05e7b1c0ef8cce2d77","observation_id":"e9f5c47a-0b60-4a74-b1b1-a435ff72d8e4","resolution":{"observed_at":"2026-08-06T15:55:39.052117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/978-3-030-01252-6_33","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:03:56.115653Z","title":"Dokania, Thalaiyasingam Ajanthan, and Philip H","venue":"Lecture notes in computer science","work_id":"0e57f547-0ec0-48e9-8c7d-0a680b9a2045","year":2018},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:28.401406Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:0fa95419a56a7b04f291bca6ef0b98ca29e34c42384f80cd097c2f6a7c7cd8b4","observation_id":"922c372d-0e75-44f0-aa12-0934ad6ed8a0","resolution":{"observed_at":"2026-08-06T15:55:34.717393Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00420","last_updated":"2019-01-09T11:11:47Z","snapshot_observed_at":"2026-07-06T07:18:30.039631Z","submitted_at":"2018-12-02T16:39:19Z","title":"Efficient Lifelong Learning with A-GEM","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00420","snapshot_observed_at":"2026-08-06T15:55:28.475645Z","title":"Efficient lifelong learning with a-gem","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:28.475645Z"},"links":{"cited_paper":"/paper/1812.00420","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:e84ec87484341748ddde72361ccefc3475d9c629bfb48437f6d336516343db7f","observation_id":"68e4af7f-4cfa-4526-a7fc-fb10a733857f","resolution":{"observed_at":"2026-08-06T15:55:28.475645Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.11416","last_updated":"2022-12-06T21:39:48Z","snapshot_observed_at":"2026-07-06T14:08:18.855958Z","submitted_at":"2022-10-20T16:58:32Z","title":"Scaling Instruction-Finetuned Language Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.11416","snapshot_observed_at":"2026-08-06T15:55:28.546400Z","title":"Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:28.546400Z"},"links":{"cited_paper":"/paper/2210.11416","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:e3c9e4a15d1ef204aec7d807a57b955e733106c250a09af4c6c3eddae36e3c10","observation_id":"f9ef4a1b-f78c-4ce9-8f7d-26367ff795f4","resolution":{"observed_at":"2026-08-06T15:55:28.546400Z","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":"2026-08-06T15:55:38.736955Z","title":"Episodic memory in lifelong language learning","venue":null,"work_id":"58948585-7dd3-4a8a-9642-48cbe39ef06e","year":2019},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:28.618295Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:fc8d6e7d1b7deb07a31540a2a0a37fe1e184c8f0ca4012923865596764941188","observation_id":"65d0145c-2b28-4196-8fa0-dfa74b61f5b7","resolution":{"observed_at":"2026-08-06T15:55:38.829295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:38.411947Z","title":"Parameter-efficient fine-tuning of large-scale pre-trained language models","venue":null,"work_id":"6f09fab8-eb5a-48da-a8d1-bfbaeaeded29","year":2023},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:28.697092Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:1f35d627372602718fb46444943b9b92fa77ba7d8f35bdc603b627df7c26b458","observation_id":"f76dd274-6bb3-4c58-b4dc-35cf032225c8","resolution":{"observed_at":"2026-08-06T15:55:38.600490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:38.077878Z","title":"Dytox: Transformers for continual learning with dynamic token expansion","venue":null,"work_id":"520704e5-6904-4d8c-abd3-93a97a36e15f","year":2022},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:28.768103Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:7fb1e29e2be2bc27fa24f7c9e908245d62f4186d472f7b2aab6943e57f3a68e7","observation_id":"5088cccb-8157-447f-bbbb-9b9af8fbcccd","resolution":{"observed_at":"2026-08-06T15:55:38.245141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:37.977043Z","title":"Memory efficient continual learning with transformers","venue":null,"work_id":"2ddd424e-e3ce-424c-b0b3-4bdc09ccbd91","year":2022},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:28.844380Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:41791b9b4e3ef6f2d8b66631ea9dac4549f576d258eda7908d23c97f391f6d82","observation_id":"6ad11870-723e-4524-b831-e8753f885ec1","resolution":{"observed_at":"2026-08-06T15:55:37.994941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.04332","last_updated":"2022-03-14T02:05:06Z","snapshot_observed_at":"2026-08-09T18:32:47.872424Z","submitted_at":"2021-09-09T15:11:04Z","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.04332","snapshot_observed_at":"2026-08-06T15:55:28.942688Z","title":"Ppt: