{"as_of":"2026-08-18T09:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:01c4113daadb33657b28403c54f9e5176b6cd517c4a071c396485f971f51b96e","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T22:50:15.749239Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T05:16:35.355130Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.20629","snapshot_observed_at":"2026-08-02T05:16:35.355130Z","title":"Plop: Precise lora placement for efficient finetuning of large models.arXiv preprint arXiv:2506.20629,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13425","last_updated":"2026-07-15T04:03:24Z","snapshot_observed_at":"2026-08-16T22:11:34.311205Z","submitted_at":"2026-07-15T04:03:24Z","title":"Data-Efficient Adaptation of LLMs via Attention Head Reweighting","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T05:16:35.355130Z"},"links":{"cited_paper":"/paper/2506.20629","citing_paper":"/paper/2607.13425"},"observation_digest":"sha256:ba6bcd230e85722c7e299044b59c3b03f568f9e5ebaf05c6691afbfd2c502300","observation_id":"b39c9925-8b32-4b65-8f19-cfb6d7b58af3","resolution":{"observed_at":"2026-08-02T05:16:35.355130Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.20629","snapshot_observed_at":"2026-08-02T02:01:50.780452Z","title":"Plop: Precise lora placement for efficient finetuning of large models.arXiv preprint arXiv:2506.20629, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14506","last_updated":"2026-07-16T02:42:24Z","snapshot_observed_at":"2026-08-10T11:42:23.996756Z","submitted_at":"2026-07-16T02:42:24Z","title":"Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T02:01:50.780452Z"},"links":{"cited_paper":"/paper/2506.20629","citing_paper":"/paper/2607.14506"},"observation_digest":"sha256:66944ea868649c0d4b51765b12551d7c957be1be2148ab8088ecd1e797f3ccc8","observation_id":"a91d7e92-debe-4d2e-9bb7-a94f201777d4","resolution":{"observed_at":"2026-08-02T02:01:50.780452Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.20629","snapshot_observed_at":"2026-08-01T17:32:33.530247Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17620","last_updated":"2026-07-20T07:16:31Z","snapshot_observed_at":"2026-08-14T17:02:17.072637Z","submitted_at":"2026-07-20T07:16:31Z","title":"PoLoRA: A Preconditioned Orthogonalized LoRA Optimizer","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-01T17:32:33.530247Z"},"links":{"cited_paper":"/paper/2506.20629","citing_paper":"/paper/2607.17620"},"observation_digest":"sha256:caf3d0c4dac40cc12e3d27ff6be5ff562a99370b6efd81302ead3af0ee405e59","observation_id":"ab7739c6-94ab-4006-b8c5-da9c222a1270","resolution":{"observed_at":"2026-08-01T17:32:33.530247Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.20629/citation-record","integrity":"/paper/2506.20629/integrity","json":"/paper/2506.20629/citation-record.json","paper":"/paper/2506.20629"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:50:11.762337Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:11.762337Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:e564b2d0b88090a8953cc4a7093151bfa3fced8e65d690c7a40b6e3cd553bc06","observation_id":"b5db60fe-41bd-4e44-9518-a79662231a5a","resolution":{"observed_at":"2026-08-06T22:50:11.762337Z","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":"2026-08-06T22:50:18.557838Z","title":"LoRA+: Efficient low rank adaptation of large models","venue":null,"work_id":"0e388279-5e07-4f41-8a56-571e4bc896c2","year":2024},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:11.806899Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:db22a02febecf766f3fc3e7f6e5bda51844eb80359d41cd748e99cbdb2b4b82a","observation_id":"bc146791-03eb-470b-ba9f-97bd0c413541","resolution":{"observed_at":"2026-08-06T22:50:18.645387Z","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":"2026-08-06T22:50:18.383214Z","title":"Dora: Weight-decomposed low-rank adaptation","venue":null,"work_id":"aa93b1da-ce13-4622-893d-790948c5b5c7","year":2024},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:11.866917Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:f4fbe686850483c00723aa6483a69c12c30ee2ccfb7e7409b57e3e2315051609","observation_id":"d6846caf-cf64-4ca6-90dd-ea8b981b5217","resolution":{"observed_at":"2026-08-06T22:50:18.456925Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:50:11.916739Z","title":"RA-LoRA: Rank- adaptive parameter-efficient fine-tuning for accurate 2-bit quantized large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:11.916739Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:a399b228023d523bbbb300bd8de07746bcd3e99cd2c7fdd295ed038013407aff","observation_id":"afdf1c00-ad44-45e4-ae95-dd2109535032","resolution":{"observed_at":"2026-08-06T22:50:11.916739Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.01004","last_updated":"2026-05-27T06:22:29Z","snapshot_observed_at":"2026-08-16T21:38:53.773168Z","submitted_at":"2024-12-01T23:41:42Z","title":"Take Only What You Need: Rank Minimization as an Implicit Forgetting Regularizer in Continual Learning","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.01004","snapshot_observed_at":"2026-08-06T22:50:11.955707Z","title":"Adaptive rank, reduced forgetting: Knowledge retention in continual learning vision- language models with dynamic rank-selective lora, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:11.955707Z"},"links":{"cited_paper":"/paper/2412.01004","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:37694e2427a2d89e6a0de12db8d84b46fd6297920b64833b6ba8b26cfaafa13f","observation_id":"4f14b611-5324-426a-9f6a-8c236fabb752","resolution":{"observed_at":"2026-08-06T22:50:11.955707Z","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":"2026-08-06T22:50:18.189040Z","title":"The impact of initialization on lora finetuning dynamics","venue":null,"work_id":"b20b874b-3bd7-4c98-964c-45894967c130","year":null},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.015542Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:5815dd208a0689aef797cbe0fcbea152886a0b19bc1927fe4f8bacd2831c9f3b","observation_id":"411880e2-f4d0-4922-8149-838dee2eefcb","resolution":{"observed_at":"2026-08-06T22:50:18.283837Z","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":"2303.10512","last_updated":"2023-12-20T20:56:14Z","snapshot_observed_at":"2026-08-12T23:46:47.414754Z","submitted_at":"2023-03-18T22:36:25Z","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.10512","snapshot_observed_at":"2026-08-06T22:50:12.149846Z","title":"Adalora: Adaptive budget allocation for parameter-efficient fine-tuning, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.149846Z"},"links":{"cited_paper":"/paper/2303.10512","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:7fbdcbc7f738f3fb451ef46841ec7d6618ea01d2013433b0e6536b41a72b9e15","observation_id":"32f10d84-83ea-4ff9-8bb6-cbc0cb9fd109","resolution":{"observed_at":"2026-08-06T22:50:12.149846Z","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":"2026-08-06T22:50:17.850421Z","title":"Qlora: Effi- cient finetuning of quantized llms","venue":null,"work_id":"acc5618a-ea06-4ba1-8a77-d08f85ca4a26","year":2023},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.211265Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:e6a1fcae8ad55490cf00ba0368831b745aea8b88e90c715db3a797cf46b1ea2a","observation_id":"dad788d7-cbe3-45db-ab3d-6b88285e0e49","resolution":{"observed_at":"2026-08-06T22:50:17.926630Z","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":"2310.11454","last_updated":"2024-01-16T18:59:22Z","snapshot_observed_at":"2026-08-18T09:45:42.493282Z","submitted_at":"2023-10-17T17:59:46Z","title":"VeRA: Vector-based Random Matrix Adaptation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.11454","snapshot_observed_at":"2026-08-06T22:50:12.267784Z","title":"Kopiczko, Tijmen Blankevoort, and Yuki M","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.267784Z"},"links":{"cited_paper":"/paper/2310.11454","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:23dc7c1834646a97530c37c5e942a8bef4486b69c60a1c409f7d6307354a7e28","observation_id":"60eda5be-c04f-4910-a234-c24fe22a6fcd","resolution":{"observed_at":"2026-08-06T22:50:12.267784Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-13T08:01:16.750424Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-06T22:50:12.331356Z","title":"Lora-fa: