{"as_of":"2026-08-10T16:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:233c4a047e465ebc181fc8384690f293113ed16c920f85efb323f7e0b65bae82","coverage":[{"denominator":12,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T22:50:37.455874Z","state":"measured"},{"denominator":12,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":12,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2502.04315/citation-record","integrity":"/paper/2502.04315/integrity","json":"/paper/2502.04315/citation-record.json","paper":"/paper/2502.04315"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.14946","last_updated":"2024-03-22T04:38:42Z","snapshot_observed_at":"2026-08-09T19:13:17.333607Z","submitted_at":"2024-03-22T04:38:42Z","title":"A Single Linear Layer Yields Task-Adapted Low-Rank Matrices","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.14946","snapshot_observed_at":"2026-08-08T22:50:37.313679Z","title":"A single linear layer yields task- adapted low-rank matrices","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.04315","last_updated":"2025-02-11T14:01:39Z","snapshot_observed_at":"2026-08-10T14:12:48.551333Z","submitted_at":"2025-02-06T18:57:06Z","title":"ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-08T22:50:37.313679Z"},"links":{"cited_paper":"/paper/2403.14946","citing_paper":"/paper/2502.04315"},"observation_digest":"sha256:e5fde449bf647dea4aac11cbdd56f7248f4ec643197267ae5fd96f2ca7fe2cba","observation_id":"7ab27d78-caf3-4312-bbbd-75802d41488e","resolution":{"observed_at":"2026-08-08T22:50:37.313679Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.04489","last_updated":"2021-06-08T16:16:40Z","snapshot_observed_at":"2026-08-03T19:17:21.128233Z","submitted_at":"2021-06-08T16:16:40Z","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.04489","snapshot_observed_at":"2026-08-08T22:50:37.318710Z","title":"Rabeeh Karimi Mahabadi, Sebastian Ruder, Mostafa Dehghani, and James Henderson","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.04315","last_updated":"2025-02-11T14:01:39Z","snapshot_observed_at":"2026-08-10T14:12:48.551333Z","submitted_at":"2025-02-06T18:57:06Z","title":"ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T22:50:37.318710Z"},"links":{"cited_paper":"/paper/2106.04489","citing_paper":"/paper/2502.04315"},"observation_digest":"sha256:f51c74a9e6a082ac45db53494d1afb1e1e7b8c83ce90f114ad69a405f84744d7","observation_id":"be15184d-3f5c-4dc1-aae0-07261fcab50c","resolution":{"observed_at":"2026-08-08T22:50:37.318710Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.11157","last_updated":"2024-05-18T03:02:23Z","snapshot_observed_at":"2026-07-06T18:16:03.617132Z","submitted_at":"2024-05-18T03:02:23Z","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.11157","snapshot_observed_at":"2026-08-08T22:50:37.432514Z","title":"Towards modular llms by building and reusing a library of loras","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.04315","last_updated":"2025-02-11T14:01:39Z","snapshot_observed_at":"2026-08-10T14:12:48.551333Z","submitted_at":"2025-02-06T18:57:06Z","title":"ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T22:50:37.432514Z"},"links":{"cited_paper":"/paper/2405.11157","citing_paper":"/paper/2502.04315"},"observation_digest":"sha256:afcc8cd0b32c66e1fdee2e79e27cfd22936be623c6d9086107480e2d3025309a","observation_id":"367181da-64e1-402b-b301-d28d59ab3c03","resolution":{"observed_at":"2026-08-08T22:50:37.432514Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.05816","last_updated":"2025-02-17T15:55:26Z","snapshot_observed_at":"2026-07-06T18:27:45.631190Z","submitted_at":"2024-06-09T15:08:00Z","title":"Attention as a Hypernetwork","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.05816","snapshot_observed_at":"2026-08-08T22:50:37.437040Z","title":"Attention as a