Pre-trained prompt tuning for few-shot learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:28.942688Z"},"links":{"cited_paper":"/paper/2109.04332","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:453a9213ceede0964a4060d309f0d9c85266dfd68204f2d4b6b4d27dbd72d0d9","observation_id":"ded21617-762f-4eab-9429-142acbf17f72","resolution":{"observed_at":"2026-08-06T15:55:28.942688Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.14607","last_updated":"2024-04-22T22:04:16Z","snapshot_observed_at":"2026-07-06T18:04:04.541434Z","submitted_at":"2024-04-22T22:04:16Z","title":"Q-Tuning: Queue-based Prompt Tuning for Lifelong Few-shot Language Learning","version":1},"cited_work":{"arxiv_id":"2404.14607","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.14607","snapshot_observed_at":"2026-08-06T15:55:35.281292Z","title":"Q-Tuning: Queue-based Prompt Tuning for Lifelong Few-shot Language Learning","venue":"cs.CL","work_id":"ebaf5a33-bcea-41ac-aa30-930e44406839","year":2024},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:28.986642Z"},"links":{"cited_paper":"/paper/2404.14607","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:b1e4d9e8ba20ecd80056698225e321520fb24dd68efff7048be303e745cf135d","observation_id":"88cace18-6d4b-4c83-90f6-706222e90a37","resolution":{"observed_at":"2026-08-06T15:55:35.390730Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:37.822174Z","title":"Visual prompt tuning","venue":null,"work_id":"22d9d926-fa2c-4290-a84e-14c17b639bbb","year":2022},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:29.074126Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:f8d01f5895285669f25d895ed8238f5af7b7a52be1a1724283f8a203b9235fd2","observation_id":"45effcec-fc1f-4bcc-afa3-d0f3b1284114","resolution":{"observed_at":"2026-08-06T15:55:37.880976Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13024","last_updated":"2023-10-19T06:34:40Z","snapshot_observed_at":"2026-07-06T16:35:52.483600Z","submitted_at":"2023-10-19T06:34:40Z","title":"Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt","version":1},"cited_work":{"arxiv_id":"2310.13024","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.13024","snapshot_observed_at":"2026-08-06T15:55:35.094489Z","title":"Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt","venue":"cs.CL","work_id":"7e6f070a-5da4-40e8-b02f-99ba9da829e2","year":2023},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:29.165010Z"},"links":{"cited_paper":"/paper/2310.13024","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:228f7a90fdb5cf317b0041a64ab40a6cb08719b9074d18cdb2754724e98d848b","observation_id":"f0199218-1147-4b99-bdf4-2a43ca774d55","resolution":{"observed_at":"2026-08-06T15:55:35.167961Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.00123","last_updated":"2021-06-11T22:08:29Z","snapshot_observed_at":"2026-07-06T10:45:06.227629Z","submitted_at":"2021-02-27T04:09:32Z","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.00123","snapshot_observed_at":"2026-08-06T15:55:29.254637Z","title":"Grad-match: Gradient matching based data subset selection for efficient deep model training, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:29.254637Z"},"links":{"cited_paper":"/paper/2103.00123","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:e6707482c0e09a388838ff45c7a292f9798e52f2129aa0695d17cdb562312110","observation_id":"15fe70e1-9b0a-42c3-b6a3-5c3bd9d7ee43","resolution":{"observed_at":"2026-08-06T15:55:29.254637Z","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":"2026-08-06T15:55:29.359987Z","title":"Overcoming catastrophic forgetting in neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:29.359987Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:d0719a00edc49751d35639859b7d37b1c8b5c60280274fbd7bd2499bd173685e","observation_id":"4fc4fa79-4d77-4a4f-aa99-c1ad2de686e8","resolution":{"observed_at":"2026-08-06T15:55:29.359987Z","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":"2026-08-06T15:55:29.450650Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:29.450650Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:f01a21b5d3a2223588bd414bd074eccc1dce97650f25721faf5ad94cc97863d1","observation_id":"6253a496-05e4-4961-a081-ce156931f108","resolution":{"observed_at":"2026-08-06T15:55:29.450650Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00190","last_updated":"2021-01-01T08:00:36Z","snapshot_observed_at":"2026-07-06T10:29:18.734092Z","submitted_at":"2021-01-01T08:00:36Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00190","snapshot_observed_at":"2026-08-06T15:55:29.519202Z","title":"Prefix-tuning: Optimizing continuous prompts for generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:29.519202Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:e53576ed2278b86ed7bd1852ba9e57cccff7015a75652742bcaa55592ff345e8","observation_id":"11a0028b-dd93-41fb-b4b2-cf04d9cb3aec","resolution":{"observed_at":"2026-08-06T15:55:29.519202Z","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":"2026-08-06T15:55:29.596908Z","title":"Learning without forgetting","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:29.596908Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:74221f12ea841f8e64cc4d3b722fc785973307556040ea1c1919cd7e3705cc75","observation_id":"29aaeb2f-1116-4e69-9253-92c96fce5ad3","resolution":{"observed_at":"2026-08-06T15:55:29.596908Z","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":"2026-08-06T15:55:37.648944Z","title":"Learning word vectors for sentiment analysis","venue":null,"work_id":"23f4e0fa-f881-4b70-86ba-2bebaa5875bc","year":2011},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:29.666510Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:1ed775b62a868921aca8bd7c705f76a23fdc4092d2ee059c88f80793b75d256a","observation_id":"e49a8577-7c4a-4675-b617-080eecbd5b42","resolution":{"observed_at":"2026-08-06T15:55:37.715672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:29.772447Z","title":"Catastrophic interference in connectionist networks: The sequential learning problem","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:29.772447Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:c6643c5ecda197947858652ff3025e73b999de0ebf6287f3a075f8cd4579694e","observation_id":"a0d233de-48f6-44dc-83ed-a13701d33c10","resolution":{"observed_at":"2026-08-06T15:55:29.772447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.01827","last_updated":"2020-11-16T20:58:39Z","snapshot_observed_at":"2026-08-09T13:39:54.013511Z","submitted_at":"2019-06-05T05:10:37Z","title":"Coresets for Data-efficient Training of Machine Learning Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.01827","snapshot_observed_at":"2026-08-06T15:55:29.862346Z","title":"Coresets for data-efficient training of machine learning models, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:29.862346Z"},"links":{"cited_paper":"/paper/1906.01827","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:a9fac3d1cf4b874a56a8afed586ee249f20e30a161d81ce84eedebbd2f85cc64","observation_id":"2a43063c-e289-43d5-b3be-4685848fdde9","resolution":{"observed_at":"2026-08-06T15:55:29.862346Z","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":"2026-08-06T15:55:37.503747Z","title":"Q.: A survey on transfer learning","venue":null,"work_id":"86f6ac88-aec2-4ba5-8a92-1c58e8354e15","year":2010},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:29.973347Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:31beb08450d2186da4f0a4459486d9936411bb4a0490617a33008438b6f0d3ab","observation_id":"e8013613-d576-47f0-8276-6061ffd3dc18","resolution":{"observed_at":"2026-08-06T15:55:37.573625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.07298","last_updated":"2022-03-31T02:40:57Z","snapshot_observed_at":"2026-08-05T10:50:54.178336Z","submitted_at":"2021-10-14T12:06:29Z","title":"LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.07298","snapshot_observed_at":"2026-08-06T15:55:30.121698Z","title":"Lfpt5: A unified framework for lifelong few-shot language learning based on prompt tuning of