Memory- efficient low-rank adaptation for large language models fine-tuning, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.331356Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:1a27307ef08a1bdab674ea73904c76c2532083ee7f31dc941f97eac364ef84d4","observation_id":"5c6837c7-1911-4314-905f-1ef8bbbf7e3a","resolution":{"observed_at":"2026-08-06T22:50:12.331356Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.19245","last_updated":"2024-05-23T15:06:02Z","snapshot_observed_at":"2026-08-18T09:28:28.076815Z","submitted_at":"2024-04-30T04:01:09Z","title":"HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.19245","snapshot_observed_at":"2026-08-06T22:50:12.357927Z","title":"Hydralora: An asymmetric lora architecture for efficient fine-tuning, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.357927Z"},"links":{"cited_paper":"/paper/2404.19245","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:daee54e120bb451a6abf387c190fd629240c1215f6c88d6b8f8d6f30d0635815","observation_id":"ee0ed6d0-85d7-49d5-b489-a2954f848beb","resolution":{"observed_at":"2026-08-06T22:50:12.357927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.12130","last_updated":"2024-05-20T15:48:32Z","snapshot_observed_at":"2026-08-18T09:50:57.462570Z","submitted_at":"2024-05-20T15:48:32Z","title":"MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.12130","snapshot_observed_at":"2026-08-06T22:50:12.408587Z","title":"Mora: High-rank updating for parameter-efficient fine-tuning, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.408587Z"},"links":{"cited_paper":"/paper/2405.12130","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:93a7e79fa0649bc64858c4dcbf414b0a2e1945ebd688a386bf2ec70a99e0a14f","observation_id":"6d5a7cc4-248e-4a91-8ea7-52f11502b57a","resolution":{"observed_at":"2026-08-06T22:50:12.408587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.05086","last_updated":"2024-04-07T22:00:50Z","snapshot_observed_at":"2026-08-16T14:02:55.782046Z","submitted_at":"2024-04-07T22:00:50Z","title":"A Note on LoRA","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.05086","snapshot_observed_at":"2026-08-06T22:50:12.474879Z","title":"A note on lora","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.474879Z"},"links":{"cited_paper":"/paper/2404.05086","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:087dfc6d06322a1e4351e0a79a5efc2955e40052d8b359c28f9277672c1e278c","observation_id":"f9d36fd4-5867-4440-8523-58922a1ec4a0","resolution":{"observed_at":"2026-08-06T22:50:12.474879Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04366","last_updated":"2022-02-02T16:39:23Z","snapshot_observed_at":"2026-08-18T09:21:01.141614Z","submitted_at":"2021-10-08T20:22:26Z","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.04366","snapshot_observed_at":"2026-08-06T22:50:12.504083Z","title":"Towards a unified view of parameter-efficient transfer learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.504083Z"},"links":{"cited_paper":"/paper/2110.04366","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:5a7f24e9df6dfe5699706d8cf618c6fa284e2834db6077d91ade5e595e665680","observation_id":"9cd9a7cb-07f0-49eb-bc91-7b730ad0733e","resolution":{"observed_at":"2026-08-06T22:50:12.504083Z","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":"2026-08-06T22:50:17.705809Z","title":"The llama 3 herd of models, 2024","venue":null,"work_id":"64dc7f5c-baf1-4a5a-9243-f7d26dbc2983","year":2024},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.614220Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:77344804e1c6255cd20d4d4e0e151128d4cbbfa4359c54300c4d6cce0b9182fd","observation_id":"383b47b1-d223-4a68-a1ec-16c743680418","resolution":{"observed_at":"2026-08-06T22:50:17.756774Z","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":"2104.08771","last_updated":"2021-09-14T16:07:09Z","snapshot_observed_at":"2026-08-16T18:30:47.800789Z","submitted_at":"2021-04-18T08:41:01Z","title":"Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08771","snapshot_observed_at":"2026-08-06T22:50:12.706998Z","title":"Cross-attention