{"as_of":"2026-08-10T09:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:91c0e420fa8cb697feac300b64b2a20042a6d3b85513eedf46ee38ef08c8a9f8","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":14,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T13:44:00.593433Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T10:39:45.481307Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04564","snapshot_observed_at":"2026-08-08T13:44:00.593433Z","title":"Relu strikes back: Exploiting activation sparsity in large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.07832","last_updated":"2025-02-11T00:21:40Z","snapshot_observed_at":"2026-08-10T01:10:52.838340Z","submitted_at":"2025-02-11T00:21:40Z","title":"SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-08T13:44:00.593433Z"},"links":{"cited_paper":"/paper/2310.04564","citing_paper":"/paper/2502.07832"},"observation_digest":"sha256:055d134c085c1723dbe3d552752d72e7a7ad8b16a581a9edeb84acd7f6416752","observation_id":"b1b78aea-63f9-44a5-ac99-833b591b03f4","resolution":{"observed_at":"2026-08-08T13:44:00.593433Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04564","snapshot_observed_at":"2026-08-07T20:07:26.248303Z","title":"C., Tuzel, O., Samei, G., Rastegari, M., and Farajtabar, M","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.09954","last_updated":"2025-02-14T07:22:24Z","snapshot_observed_at":"2026-08-08T19:07:06.691842Z","submitted_at":"2025-02-14T07:22:24Z","title":"On Space Folds of ReLU Neural Networks","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T20:07:26.248303Z"},"links":{"cited_paper":"/paper/2310.04564","citing_paper":"/paper/2502.09954"},"observation_digest":"sha256:1706dfe956574c3a0fe470bccdcf305d5ab6bf784491d54c30d5425d445dac02","observation_id":"6808688d-741c-4180-8c1e-8b95383694c9","resolution":{"observed_at":"2026-08-07T20:07:26.248303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","version":1},"cited_work":{"arxiv_id":"2310.04564","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.04564","snapshot_observed_at":"2026-07-04T10:39:45.481307Z","title":"Relu strikes back: Exploiting activation sparsity in large language models","venue":null,"work_id":"f7aa58e5-b867-424f-8eab-054e4374bda9","year":2023},"citing_paper":{"arxiv_id":"2506.06374","last_updated":"2026-04-20T13:03:47Z","snapshot_observed_at":"2026-07-06T21:38:10.885548Z","submitted_at":"2025-06-04T13:54:02Z","title":"SiLIF: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-19T11:05:05.783726Z"},"links":{"cited_paper":"/paper/2310.04564","citing_paper":"/paper/2506.06374"},"observation_digest":"sha256:5cbba524bc292db11260c56aebf02ecdb9ee0f77fa107c57f95f380f4e88b8cd","observation_id":"bd293422-dbdf-40b9-8a85-9fd138d28d84","resolution":{"observed_at":"2026-05-19T11:07:15.260111Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04564","snapshot_observed_at":"2026-08-06T18:20:00.326711Z","title":"ReLU strikes back: Exploiting activation sparsity in large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.08771","last_updated":"2025-07-30T04:14:15Z","snapshot_observed_at":"2026-08-07T06:32:52.508610Z","submitted_at":"2025-07-11T17:28:56Z","title":"BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-06T18:20:00.326711Z"},"links":{"cited_paper":"/paper/2310.04564","citing_paper":"/paper/2507.08771"},"observation_digest":"sha256:ef29c3d2f0c3305bc9050f7c1a07eec9c4af6a574b56553492b090ff725fe51a","observation_id":"d7dd08c2-2153-43ea-a3d4-cf8960f2ad0a","resolution":{"observed_at":"2026-08-06T18:20:00.326711Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04564","snapshot_observed_at":"2026-08-06T05:11:11.632490Z","title":"C.; Tuzel, O.; Samei, G.; Rastegari, M.; and Farajtabar, M","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.02128","last_updated":"2025-08-04T07:22:36Z","snapshot_observed_at":"2026-08-08T06:49:38.643278Z","submitted_at":"2025-08-04T07:22:36Z","title":"Amber Pruner: Leveraging N:M Activation Sparsity for Efficient Prefill in Large Language Models","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-06T05:11:11.632490Z"},"links":{"cited_paper":"/paper/2310.04564","citing_paper":"/paper/2508.02128"},"observation_digest":"sha256:aa5b203f3e00b8d49db0a699a20dd27aae05dd70fb704d365e2e131b5134a759","observation_id":"bff4c606-33e3-4f43-8258-bc8ccc9cd123","resolution":{"observed_at":"2026-08-06T05:11:11.632490Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","version":1},"cited_work":{"arxiv_id":"2310.04564","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.04564","snapshot_observed_at":"2026-07-04T10:39:45.481307Z","title":"Relu strikes back: Exploiting activation sparsity in large language