hypernetwork","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.04315","last_updated":"2025-02-11T14:01:39Z","snapshot_observed_at":"2026-08-10T14:12:48.551333Z","submitted_at":"2025-02-06T18:57:06Z","title":"ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T22:50:37.437040Z"},"links":{"cited_paper":"/paper/2406.05816","citing_paper":"/paper/2502.04315"},"observation_digest":"sha256:fbd8eb7595413f033dbe90a9acf8d8c316f3c3f1ffa4feb0bdd37a2e7a526732","observation_id":"199dea76-f247-4507-a4ca-5249b46a01b2","resolution":{"observed_at":"2026-08-08T22:50:37.437040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.06252","last_updated":"2025-01-24T01:26:30Z","snapshot_observed_at":"2026-08-10T14:11:50.642675Z","submitted_at":"2025-01-09T01:19:21Z","title":"Transformer-Squared: Self-adaptive LLMs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.06252","snapshot_observed_at":"2026-08-08T22:50:37.441813Z","title":"Transformer 2: Self-adaptive llms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.04315","last_updated":"2025-02-11T14:01:39Z","snapshot_observed_at":"2026-08-10T14:12:48.551333Z","submitted_at":"2025-02-06T18:57:06Z","title":"ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T22:50:37.441813Z"},"links":{"cited_paper":"/paper/2501.06252","citing_paper":"/paper/2502.04315"},"observation_digest":"sha256:ac665e0d971b955b372bd85805613f3a237466d3bde72086cf653a82364b5c60","observation_id":"4cbc18e0-3b43-47e4-a4a1-433000ee856c","resolution":{"observed_at":"2026-08-08T22:50:37.441813Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.11030","last_updated":"2024-07-03T18:34:08Z","snapshot_observed_at":"2026-07-06T18:46:39.497352Z","submitted_at":"2024-07-03T18:34:08Z","title":"DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.11030","snapshot_observed_at":"2026-08-08T22:50:37.446530Z","title":"Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.04315","last_updated":"2025-02-11T14:01:39Z","snapshot_observed_at":"2026-08-10T14:12:48.551333Z","submitted_at":"2025-02-06T18:57:06Z","title":"ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-08T22:50:37.446530Z"},"links":{"cited_paper":"/paper/2407.11030","citing_paper":"/paper/2502.04315"},"observation_digest":"sha256:ec590c4c604a198fb134efa80417e9d412d9ee3ab51bd6d521848207b03460f4","observation_id":"1adf4c8b-e81f-42ca-8903-4de941526d81","resolution":{"observed_at":"2026-08-08T22:50:37.446530Z","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":"2026-08-08T22:50:37.455874Z","title":"URL https://aclanthology.org/ 2023.emnlp-main.487","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.04315","last_updated":"2025-02-11T14:01:39Z","snapshot_observed_at":"2026-08-10T14:12:48.551333Z","submitted_at":"2025-02-06T18:57:06Z","title":"ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-08T22:50:37.455874Z"},"links":{"citing_paper":"/paper/2502.04315"},"observation_digest":"sha256:f855a4a3372d3862cd3d62cd17124cfa06fe92fd478fb45cc060716586d96757","observation_id":"518d606a-d4a8-4289-b7e3-a3e896fc9d80","resolution":{"observed_at":"2026-08-08T22:50:37.455874Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.01411","last_updated":"2024-08-25T09:39:23Z","snapshot_observed_at":"2026-08-10T14:14:00.541579Z","submitted_at":"2024-07-01T16:00:53Z","title":"HyperLoader: Integrating Hypernetwork-Based LoRA and Adapter Layers into Multi-Task Transformers for Sequence Labelling","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.01411","snapshot_observed_at":"2026-08-08T22:50:37.426911Z","title":"Hyperloader: Integrating hypernetwork-based lora and adapter layers into multi-task transformers for sequence labelling","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.04315","last_updated":"2025-02-11T14:01:39Z","snapshot_observed_at":"2026-08-10T14:12:48.551333Z","submitted_at":"2025-02-06T18:57:06Z","title":"ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters","version":3},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-08T22:50:37.426911Z"},"links":{"cited_paper":"/paper/2407.01411","citing_paper":"/paper/2502.04315"},"observation_digest":"sha256:63a61e3d0951a39f1cb2168bfe4c66559a77d4a120e8ecc135ae616511b28fb4","observation_id":"e4b30460-a726-48b6-9b1d-526810ffe18b","resolution":{"observed_at":"2026-08-08T22:50:37.426911Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.08304","last_updated":"2022-10-18T17:37:56Z","snapshot_observed_at":"2026-08-09T23:18:55.374147Z","submitted_at":"2022-03-15T22:39:53Z","title":"Hyperdecoders: Instance-specific decoders for multi-task NLP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.08304","snapshot_observed_at":"2026-08-08T22:50:37.308799Z","title":"Hyperdecoders: Instance-specific decoders for multi-task nlp","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.04315","last_updated":"2025-02-11T14:01:39Z","snapshot_observed_at":"2026-08-10T14:12:48.551333Z","submitted_at":"2025-02-06T18:57:06Z","title":"ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters","version":3},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-08T22:50:37.308799Z"},"links":{"cited_paper":"/paper/2203.08304","citing_paper":"/paper/2502.04315"},"observation_digest":"sha256:980bf92be9f10c685f74f1dd808a0e6d4bab57a7215f50a43f02057e13e379ae","observation_id":"cbb98265-5eaf-47dc-bcbd-64c5f7fec3a2","resolution":{"observed_at":"2026-08-08T22:50:37.308799Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-07T07:43:16.294957Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-08T22:50:37.303752Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.04315","last_updated":"2025-02-11T14:01:39Z","snapshot_observed_at":"2026-08-10T14:12:48.551333Z","submitted_at":"2025-02-06T18:57:06Z","title":"ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters","version":3},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-08T22:50:37.303752Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2502.04315"},"observation_digest":"sha256:3d08f00fc1a5269ae92a3bc09faea73d1a5129955f761c476022440aeb5bfd5f","observation_id":"b712e446-31b3-410d-a336-04cf10263b42","resolution":{"observed_at":"2026-08-08T22:50:37.303752Z","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":"2026-08-08T22:50:37.641320Z","title":"Task-agnostic low-rank adapters for unseen english dialects","venue":null,"work_id":"311d4399-cccb-49c7-9f2d-18701fa8803b","year":2023},"citing_paper":{"arxiv_id":"2502.04315","last_updated":"2025-02-11T14:01:39Z","snapshot_observed_at":"2026-08-10T14:12:48.551333Z","submitted_at":"2025-02-06T18:57:06Z","title":"ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters","version":3},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-08T22:50:37.451266Z"},"links":{"citing_paper":"/paper/2502.04315"},"observation_digest":"sha256:267f448729891d72f4e5fdc3e4119260ded497f192a0bc0aeaad65fed1ab845c","observation_id":"a1790815-d9a6-4e08-81e6-590e87489d2a","resolution":{"observed_at":"2026-08-08T22:50:37.647750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.09106","last_updated":"2016-12-01T10:08:15Z","snapshot_observed_at":"2026-08-08T11:39:44.107967Z","submitted_at":"2016-09-27T05:57:00Z","title":"HyperNetworks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.09106","snapshot_observed_at":"2026-08-08T22:50:37.298070Z","title":"David Ha, Andrew Dai, and Quoc V Le","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.04315","last_updated":"2025-02-11T14:01:39Z","snapshot_observed_at":"2026-08-10T14:12:48.551333Z","submitted_at":"2025-02-06T18:57:06Z","title":"ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters","version":3},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-08T22:50:37.298070Z"},"links":{"cited_paper":"/paper/1609.09106","citing_paper":"/paper/2502.04315"},"observation_digest":"sha256:09868f93b39f63728fc73c703a2f68345d567e14f714f1645a401f6165754413","observation_id":"d88fba39-4df2-4248-8097-b175c8e4c24c","resolution":{"observed_at":"2026-08-08T22:50:37.298070Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.04315","last_updated":"2025-02-11T14:01:39Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-10T14:12:48.551333Z","submitted_at":"2025-02-06T18:57:06Z","title":"ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters"},"reference_resolution":{"displayed":12,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":1},"total_outbound_references":12},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2502.04315."}