{"as_of":"2026-08-18T13:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:39b697af0d06a4b8baba84cc73ef43fd8837ef6649bf2bcb8c5f3ab00b3d507f","coverage":[{"denominator":13,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":13,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T13:07:16.719365Z","state":"measured"},{"denominator":13,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":13,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2509.00996/citation-record","integrity":"/paper/2509.00996/integrity","json":"/paper/2509.00996/citation-record.json","paper":"/paper/2509.00996"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T13:07:18.152013Z","title":null,"venue":null,"work_id":"98b83e9d-ceeb-403d-8d2a-2b75c4aef8d3","year":null},"citing_paper":{"arxiv_id":"2509.00996","last_updated":"2025-09-13T23:37:47Z","snapshot_observed_at":"2026-08-13T15:02:21.471817Z","submitted_at":"2025-08-31T21:19:25Z","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T13:07:16.420352Z"},"links":{"citing_paper":"/paper/2509.00996"},"observation_digest":"sha256:ea5aee5c32fd3df990d8c2a0cd1171fd2c91715db58f07439c981b88df0a5b05","observation_id":"bef4a97f-0dca-45b6-929f-03b948508f58","resolution":{"observed_at":"2026-08-05T13:07:18.160144Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-05T13:07:18.011706Z","title":null,"venue":null,"work_id":"d2134b7b-0e40-47fa-865d-d96de95fa098","year":null},"citing_paper":{"arxiv_id":"2509.00996","last_updated":"2025-09-13T23:37:47Z","snapshot_observed_at":"2026-08-13T15:02:21.471817Z","submitted_at":"2025-08-31T21:19:25Z","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T13:07:16.544409Z"},"links":{"citing_paper":"/paper/2509.00996"},"observation_digest":"sha256:872b09a527360c7a3eabad297d38f4d4f91f9c086a89702d03ad21572f8fd95f","observation_id":"24291a6c-b628-497a-84d7-432a002c3271","resolution":{"observed_at":"2026-08-05T13:07:18.113996Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-05T13:07:17.731745Z","title":"These phenomena motivate our method","venue":null,"work_id":"63c6eff2-2b86-4205-a033-767ab8db7f32","year":null},"citing_paper":{"arxiv_id":"2509.00996","last_updated":"2025-09-13T23:37:47Z","snapshot_observed_at":"2026-08-13T15:02:21.471817Z","submitted_at":"2025-08-31T21:19:25Z","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T13:07:16.644396Z"},"links":{"citing_paper":"/paper/2509.00996"},"observation_digest":"sha256:06ef26ad91146d91824daa55adcd23b1cea1dd048ea05bc6c3becf9fb45ba037","observation_id":"13a9f20e-a66c-4ba9-8b5a-d3caf31cb03a","resolution":{"observed_at":"2026-08-05T13:07:17.830629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-05T13:07:18.249200Z","title":"Mixture of Expert Prompt Tuning as a Manifold Mapper","venue":null,"work_id":"b6db7001-d7fb-4acd-afc6-20d92931be07","year":2018},"citing_paper":{"arxiv_id":"2509.00996","last_updated":"2025-09-13T23:37:47Z","snapshot_observed_at":"2026-08-13T15:02:21.471817Z","submitted_at":"2025-08-31T21:19:25Z","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T13:07:16.169704Z"},"links":{"citing_paper":"/paper/2509.00996"},"observation_digest":"sha256:f1a2ccce10b0a30332dc0ad618b13da4bd062d5730af8f64e77b5941e34bd88e","observation_id":"b719fa23-1f78-4aab-a927-17547542492d","resolution":{"observed_at":"2026-08-05T13:07:18.258000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-05T13:07:17.501190Z","title":null,"venue":null,"work_id":"678f6841-d3f2-41b6-a391-7007c3ba659b","year":2024},"citing_paper":{"arxiv_id":"2509.00996","last_updated":"2025-09-13T23:37:47Z","snapshot_observed_at":"2026-08-13T15:02:21.471817Z","submitted_at":"2025-08-31T21:19:25Z","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T13:07:16.719365Z"},"links":{"citing_paper":"/paper/2509.00996"},"observation_digest":"sha256:5af349e5c8ed9bbafeadf09e7797d77aa2b79825bbfce49bf265ea0bd5881440","observation_id":"3b882d89-9322-40c0-9843-fa52f0353db0","resolution":{"observed_at":"2026-08-05T13:07:17.567768Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-05T13:07:18.177343Z","title":"common