{"as_of":"2026-08-19T23:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1806648f611bb31e5dc60a54216c8af50011a3ccdc1143d8b52f04e17f112ff1","coverage":[{"denominator":36,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":36,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T05:01:16.450014Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2508.02381/citation-record","integrity":"/paper/2508.02381/integrity","json":"/paper/2508.02381/citation-record.json","paper":"/paper/2508.02381"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T05:01:22.120020Z","title":null,"venue":null,"work_id":"71665441-368e-4809-a38b-6fa633457251","year":2024},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.247195Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:810f7ecd3a1eb7828bc0fb8f66f9456ceb67dc2322130cf76b4da6972df6cb26","observation_id":"0f74d977-bd55-4adc-957f-e585457f5dc1","resolution":{"observed_at":"2026-08-06T05:01:22.237573Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.03315","last_updated":"2021-02-05T17:41:43Z","snapshot_observed_at":"2026-08-16T18:47:26.912121Z","submitted_at":"2021-02-05T17:41:43Z","title":"Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.03315","snapshot_observed_at":"2026-08-06T05:01:16.252691Z","title":"D.; Richardson, K.; Sabharwal, A.; Schoenick, C.; Tafjord, O.; and Clark, P","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.252691Z"},"links":{"cited_paper":"/paper/2102.03315","citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:8e7ce1a9fdcf18604ccbb437b858bb139d8f7765ed8a231827ba9d0fbd1b9309","observation_id":"b0c61715-c566-4bd6-bec0-7e842dd5819d","resolution":{"observed_at":"2026-08-06T05:01:16.252691Z","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":"2026-08-06T05:01:21.953659Z","title":null,"venue":null,"work_id":"c2a8184b-881b-4ace-bcd6-db8154edbae1","year":2019},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.257468Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:37fd949c62b167d2c2684d03320de3eb3d903b325d7c722bd4e68e93cb1729be","observation_id":"93e7be23-1c25-402c-bba1-4e4bcb67ae78","resolution":{"observed_at":"2026-08-06T05:01:22.046687Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-06T05:01:16.262976Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.262976Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:49f4e8549a9cb8e67fc94e47d0de0a75ef0cd3039986cea0be2e5cbec6d66eda","observation_id":"32d86223-3363-4b0a-904a-90eeee416ac3","resolution":{"observed_at":"2026-08-06T05:01:16.262976Z","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":"2026-08-06T05:01:21.659006Z","title":"J.; Rodgers, P.; Kilpatrick, P.; Spence, I","venue":null,"work_id":"31d79c83-fe18-4aef-83d3-fb8d1cab29c5","year":2024},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.267888Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:f70be39dd9ccae028afbffc9d189543ead703afab5e4672954657c75d237c69d","observation_id":"d885cce9-3d41-45db-a366-19fd8dae7097","resolution":{"observed_at":"2026-08-06T05:01:21.799271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:21.354850Z","title":null,"venue":null,"work_id":"39a35835-3abd-408b-980f-b083d1d417c4","year":2018},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.272352Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:affe470d44cbedeed0303600efe93772b4469ddb879c15093df5166b3ade3b01","observation_id":"7eabdb1f-4650-4e5a-8bb6-0437849ec4db","resolution":{"observed_at":"2026-08-06T05:01:21.478968Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:21.040305Z","title":null,"venue":null,"work_id":"2c111a3f-5f01-470e-868b-eb59db201626","year":2024},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.277465Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:cacb5eabac785383bc3183f9a168700d530615543b3dda81b27241d895c7ea31","observation_id":"34a040a3-96e6-4c36-bb20-240b16b37d8b","resolution":{"observed_at":"2026-08-06T05:01:21.168166Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.16508","last_updated":"2025-05-29T08:56:27Z","snapshot_observed_at":"2026-08-19T14:30:32.965900Z","submitted_at":"2025-05-22T10:43:00Z","title":"Edge-First Language Model Inference: Models, Metrics, and Tradeoffs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.16508","snapshot_observed_at":"2026-08-06T05:01:16.281918Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.281918Z"},"links":{"cited_paper":"/paper/2505.16508","citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:67a281963c1a27fb7caca013babfbe051b13492f8f220c047a0a340987f6c26f","observation_id":"c66cbdd8-ecab-456e-a4b7-378d932f4f42","resolution":{"observed_at":"2026-08-06T05:01:16.281918Z","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":"2026-08-06T05:01:20.787795Z","title":null,"venue":null,"work_id":"3d470f97-b83b-48cd-bf3d-6b7f86cb2ad4","year":2024},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.286651Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:90f78cc946167c62e3b5d4a63605cd16bc36a80f942a5518cf5c67250d0300c3","observation_id":"e6dcfd99-0053-497f-bc7e-0d81812d79c3","resolution":{"observed_at":"2026-08-06T05:01:20.897697Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:20.529255Z","title":"J.; Abdul - Mageed, M.; Lakshmanan, L","venue":null,"work_id":"d49a9ddf-09e8-44d9-9fac-971a1ada2dac","year":2023},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.290988Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:fe171e5003e03292062150d1dc279dc2ab1b7f4806b2224d772b2b7e96e55793","observation_id":"3285f44c-53a3-4c30-b8a4-2eaa88d36861","resolution":{"observed_at":"2026-08-06T05:01:20.641663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.11233","last_updated":"2024-09-17T14:34:11Z","snapshot_observed_at":"2026-08-16T13:17:48.841827Z","submitted_at":"2024-09-17T14:34:11Z","title":"Evaluating the Impact of Compression Techniques on Task-Specific Performance of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.11233","snapshot_observed_at":"2026-08-06T05:01:16.295746Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.295746Z"},"links":{"cited_paper":"/paper/2409.11233","citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:cb7d76101f2d2b0122309ac4e5e031caddcd3211f78186f77995c74805a20e1c","observation_id":"8e484b19-b782-444d-af69-90807bee2b56","resolution":{"observed_at":"2026-08-06T05:01:16.295746Z","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":"2026-08-06T05:01:20.342171Z","title":null,"venue":null,"work_id":"fe4df815-aa09-4528-8392-44e6fcd33a39","year":2025},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.301044Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:639cffc694e679d48d68f46082b9e91c58ce342028b2b78ba87877b41c2dfd8b","observation_id":"94a42e4a-1c62-4307-9abd-19e98f0e4bbb","resolution":{"observed_at":"2026-08-06T05:01:20.430609Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:20.185585Z","title":null,"venue":null,"work_id":"2fa399ce-dfea-4f18-95ac-054a7d1127a3","year":2025},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.305534Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:169e9c5096bcd9ae2b4440c934db4ab0b068dd2f37f8111a6798fa8511e10ff6","observation_id":"5893f5d4-eee8-4dbe-848b-7459b4868f6b","resolution":{"observed_at":"2026-08-06T05:01:20.253921Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:19.965004Z","title":null,"venue":null,"work_id":"ee6f9485-e4ab-4d84-9fed-98f7edd08ca3","year":1991},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.309738Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:c8d63d263c365528094fe19de1d4313a61716564aa9f6bbaeed34db03412d5c5","observation_id":"e9356965-a272-4f4e-9105-58a6b2748d91","resolution":{"observed_at":"2026-08-06T05:01:20.046463Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.17138","last_updated":"2026-05-18T17:05:12Z","snapshot_observed_at":"2026-08-17T13:25:30.263845Z","submitted_at":"2025-05-22T06:12:42Z","title":"RAP: Runtime Adaptive Pruning for LLM Inference","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.17138","snapshot_observed_at":"2026-08-06T05:01:16.313765Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.313765Z"},"links":{"cited_paper":"/paper/2505.17138","citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:49f6db2440b33ca10080f05f00eb649b9b9232abf256b449aa447e053c74d69b","observation_id":"27c7f9dd-bcdf-47fc-afe8-a2c8a43a05e1","resolution":{"observed_at":"2026-08-06T05:01:16.313765Z","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":"2026-08-06T05:01:19.837305Z","title":"W.; and Yang, Y","venue":null,"work_id":"33536351-557b-4a3e-9568-8449b0a965d5","year":2024},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.318495Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:fa9c349dc9d345dccd2bde925aec7cdd1dd0c0a8a9642310649cde7269d8791e","observation_id":"9413720b-797d-483a-833c-fd987fbd9e9f","resolution":{"observed_at":"2026-08-06T05:01:19.887788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:19.623119Z","title":null,"venue":null,"work_id":"2c458dfd-64e6-41e5-a5aa-68bc214fb159","year":2023},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.322757Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:5e84563c783bd3e66505dc3228224978c9d8a5991aa53d3d55f267f6eacae170","observation_id":"07f439c6-d3d6-46d3-a7c6-93c64df99330","resolution":{"observed_at":"2026-08-06T05:01:19.736310Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:19.461889Z","title":"P.; Santorini, B.; and