t5","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:30.121698Z"},"links":{"cited_paper":"/paper/2110.07298","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:f300ea01fc38c69961cbb5a3193bc9f31a8d8d28591dab0e42bf85209b8da31d","observation_id":"4bae5a01-cabc-4a11-8e98-c41d05008357","resolution":{"observed_at":"2026-08-06T15:55:30.121698Z","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":"2026-08-06T15:55:30.212328Z","title":"Exploring the limits of transfer learning with a unified text-to-text transformer","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:30.212328Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:fb768ee447f55ea5fe969d7775fc3f0df4633f370e782f38d5bbe0069eb27d57","observation_id":"a97a4305-72e3-428d-bfb9-585b04106c88","resolution":{"observed_at":"2026-08-06T15:55:30.212328Z","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":"2026-08-06T15:55:37.164221Z","title":"Progressive prompts: Continual learning for language models","venue":null,"work_id":"f121d155-c2d9-48b6-8342-471526d81577","year":2023},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:30.307491Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:04d4ff7bf12f033ba4a03705362de70605e68a5db6bd3fb2076ecd541867b36d","observation_id":"6ae503af-6752-415c-9259-dfd0a621fd1c","resolution":{"observed_at":"2026-08-06T15:55:37.327453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:36.953604Z","title":"icarl: Incremental classifier and representation learning","venue":null,"work_id":"e8ecabef-75bf-4776-80d1-92a04e87a000","year":2001},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:30.441753Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:30a7846e4309ffcf9cf7d1e28cbbba0d10b14ac7ce3b2596c48ad609731f9419","observation_id":"ccf985f3-45df-4405-8743-74ccc91225c7","resolution":{"observed_at":"2026-08-06T15:55:37.013943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10084","last_updated":"2019-08-27T08:50:17Z","snapshot_observed_at":"2026-07-06T08:17:05.681370Z","submitted_at":"2019-08-27T08:50:17Z","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.10084","snapshot_observed_at":"2026-08-06T15:55:30.548750Z","title":"Sentence-bert: Sentence embeddings using siamese bert-networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:30.548750Z"},"links":{"cited_paper":"/paper/1908.10084","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:5f7874f72d0808184db2c062448f1ada89ae26e55c746526f4880462cd53c7bf","observation_id":"83eeef6a-16ef-481e-9dcf-f060fd032a10","resolution":{"observed_at":"2026-08-06T15:55:30.548750Z","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":"2026-08-06T15:55:36.764879Z","title":"Representation matters: Assessing the importance of subgroup allocations in training data","venue":null,"work_id":"fca601b2-4858-4d70-81d9-052d39db940b","year":2021},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:30.658597Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:e7d524f145cb42ced7f1c97aa4d1b594fa857706619a5222e76a2b1e6f415878","observation_id":"41bdb37a-3717-48c5-ad7b-007379e57708","resolution":{"observed_at":"2026-08-06T15:55:36.842587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:30.754137Z","title":"AdapterDrop : O n the efficiency of adapters in transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:30.754137Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:b6a2eaf3bd806a1fd4c55c8e6d442ee9c12313956281ad265f56846010ec9d17","observation_id":"999c720f-6066-45a9-881e-03874dca3014","resolution":{"observed_at":"2026-08-06T15:55:30.754137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.04671","last_updated":"2022-10-22T14:34:44Z","snapshot_observed_at":"2026-08-09T14:14:13.613085Z","submitted_at":"2016-06-15T08:20:51Z","title":"Progressive Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.04671","snapshot_observed_at":"2026-08-06T15:55:30.850923Z","title":"Progressive neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:30.850923Z"},"links":{"cited_paper":"/paper/1606.04671","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:c69c9c1b2259323204cec5e80a81a5ec3f6151b289c415228495736f5b82ba0c","observation_id":"165431f6-d3cc-4028-a671-6e655ac1cd6c","resolution":{"observed_at":"2026-08-06T15:55:30.850923Z","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":"10.18653/v1/2024.emnlp-main.676","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:34.487743Z","title":null,"venue":null,"work_id":"129a1dd9-c62f-4e37-a7e3-f6564c53fcd8","year":2024},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:30.999926Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:24cce4849a0d57074935d1febd9ab5c05cca5c8ca8e1f7e2bc7851e727fc09cb","observation_id":"b6034890-6961-49a6-a213-5fddd38b8cc1","resolution":{"observed_at":"2026-08-06T15:55:34.564993Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:31.136745Z","title":"Continual