knowledge","venue":null,"work_id":"4659e31a-fca4-4718-b172-aafc088f3274","year":2010},"citing_paper":{"arxiv_id":"2509.00996","last_updated":"2025-09-13T23:37:47Z","snapshot_observed_at":"2026-08-13T15:02:21.471817Z","submitted_at":"2025-08-31T21:19:25Z","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T13:07:16.346952Z"},"links":{"citing_paper":"/paper/2509.00996"},"observation_digest":"sha256:b7710942cc3fd5d163fc63d8adf7788f77011e96e2d80433e88374376409e8c6","observation_id":"e2321bcc-4cb0-41ad-a110-ce5846528572","resolution":{"observed_at":"2026-08-05T13:07:18.185458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09519","last_updated":"2025-05-14T16:16:36Z","snapshot_observed_at":"2026-08-16T18:39:33.824991Z","submitted_at":"2025-05-14T16:16:36Z","title":"PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning","version":1},"cited_work":{"arxiv_id":"2505.09519","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.09519","snapshot_observed_at":"2026-08-05T13:07:16.907576Z","title":"PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning","venue":"cs.CL","work_id":"83be2c19-98be-4efb-aa0a-5e07cc5b10f3","year":2025},"citing_paper":{"arxiv_id":"2509.00996","last_updated":"2025-09-13T23:37:47Z","snapshot_observed_at":"2026-08-13T15:02:21.471817Z","submitted_at":"2025-08-31T21:19:25Z","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","version":2},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-05T13:07:15.703970Z"},"links":{"cited_paper":"/paper/2505.09519","citing_paper":"/paper/2509.00996"},"observation_digest":"sha256:8b1e865bd408c621681df14a47aa64098879cdc69699fb51117ffb243d2428dc","observation_id":"37d6c7a0-cbde-4473-946d-16627c976d2c","resolution":{"observed_at":"2026-08-05T13:07:16.990337Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12354","last_updated":"2024-07-04T18:33:00Z","snapshot_observed_at":"2026-08-16T14:17:14.074196Z","submitted_at":"2024-02-19T18:33:49Z","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12354","snapshot_observed_at":"2026-08-05T13:07:15.588822Z","title":"InICLR (Workshop Poster)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.00996","last_updated":"2025-09-13T23:37:47Z","snapshot_observed_at":"2026-08-13T15:02:21.471817Z","submitted_at":"2025-08-31T21:19:25Z","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","version":2},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-05T13:07:15.588822Z"},"links":{"cited_paper":"/paper/2402.12354","citing_paper":"/paper/2509.00996"},"observation_digest":"sha256:f8bdf4e1b90f0469ff05cb6fcbb6b57868f2ca33e181f36a1bcac91d8d225d36","observation_id":"3a4385f7-7aef-45a8-b6c9-e7c5d855b7dc","resolution":{"observed_at":"2026-08-05T13:07:15.588822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.00255","last_updated":"2024-06-01T08:04:02Z","snapshot_observed_at":"2026-08-16T15:04:06.989857Z","submitted_at":"2023-09-01T05:12:25Z","title":"SortedNet: A Scalable and Generalized Framework for Training Modular Deep Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.00255","snapshot_observed_at":"2026-08-05T13:07:16.051235Z","title":"In NAACL","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.00996","last_updated":"2025-09-13T23:37:47Z","snapshot_observed_at":"2026-08-13T15:02:21.471817Z","submitted_at":"2025-08-31T21:19:25Z","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-05T13:07:16.051235Z"},"links":{"cited_paper":"/paper/2309.00255","citing_paper":"/paper/2509.00996"},"observation_digest":"sha256:25f51d0393bc0004955c094302109a699e5433205a9fa04d2704934e0ceece01","observation_id":"9bac447c-7fb6-4862-bcbe-dd0e9367417d","resolution":{"observed_at":"2026-08-05T13:07:16.051235Z","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":"2026-08-05T13:07:18.283958Z","title":"Matthew