Marcinkiewicz, M","venue":null,"work_id":"5bf8ce8f-4d7a-487a-af19-e3aedc36a047","year":1993},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.326937Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:ca5287b9ebb0d2b24e203ee84238009ce1888f77b9462e8fdd05668f4ccc003e","observation_id":"85607d37-5730-465b-912b-95205e23ebb3","resolution":{"observed_at":"2026-08-06T05:01:19.503643Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:19.269804Z","title":null,"venue":null,"work_id":"d9bbce46-8a41-47f2-9db4-4b332e753e77","year":2025},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.331100Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:5ebc806387865cb16b9e6629b6a54c17578c743691d8261889cb1ceb1cade88c","observation_id":"a10b0b98-bbe3-4ef6-8f02-e5a9c0fe1b26","resolution":{"observed_at":"2026-08-06T05:01:19.358118Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:19.081859Z","title":null,"venue":null,"work_id":"bd4f3e13-02af-49a3-9199-4b09af0493e3","year":2017},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.335552Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:b98556353a46ad1e2032a3b9d487981770cb270159f768296d3f407496ac97b2","observation_id":"1b6c4212-dac2-4806-8a50-a746c6347958","resolution":{"observed_at":"2026-08-06T05:01:19.161036Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:18.859976Z","title":null,"venue":null,"work_id":"304b5771-93a7-4ffd-bf3b-d53f4fc0a296","year":2019},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.339600Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:7d8630d36c4d70c5c16fcb084a511f171fb6f3145418dda2d372b9b797309087","observation_id":"d4ba2ac6-88b3-4b9a-8e5a-bcc7b868f888","resolution":{"observed_at":"2026-08-06T05:01:18.961066Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:18.660858Z","title":null,"venue":null,"work_id":"66fa870e-c8d2-4813-8597-c6bbe0bd75a7","year":2018},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.343348Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:0954bfefa7845cc183362389a007edd71488cad3f51df214456d37c9a217e6b2","observation_id":"48818d6b-c28e-4399-9a36-f6828ed2c5dd","resolution":{"observed_at":"2026-08-06T05:01:18.782766Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:18.435119Z","title":"Z.; DeVito, Z.; Raison, M.; Tejani, A.; Chilamkurthy, S.; Steiner, B.; Fang, L.; Bai, J.; and Chintala, S","venue":null,"work_id":"2cae0a75-efc5-42ee-b841-20b5327822a1","year":2019},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.347282Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:40300d5324120885a32e799d1c2f0865b39ba93da5ab5863611a822ce7f68266","observation_id":"ffb4c5ea-2ce5-469e-84be-10945d4c0017","resolution":{"observed_at":"2026-08-06T05:01:18.506998Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:18.183281Z","title":"L.; Bhagavatula, C.; and Choi, Y","venue":null,"work_id":"cf6e3b8f-2df4-490e-ae46-b0e9665f1be9","year":2021},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.351477Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:7b984be4e3e76aea4d36f9e9ec8132e104cb3b76c763db5665f26d98b23ecf92","observation_id":"7ab6335e-3525-44f4-9e64-8554b2a3dcec","resolution":{"observed_at":"2026-08-06T05:01:18.312001Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:17.937974Z","title":null,"venue":null,"work_id":"5f3e980f-2e47-4cf7-adfd-ba2085ea34e5","year":2025},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.355776Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:881cab1461f0bcdef3e54d1fdb889ca5817c1e718833b79a70454a665b671b79","observation_id":"18985b8b-a67f-4c83-ae3c-6d9aa72a7a61","resolution":{"observed_at":"2026-08-06T05:01:18.046701Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:17.711427Z","title":null,"venue":null,"work_id":"8414ff3b-56e9-4778-b830-53462ad5660a","year":2024},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.359867Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:fab0be7903e04e65250ff17425f7950a4489effd6785fa25801a667a77fcf8cc","observation_id":"8055cdb0-df3f-4a87-ae03-6572eeb700ef","resolution":{"observed_at":"2026-08-06T05:01:17.828652Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-06T05:01:16.364093Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.364093Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:0e43bfe0fe445bde206f348a3fec3734c1596cfea1b9eaed164c1bd94d95ff71","observation_id":"5fce630e-2b1e-4573-a473-f7a1b39f6c74","resolution":{"observed_at":"2026-08-06T05:01:16.364093Z","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":"2026-08-06T05:01:17.521168Z","title":null,"venue":null,"work_id":"2920e2e7-2442-487d-9c8f-5f5868815e4c","year":2019},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.369510Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:e5be31b38eb1d769