learning with deep generative replay","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:31.136745Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:e4ed60b365d85f91f6123e386cf4f54dced1f37db5cf1bbeb90cbb1a1d4317ae","observation_id":"c6cd62ae-da39-4670-a58f-0a94732fce40","resolution":{"observed_at":"2026-08-06T15:55:31.136745Z","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":"2026-08-06T15:55:36.606268Z","title":"Coda-prompt: Continual decomposed attention-based prompting for rehearsal-free continual learning","venue":null,"work_id":"e15880f4-d44d-4e30-a5d9-2c24275f05ee","year":2023},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:31.241128Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:cf0c780f34a205b49b2c59fbf80a0353715dd0a89bc7fa6170438851d2c2eba1","observation_id":"9616aebc-6961-44b1-bb81-f9f70fd9b72f","resolution":{"observed_at":"2026-08-06T15:55:36.661289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.03329","last_updated":"2019-12-23T04:36:52Z","snapshot_observed_at":"2026-08-05T02:46:51.475659Z","submitted_at":"2019-09-07T20:17:34Z","title":"LAMOL: LAnguage MOdeling for Lifelong Language Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.03329","snapshot_observed_at":"2026-08-06T15:55:31.339884Z","title":"Lamol: Language modeling for lifelong language learning","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:31.339884Z"},"links":{"cited_paper":"/paper/1909.03329","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:2db82638c4cae1f58284c43d8a46ff190f81075f57fa755bfe2a830da82f9e45","observation_id":"13d7237c-1a87-46c6-8955-525d6864c5ba","resolution":{"observed_at":"2026-08-06T15:55:31.339884Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.07734","last_updated":"2019-04-15T12:22:36Z","snapshot_observed_at":"2026-07-06T07:46:29.188511Z","submitted_at":"2019-04-15T12:22:36Z","title":"Three scenarios for continual learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.07734","snapshot_observed_at":"2026-08-06T15:55:31.440523Z","title":"Three scenarios for continual learning","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:31.440523Z"},"links":{"cited_paper":"/paper/1904.07734","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:5c302c1dd224b03369de4d29affc1e975f7478516d753972d1c01c98c60b57cc","observation_id":"131cd3d8-160b-40fe-9015-54ab9e38c7bb","resolution":{"observed_at":"2026-08-06T15:55:31.440523Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.12631","last_updated":"2021-02-12T18:25:43Z","snapshot_observed_at":"2026-08-08T18:09:04.072442Z","submitted_at":"2020-12-23T12:42:16Z","title":"Efficient Continual Learning with Modular Networks and Task-Driven Priors","version":2},"cited_work":{"arxiv_id":"2012.12631","doi":null,"metadata_source":"pith","pith_arxiv_id":"2012.12631","snapshot_observed_at":"2026-08-06T15:55:34.833774Z","title":"Efficient Continual Learning with Modular Networks and Task-Driven Priors","venue":"cs.LG","work_id":"26b7d35c-02ec-4a5d-8082-f59e6d088e20","year":2020},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:31.565281Z"},"links":{"cited_paper":"/paper/2012.12631","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:3a1be10ecfc01a5a1f792e008c90103374c212f7783dfe0db1bd972d5f972690","observation_id":"33fca8d7-aadb-421f-a6e3-145823882c7b","resolution":{"observed_at":"2026-08-06T15:55:34.880566Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.07461","last_updated":"2019-02-22T23:53:34Z","snapshot_observed_at":"2026-07-06T06:34:26.609892Z","submitted_at":"2018-04-20T06:35:04Z","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.07461","snapshot_observed_at":"2026-08-06T15:55:31.664526Z","title":"Glue: A multi-task benchmark and analysis platform for natural