is all you need: Adapt- ing pretrained transformers for machine translation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.706998Z"},"links":{"cited_paper":"/paper/2104.08771","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:bd7556a5d2ba5045d1279d6b39520407e3fa7b5dd6e9938db5e9814a11e505e3","observation_id":"6102ceff-bbf2-45f1-8b94-602a10a7f861","resolution":{"observed_at":"2026-08-06T22:50:12.706998Z","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":"2026-08-06T22:50:17.479671Z","title":"Gradient-based parameter selection for efficient fine-tuning","venue":null,"work_id":"7d03ef79-3317-44ef-9927-d1f29b10705d","year":2024},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.818350Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:dd5729b68e118395152db88485877d6b3275b82757c85192f5cc0af8233d5ab9","observation_id":"cd0794ff-9d5f-4fb4-be95-65d80cded92d","resolution":{"observed_at":"2026-08-06T22:50:17.562213Z","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":"2026-08-06T22:50:17.320992Z","title":"Sensitivity-aware visual parameter-efficient fine-tuning","venue":null,"work_id":"cc2f5272-b0cf-4c63-9853-3661f42fd872","year":2023},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.910209Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:0f8315cd517ab32068c1e5986e4077b32a9627a6608d7715ce1a5d72fedf68b3","observation_id":"2da089bd-1adc-4d98-bc7a-aa29fc568acd","resolution":{"observed_at":"2026-08-06T22:50:17.380197Z","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":"2026-08-06T22:50:17.157021Z","title":null,"venue":null,"work_id":"1202dfae-7cff-4ff2-9df6-444ec21d2581","year":null},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:13.021420Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:482a8c486ce0d244e2e2cc6b0d9f2eb79f37fb3861087706dabc4873a98bb0ef","observation_id":"ce9e4aa4-272e-4d60-b1a5-fefd85e3a4f3","resolution":{"observed_at":"2026-08-06T22:50:17.238859Z","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":"2026-08-06T22:50:17.015349Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":"da95f519-2415-475e-a5d1-fb519118d58b","year":null},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:13.218947Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:96187bc2ded6c7fb03f8c32ddbc7ae93466f22128a6ae7cb3b6347ee9378b909","observation_id":"ce83a540-3168-4779-9db0-909cbe759f6d","resolution":{"observed_at":"2026-08-06T22:50:17.096221Z","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":"1802.04434","last_updated":"2018-08-07T18:55:19Z","snapshot_observed_at":"2026-08-14T19:46:33.101156Z","submitted_at":"2018-02-13T02:14:35Z","title":"signSGD: Compressed Optimisation for Non-Convex Problems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.04434","snapshot_observed_at":"2026-08-06T22:50:13.453468Z","title":"signsgd: Compressed optimisation for non-convex problems, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:13.453468Z"},"links":{"cited_paper":"/paper/1802.04434","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:ae570f9d10ed5fcc900c2b69991814dbf28939ea7eeae3959073e3effa27b475","observation_id":"8dc6addd-a51a-4ece-bbfc-5d095e255263","resolution":{"observed_at":"2026-08-06T22:50:13.453468Z","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":"2410.04264","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:50:16.222658Z","title":"Visualising feature learning in deep neural networks by diagonalizing the forward feature map, 2024","venue":null,"work_id":"123cc28a-2459-4670-858c-b75791b44440","year":2024},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:13.578167Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:014b882fe16cbc5fd18e78d2528bb0378817a3123b7945a14f27b6601e25b944","observation_id":"dd1a8385-e7d5-48c7-a0fd-26dbbedfddfe","resolution":{"observed_at":"2026-08-06T22:50:16.273915Z","resolver_source":"raw_fallback","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":"2008.00938","last_updated":"2021-03-17T00:57:56Z","snapshot_observed_at":"2026-08-18T09:45:45.664511Z","submitted_at":"2020-08-03T15:18:07Z","title":"Implicit