E Peters, Mark Neumann, Luke Zettlemoyer, and Wen-tau Yih","venue":null,"work_id":"7ab80a2e-b6df-4bd4-a997-697bee113118","year":2018},"citing_paper":{"arxiv_id":"2509.00996","last_updated":"2025-09-13T23:37:47Z","snapshot_observed_at":"2026-08-13T15:02:21.471817Z","submitted_at":"2025-08-31T21:19:25Z","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-05T13:07:15.925983Z"},"links":{"citing_paper":"/paper/2509.00996"},"observation_digest":"sha256:eb718efbfdbf4ef57da871cb23784ba1edaae62e0cc2e486a0c5ed1928e2ac74","observation_id":"d7b6bf48-cf34-4aa6-994c-36a39c857d7b","resolution":{"observed_at":"2026-08-05T13:07:18.294413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-05T13:07:18.327702Z","title":null,"venue":null,"work_id":"c17a9fdf-8402-408c-a798-e935ebd13fec","year":2018},"citing_paper":{"arxiv_id":"2509.00996","last_updated":"2025-09-13T23:37:47Z","snapshot_observed_at":"2026-08-13T15:02:21.471817Z","submitted_at":"2025-08-31T21:19:25Z","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-05T13:07:15.808110Z"},"links":{"citing_paper":"/paper/2509.00996"},"observation_digest":"sha256:b7bf8c4c2a12d54ba51342ea7ef143a579f7bb057029a260c260a4be4b9a350d","observation_id":"3088efdf-4418-4f19-8b17-c5c77a268f5a","resolution":{"observed_at":"2026-08-05T13:07:18.335092Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.03155","last_updated":"2023-02-16T10:53:37Z","snapshot_observed_at":"2026-08-16T16:26:19.081940Z","submitted_at":"2022-10-06T18:37:49Z","title":"Understanding Neural Coding on Latent Manifolds by Sharing Features and Dividing Ensembles","version":2},"cited_work":{"arxiv_id":"2210.03155","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.03155","snapshot_observed_at":"2026-08-05T13:07:17.261239Z","title":"Understanding Neural Coding on Latent Manifolds by Sharing Features and Dividing Ensembles","venue":"stat.ML","work_id":"573cc242-ac7c-4ef5-88c4-547898986f9d","year":2022},"citing_paper":{"arxiv_id":"2509.00996","last_updated":"2025-09-13T23:37:47Z","snapshot_observed_at":"2026-08-13T15:02:21.471817Z","submitted_at":"2025-08-31T21:19:25Z","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-05T13:07:15.456726Z"},"links":{"cited_paper":"/paper/2210.03155","citing_paper":"/paper/2509.00996"},"observation_digest":"sha256:457f3fe4feec3328f08d081d4de0f1cc3140831e4b3339593d486b635ffa6082","observation_id":"180cf9db-c78b-4872-8830-fad77d15cc1c","resolution":{"observed_at":"2026-08-05T13:07:17.401770Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-05T13:07:18.217008Z","title":"XPrompt (Ma et al., 2022) enhances efficiency by prun- ing less informative token-level and piece-level prompts","venue":null,"work_id":"43f0f349-47b7-4cfe-9523-0ea506743b25","year":2022},"citing_paper":{"arxiv_id":"2509.00996","last_updated":"2025-09-13T23:37:47Z","snapshot_observed_at":"2026-08-13T15:02:21.471817Z","submitted_at":"2025-08-31T21:19:25Z","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-05T13:07:16.266678Z"},"links":{"citing_paper":"/paper/2509.00996"},"observation_digest":"sha256:f3e905342cc15499f9d1f003241fe34b394d45b818e5ad77a91dabffd8c606f9","observation_id":"6c376ea3-0bc0-4367-8eb5-8186125bdc95","resolution":{"observed_at":"2026-08-05T13:07:18.231437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.00996","last_updated":"2025-09-13T23:37:47Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T15:02:21.471817Z","submitted_at":"2025-08-31T21:19:25Z","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper"},"reference_resolution":{"displayed":13,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":6,"verified_exact":1,"verified_fuzzy":5},"total_outbound_references":13},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 0 inbound Pith citation observations for arXiv:2509.00996."}