language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:31.664526Z"},"links":{"cited_paper":"/paper/1804.07461","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:ac4bf37b3f1e0dc9154e0ac1d3047504ce6bb13ee05bf319fd3ff5717367e508","observation_id":"2de07160-f79c-43ec-9a15-75ad59a4f062","resolution":{"observed_at":"2026-08-06T15:55:31.664526Z","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":"2026-08-06T15:55:31.765482Z","title":"Superglue: A stickier benchmark for general-purpose language understanding systems","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:31.765482Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:647a6f848a4f82613d4c3d66f0458e4a473d18d37c3e632e8d4d2f3773d9b320","observation_id":"31d50b85-94a1-435b-a509-0eaeb6d90605","resolution":{"observed_at":"2026-08-06T15:55:31.765482Z","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":"2026-08-06T15:55:36.411773Z","title":"Pre-trained language models and their applications","venue":null,"work_id":"fb942782-1b80-493d-bcac-59a549a6d7ce","year":2023},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:31.850718Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:1e8168a4ac2deb18207b82d0720e7a30b4703bbf14179049d63ced3108831766","observation_id":"7525a995-19bb-4114-9f75-0a7a629c0f0a","resolution":{"observed_at":"2026-08-06T15:55:36.515977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:32.050354Z","title":"A comprehensive survey of continual learning: Theory, method and application","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:32.050354Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:0bba9ea20d2b1682f855ef5781814c0a10c21efbb0cfe9bab85cf5affd84638a","observation_id":"d727069f-69e6-4bee-83d3-2a6a4f6d057f","resolution":{"observed_at":"2026-08-06T15:55:32.050354Z","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":"2026-08-06T15:55:32.182700Z","title":"Multitask prompt tuning enables parameter-efficient transfer learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:32.182700Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:566b602358b7789ef0bb3b14a1f0cdd9a1cd3348a701a2319aa0190ead19c228","observation_id":"8b4f7eda-08a2-48b4-b594-c9098148fba9","resolution":{"observed_at":"2026-08-06T15:55:32.182700Z","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":"2026-08-06T15:55:36.125311Z","title":"Dualprompt: Complementary prompting for rehearsal-free continual learning","venue":null,"work_id":"8f34f9d7-083c-4938-9796-8b01d860e88c","year":2022},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:32.340078Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:b0a734cfeb42a1ddc7baab3f901c05243a0d3ec93b319d79503c1b8f26f2248f","observation_id":"663a8af0-0199-4e50-b178-922ee681ca92","resolution":{"observed_at":"2026-08-06T15:55:36.243562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:35.954999Z","title":"Learning to prompt for continual learning","venue":null,"work_id":"83baad59-56cb-406c-994a-27e1835b02dc","year":2022},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:32.453395Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:3ce6ef356bccbc0b7e2a02040162c89ba43794eba00834d2503db400a40e3de4","observation_id":"50991131-1879-48df-aca5-0bd2de5acd29","resolution":{"observed_at":"2026-08-06T15:55:36.037352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2020.emnlp-main.39","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:34.332789Z","title":"Efficient meta lifelong-learning with limited memory","venue":null,"work_id":"13fe3bd0-efad-4fc7-b22b-3361ca1129b7","year":2020},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:32.579553Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:60b7aa0188e40eb8b1dee98450fb11894d1067bbc18c0383fe3404b9f432d91a","observation_id":"5ff30b09-fbf2-4711-885c-0f48960fe022","resolution":{"observed_at":"2026-08-06T15:55:34.402847Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2024.findings-acl.650","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:34.195453Z","title":"Mitigate negative transfer with similarity heuristic lifelong prompt