Regularization via Neural Feature Alignment","version":3},"cited_work":{"arxiv_id":"2008.00938","doi":null,"metadata_source":"pith","pith_arxiv_id":"2008.00938","snapshot_observed_at":"2026-08-06T22:50:15.961398Z","title":"Implicit Regularization via Neural Feature Alignment","venue":"cs.LG","work_id":"fc9f60bc-6107-4380-b2cd-4514b773daff","year":2020},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:13.659226Z"},"links":{"cited_paper":"/paper/2008.00938","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:ab636498505901d4484a22a70db70781ccd40bcf68da3453c76b0564c0787130","observation_id":"516add5c-cd9c-420e-80ee-e4bf65044507","resolution":{"observed_at":"2026-08-06T22:50:16.027006Z","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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:50:16.891268Z","title":"Feature learning and signal propagation in deep neural networks","venue":null,"work_id":"9ae459cf-a19a-4936-baef-916fad689a9e","year":2022},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:13.754683Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:1d8384dd6f581f525c96e4bc56fb72f1e79ce2d4819bc8ca05493e334fb1212a","observation_id":"75d14942-7f09-45ca-95e0-f31ddb2a1c04","resolution":{"observed_at":"2026-08-06T22:50:16.966923Z","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":"2405.19279","last_updated":"2024-11-06T22:45:30Z","snapshot_observed_at":"2026-08-18T09:48:08.295122Z","submitted_at":"2024-05-29T17:11:28Z","title":"Understanding and Minimising Outlier Features in Neural Network Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.19279","snapshot_observed_at":"2026-08-06T22:50:13.820346Z","title":"Understanding and minimising outlier features in neural network training, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:13.820346Z"},"links":{"cited_paper":"/paper/2405.19279","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:3fac4c76c36683d869377f8afd79737625add7c9bab8e99a32b9fa10a80b4e8e","observation_id":"18e2395b-0685-4b1d-bddd-cbc855c1caa0","resolution":{"observed_at":"2026-08-06T22:50:13.820346Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-14T02:43:01.480086Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-06T22:50:13.890990Z","title":"Training verifiers to solve math word problems","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:13.890990Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:aeac2dd5a233e668fbdee4885d4ad1e262929cccc0128596b15bc3491044f541","observation_id":"a23e82c6-11ae-4b8d-9364-b6de3b3eef0b","resolution":{"observed_at":"2026-08-06T22:50:13.890990Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.03374","last_updated":"2021-07-14T17:16:02Z","snapshot_observed_at":"2026-08-08T11:58:24.516369Z","submitted_at":"2021-07-07T17:41:24Z","title":"Evaluating Large Language Models Trained on Code","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.03374","snapshot_observed_at":"2026-08-06T22:50:13.961350Z","title":"Evaluating large language models trained on code","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:13.961350Z"},"links":{"cited_paper":"/paper/2107.03374","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:3786ec70ad8dc467bee2afa7a34824f97f090b605da4d7c1edd32b673c051c01","observation_id":"5183aeeb-7db3-4afc-abd7-7ba021bb41d9","resolution":{"observed_at":"2026-08-06T22:50:13.961350Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.03300","last_updated":"2021-01-12T18:57:11Z","snapshot_observed_at":"2026-08-13T20:44:28.824685Z","submitted_at":"2020-09-07T17:59:25Z","title":"Measuring Massive Multitask Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.03300","snapshot_observed_at":"2026-08-06T22:50:14.042709Z","title":"Measuring massive multitask language