d96372220959bbd228971242165b52edb6088dafe999b7a8","observation_id":"564bf177-ca33-4628-a16c-6d35be08e170","resolution":{"observed_at":"2026-08-06T05:01:17.606604Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:17.327413Z","title":null,"venue":null,"work_id":"6dab0d24-7c19-455b-be86-975e24155636","year":2019},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.374196Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:52d93da770684bb420a41ea674752092b293e1ce225dbe89548b34bcdb92a335","observation_id":"37deaa0b-987d-4bec-ac37-eb13f2854841","resolution":{"observed_at":"2026-08-06T05:01:17.377642Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.03771","last_updated":"2020-07-14T03:42:34Z","snapshot_observed_at":"2026-07-06T08:27:58.343233Z","submitted_at":"2019-10-09T03:23:22Z","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.03771","snapshot_observed_at":"2026-08-06T05:01:16.380227Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.380227Z"},"links":{"cited_paper":"/paper/1910.03771","citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:b4754691e3e07469279fc05e7856d1a83d5578da265ceeafe5850d275d30573c","observation_id":"398becea-fcd2-42c0-a70b-11eb127dd9af","resolution":{"observed_at":"2026-08-06T05:01:16.380227Z","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":"2026-08-06T05:01:17.107519Z","title":"K.; Pechenizkiy, M.; Liang, Y.; Bendersky, M.; Wang, Z.; and Liu, S","venue":null,"work_id":"02feac3f-2a2b-4bad-9f55-5f679a08d7b0","year":2024},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.386990Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:cdf4db64158230d7862f496335b3ad6723bc9b2ab434440987f0911fe2029135","observation_id":"8225fbd9-68d8-4568-8c9a-f214e55a2d26","resolution":{"observed_at":"2026-08-06T05:01:17.202276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:16.905044Z","title":null,"venue":null,"work_id":"e61a37be-f7e3-4ab2-9073-1b1efbcbef4d","year":2019},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.392708Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:a72a0da348344561908536a713a882f1285bef7c47db0c7693e7f98c678d4d54","observation_id":"a70afdd4-f237-4652-bab7-6e7a1e47ce09","resolution":{"observed_at":"2026-08-06T05:01:16.975236Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10594","last_updated":"2025-05-22T04:58:06Z","snapshot_observed_at":"2026-08-19T18:23:30.667139Z","submitted_at":"2024-06-15T11:03:33Z","title":"BlockPruner: Fine-grained Pruning for Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10594","snapshot_observed_at":"2026-08-06T05:01:16.402118Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.402118Z"},"links":{"cited_paper":"/paper/2406.10594","citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:93b857820165aeb169d927ebfe36560cc9bac41ac639d6f8a8e9f97fc2091ecc","observation_id":"6fef4010-0458-46f8-96b0-18265d020eee","resolution":{"observed_at":"2026-08-06T05:01:16.402118Z","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":"2026-08-06T05:01:16.675431Z","title":null,"venue":null,"work_id":"61a25b11-6d90-4028-a90a-5503e130ecb8","year":2025},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.420093Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:e22b2b126a18af195d5abfd60a2707b0d591ef7832d5cf6f9da7063438971b92","observation_id":"21ad9091-d708-4c0d-b4c4-af5317af77e3","resolution":{"observed_at":"2026-08-06T05:01:16.791912Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T05:01:16.434668Z","title":", \" * write output.state after.block = add.period write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.434668Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:0ebfc20df88366d459837108c92921102662d217b6efe2c3cfea55126146200f","observation_id":"6bbb9ffa-fe73-472a-b5b0-2c6c9b6fee34","resolution":{"observed_at":"2026-08-06T05:01:16.434668Z","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":"2026-08-06T05:01:16.450014Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-06T05:01:16.450014Z"},"links":{"citing_paper":"/paper/2508.02381"},"observation_digest":"sha256:8a85265a2067a3e0586628ba6d599de297172f9ed3354564eb50043b75d7c63a","observation_id":"48430fd5-ac2e-40a6-b17d-3466aef1428a","resolution":{"observed_at":"2026-08-06T05:01:16.450014Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2508.02381","last_updated":"2025-08-06T03:44:36Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T09:11:20.528476Z","submitted_at":"2025-08-04T13:08:35Z","title":"Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs"},"reference_resolution":{"displayed":36,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":0,"verified_fuzzy":7},"total_outbound_references":36},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2508.02381."}