tuning","venue":null,"work_id":"50c6c29d-9cfb-48db-9585-cd5f2bd34af8","year":2024},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:32.730370Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:2d8562af90e2f0b7515ac8d4c93d91fd8f987c8b41bae469e79907bd1498913b","observation_id":"dff41a1c-7163-463d-8981-cdffbebe782c","resolution":{"observed_at":"2026-08-06T15:55:34.270634Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.12148","last_updated":"2023-12-19T13:31:24Z","snapshot_observed_at":"2026-07-06T17:05:19.007669Z","submitted_at":"2023-12-19T13:31:24Z","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.12148","snapshot_observed_at":"2026-08-06T15:55:32.848941Z","title":"Parameter-efficient fine-tuning methods for pretrained language models: A critical review and assessment, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:32.848941Z"},"links":{"cited_paper":"/paper/2312.12148","citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:d1fd2a34dd903b903000125180a55a43def87ebd475e7734e9347087bf6d8c59","observation_id":"3d14656f-e141-433c-aef2-9f753803ecbb","resolution":{"observed_at":"2026-08-06T15:55:32.848941Z","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":"10.18653/v1/2022.acl-long.218","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:33.919896Z","title":"C on T in T in: Continual learning from task instructions","venue":null,"work_id":"e47aa961-06e0-4e7c-8499-868660ae5619","year":2022},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:32.957975Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:7bad83c8f82885b2047453624a86532d6f811c43c11b8e2ebae4f3af51d66e35","observation_id":"2948f2f0-c23b-4938-a657-054d1fe36574","resolution":{"observed_at":"2026-08-06T15:55:34.077776Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:35.731788Z","title":"Lifelong learning with dynamically expandable networks","venue":null,"work_id":"3560d158-6aaa-49e8-bfa9-a90c8ceb5d0d","year":2018},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:33.059680Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:4c40bed1ee4563540013422bdcf6d8ecffaa29849587fc2d9b11b47c958c5d41","observation_id":"ae92c3fe-9246-4779-aefe-4bed2b3dafac","resolution":{"observed_at":"2026-08-06T15:55:35.827579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:33.166818Z","title":"Continual learning through synaptic intelligence","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:33.166818Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:8560c468e4ed114e1b65a40b168dbefe0e2bcbecaba37755721e7f29da330ff6","observation_id":"c4ffbf17-e77f-4e45-a96b-29749b597bc9","resolution":{"observed_at":"2026-08-06T15:55:33.166818Z","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":"2026-08-06T15:55:33.320981Z","title":"Character-level convolutional networks for text classification","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:33.320981Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:f2cdbcef35dab380883bf9e7a5c1a7e6f60847719fe9c761da65676cac404a08","observation_id":"d9c81424-ab08-41d9-9d85-50d0169c4c7b","resolution":{"observed_at":"2026-08-06T15:55:33.320981Z","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":"10.18653/v1/2022.acl-long.80","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:33.691249Z","title":"Continual prompt tuning for dialog state tracking","venue":null,"work_id":"72d95a52-dae0-4688-86fd-39559db5ca1b","year":2022},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:33.474596Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:57e463d0c3674fffc1302544223cb8c80570d7563a899813eca4380019dd8587","observation_id":"43256414-b7f7-4f62-9fbf-d8eef020786d","resolution":{"observed_at":"2026-08-06T15:55:33.801942Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:33.530330Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning","version":4},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-06T15:55:33.530330Z"},"links":{"citing_paper":"/paper/2507.14725"},"observation_digest":"sha256:70e0051240ba34bc3118f9a3fe52caf0f29892c6cb7403f1f57f6710761c6a80","observation_id":"c63a0526-ebfb-4fc5-8f56-b122b67a0126","resolution":{"observed_at":"2026-08-06T15:55:33.530330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.14725","last_updated":"2026-06-09T12:16:28Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T15:47:00.939567Z","submitted_at":"2025-07-19T19:15:03Z","title":"GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":27,"verified_exact":9,"verified_fuzzy":18},"total_outbound_references":54},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:2507.14725."}