understanding, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:14.042709Z"},"links":{"cited_paper":"/paper/2009.03300","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:3e054d78820cd36348bd3f3e870f17dacd96fb08632447a5c8eca67ade620157","observation_id":"447d596a-cfef-43ab-8d04-ea5ccab57416","resolution":{"observed_at":"2026-08-06T22:50:14.042709Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-08-06T14:58:42.911363Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-06T22:50:14.160586Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:14.160586Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:4f1d4c6a5da7060ec3c9c3f3c0c96c2e8d25966029c2ef8121b7f75b55decc71","observation_id":"b3b6997b-fa6a-4013-b85e-751b70d60b89","resolution":{"observed_at":"2026-08-06T22:50:14.160586Z","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":"2026-08-06T22:50:16.747898Z","title":"Qwen3 technical report, April 2025","venue":null,"work_id":"a114ed02-8319-45e3-a9a2-d1e4310fab49","year":2025},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:14.273874Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:220c2a7ac6867f1ac5ee6b26a40ce093443fa50eb1314b84fb1eac36fcfd2b85","observation_id":"eb7b65fa-b8be-4540-86d1-5ccfe1ac932e","resolution":{"observed_at":"2026-08-06T22:50:16.813184Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:50:14.336198Z","title":"Gemma 3 technical report, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:14.336198Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:a8d4420b4e26727308a5a2f870a65e16aeea06c5941c2ac59fb56ae213941072","observation_id":"7e6ccd7b-320c-4252-ac65-c033859c8043","resolution":{"observed_at":"2026-08-06T22:50:14.336198Z","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":"2026-08-06T22:50:16.608448Z","title":"Adversarial nli: A new benchmark for natural language understanding","venue":null,"work_id":"c772e9d7-b9ce-4f50-b2aa-e7442aeff776","year":2020},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:14.417894Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:33674da2fb65e659c72fe5e0f466aeb087125ec2a9706f9609a27b3c9b9ff625","observation_id":"5db56f86-e897-44f6-9275-bec66881314d","resolution":{"observed_at":"2026-08-06T22:50:16.682332Z","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":"2309.12284","last_updated":"2024-05-03T17:36:07Z","snapshot_observed_at":"2026-08-13T10:57:13.012119Z","submitted_at":"2023-09-21T17:45:42Z","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.12284","snapshot_observed_at":"2026-08-06T22:50:14.482792Z","title":"Metamath: Bootstrap your own mathematical questions for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:14.482792Z"},"links":{"cited_paper":"/paper/2309.12284","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:9e14cf574be58bee395935022f26177ecc399fe69f25594860f628ce8ebb7b9d","observation_id":"1f47f458-6a09-4c7a-af59-185ffdbe48e0","resolution":{"observed_at":"2026-08-06T22:50:14.482792Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.00451","last_updated":"2024-06-17T22:11:49Z","snapshot_observed_at":"2026-08-18T09:48:11.842015Z","submitted_at":"2024-05-01T11:10:24Z","title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.00451","snapshot_observed_at":"2026-08-06T22:50:14.576341Z","title":"Lillicrap, Kenji Kawaguchi, and Michael Shieh","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:14.576341Z"},"links":{"cited_paper":"/paper/2405.00451","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:2799b91415f42c8b1d1038a50b2f8c132b2cefdc28a43da49bb25c2c3df831dd","observation_id":"e070fe5c-7e87-41b8-8a10-5bf39df4fad6","resolution":{"observed_at":"2026-08-06T22:50:14.576341Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-08-15T12:33:55.451951Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-06T22:50:14.684254Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforce- ment learning, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:14.684254Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:b24171dae1550c52865df8a9e6b70cee33ef657794de1afd0d8ba9449dea0009","observation_id":"1be3cd60-22ba-4da2-b15d-2d4d881126db","resolution":{"observed_at":"2026-08-06T22:50:14.684254Z","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":"2026-08-06T22:50:14.881189Z","title":"Rae, Oriol Vinyals, and Laurent Sifre","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:14.881189Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:c6dee95b54f86b382acc842990dee896a428ee67b7f92e8a8faf877b0ec8a0c0","observation_id":"f0915151-274c-4caf-ba34-072f6be67ad8","resolution":{"observed_at":"2026-08-06T22:50:14.881189Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1502.01852","last_updated":"2015-02-06T10:44:00Z","snapshot_observed_at":"2026-08-14T23:01:07.044616Z","submitted_at":"2015-02-06T10:44:00Z","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1502.01852","snapshot_observed_at":"2026-08-06T22:50:15.138441Z","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:15.138441Z"},"links":{"cited_paper":"/paper/1502.01852","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:210447144905de0956e04c107ecaafdca398556bab6484cb1247e5e0db707728","observation_id":"e33a345d-cbf0-45e2-bc08-32823397018e","resolution":{"observed_at":"2026-08-06T22:50:15.138441Z","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":"2026-08-06T22:50:16.481153Z","title":"On the impact of the activation function on deep neural networks training","venue":null,"work_id":"b91861fb-3124-45a5-bf52-9205e5561b53","year":2019},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:15.503504Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:40829c41c4d05572caebfa7d3dbd7b6f272f2ec11872e47633cb46faaef1d4c8","observation_id":"885b4b84-f9cf-4666-89b9-1eddf68da088","resolution":{"observed_at":"2026-08-06T22:50:16.534788Z","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":"1902.04760","last_updated":"2020-04-04T22:53:19Z","snapshot_observed_at":"2026-08-18T09:45:12.030203Z","submitted_at":"2019-02-13T06:09:18Z","title":"Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.04760","snapshot_observed_at":"2026-08-06T22:50:15.749239Z","title":null,"venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:15.749239Z"},"links":{"cited_paper":"/paper/1902.04760","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:6b0dae4bf6f4945a1545c06b6107ec52846355844042337908a49ba239ea0135","observation_id":"182b4bf2-086e-478b-a7e5-4997fd1f11a4","resolution":{"observed_at":"2026-08-06T22:50:15.749239Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-06T22:50:13.370576Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:13.370576Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:c024f39b658d0e5e2c86415123999a925aa052925b0b88a6cc181ca973fe1cd3","observation_id":"a332630d-d8ed-4262-a49f-6f32e235eb1e","resolution":{"observed_at":"2026-08-06T22:50:13.370576Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.14522","last_updated":"2022-07-15T17:04:24Z","snapshot_observed_at":"2026-08-18T09:46:54.696672Z","submitted_at":"2020-11-30T03:21:05Z","title":"Feature Learning in Infinite-Width Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.14522","snapshot_observed_at":"2026-08-06T22:50:13.117590Z","title":null,"venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:13.117590Z"},"links":{"cited_paper":"/paper/2011.14522","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:30c7938eccc1d4bc4461ca1c52ae88c2b9d739a34d3ec0639ef039b119e6c8a1","observation_id":"6b15f366-c0a1-41dd-8aa3-21ed137496a3","resolution":{"observed_at":"2026-08-06T22:50:13.117590Z","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":"2026-08-06T22:50:18.009577Z","title":null,"venue":null,"work_id":"29a9e83d-761b-40e3-9875-872ebb073bc1","year":2024},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.072489Z"},"links":{"citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:f267a38154203d37768109afbcdbdb58a7ff312b2fffcda2631f17dd6f2e73e3","observation_id":"8decc2cc-64c6-4c65-89a0-bc6e92d4e8e4","resolution":{"observed_at":"2026-08-06T22:50:18.095224Z","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"}}],"paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T15:08:28.482973Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":27,"verified_exact":2,"verified_fuzzy":12},"total_outbound_references":42},"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 42 of 42 outbound references and 3 inbound Pith citation observations for arXiv:2506.20629."}