models","venue":null,"work_id":"f7aa58e5-b867-424f-8eab-054e4374bda9","year":2023},"citing_paper":{"arxiv_id":"2509.22166","last_updated":"2026-04-24T11:44:43Z","snapshot_observed_at":"2026-07-06T22:30:50.642382Z","submitted_at":"2025-09-26T10:27:55Z","title":"Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-18T13:36:55.938673Z"},"links":{"cited_paper":"/paper/2310.04564","citing_paper":"/paper/2509.22166"},"observation_digest":"sha256:7c59ed9609699b52de512d680f33a603d626b5189feeaab1ec79d16bd4bbd9f7","observation_id":"ca45b6e4-f873-4409-b5d2-5e1678fa5859","resolution":{"observed_at":"2026-05-18T13:41:25.911858Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","version":1},"cited_work":{"arxiv_id":"2310.04564","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.04564","snapshot_observed_at":"2026-07-04T10:39:45.481307Z","title":"Relu strikes back: Exploiting activation sparsity in large language models","venue":null,"work_id":"f7aa58e5-b867-424f-8eab-054e4374bda9","year":2023},"citing_paper":{"arxiv_id":"2512.12744","last_updated":"2026-05-21T01:18:21Z","snapshot_observed_at":"2026-08-07T14:28:26.092742Z","submitted_at":"2025-12-14T15:47:40Z","title":"Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-16T22:19:25.483640Z"},"links":{"cited_paper":"/paper/2310.04564","citing_paper":"/paper/2512.12744"},"observation_digest":"sha256:2315f8289c73291ee7f7b6d37dd7e1f004d40db24da48b40b45df054f183afa3","observation_id":"34ef5469-d50a-449e-953e-bad2ed9724c5","resolution":{"observed_at":"2026-05-16T22:21:19.000745Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","version":1},"cited_work":{"arxiv_id":"2310.04564","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.04564","snapshot_observed_at":"2026-07-04T10:39:45.481307Z","title":"Relu strikes back: Exploiting activation sparsity in large language models","venue":null,"work_id":"f7aa58e5-b867-424f-8eab-054e4374bda9","year":2023},"citing_paper":{"arxiv_id":"2512.12744","last_updated":"2026-05-21T01:18:21Z","snapshot_observed_at":"2026-08-07T14:28:26.092742Z","submitted_at":"2025-12-14T15:47:40Z","title":"Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-22T11:54:29.436149Z"},"links":{"cited_paper":"/paper/2310.04564","citing_paper":"/paper/2512.12744"},"observation_digest":"sha256:c655020c50aa7074bb1ca6826a29934b10182a417685d6209b7a2bbfa074e531","observation_id":"4ae7e717-d6a6-4997-bbad-e62565ee0d79","resolution":{"observed_at":"2026-05-22T11:54:51.122320Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","version":1},"cited_work":{"arxiv_id":"2310.04564","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.04564","snapshot_observed_at":"2026-07-04T10:39:45.481307Z","title":"Relu strikes back: Exploiting activation sparsity in large language models","venue":null,"work_id":"f7aa58e5-b867-424f-8eab-054e4374bda9","year":2023},"citing_paper":{"arxiv_id":"2605.25704","last_updated":"2026-05-25T11:02:05Z","snapshot_observed_at":"2026-08-06T10:25:26.859166Z","submitted_at":"2026-05-25T11:02:05Z","title":"PowLU: An Activation Function for Stable Pre-Training of LLMs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-29T21:48:45.339523Z"},"links":{"cited_paper":"/paper/2310.04564","citing_paper":"/paper/2605.25704"},"observation_digest":"sha256:3162fcf3ec9a9eb52f927cdc3bb35123eed645bb79c764536cfc6c6825042b1c","observation_id":"d0cf46d7-a057-4c14-ab32-228a08bc9970","resolution":{"observed_at":"2026-06-29T21:53:59.458769Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","version":1},"cited_work":{"arxiv_id":"2310.04564","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.04564","snapshot_observed_at":"2026-07-04T10:39:45.481307Z","title":"Relu strikes back: Exploiting activation sparsity in large language models","venue":null,"work_id":"f7aa58e5-b867-424f-8eab-054e4374bda9","year":2023},"citing_paper":{"arxiv_id":"2605.26632","last_updated":"2026-06-01T03:03:29Z","snapshot_observed_at":"2026-07-06T23:36:29.930024Z","submitted_at":"2026-05-26T07:09:49Z","title":"RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-06-29T19:40:42.033793Z"},"links":{"cited_paper":"/paper/2310.04564","citing_paper":"/paper/2605.26632"},"observation_digest":"sha256:6ccb89792177a7e6bcebc639a0af9803460592d6bfdf9f074b1025c11824df02","observation_id":"707f502b-e8d0-49b9-bf84-1847f5a5d9ba","resolution":{"observed_at":"2026-06-29T19:43:54.732489Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","version":1},"cited_work":{"arxiv_id":"2310.04564","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.04564","snapshot_observed_at":"2026-07-04T10:39:45.481307Z","title":"Relu strikes back: Exploiting activation sparsity in large language models","venue":null,"work_id":"f7aa58e5-b867-424f-8eab-054e4374bda9","year":2023},"citing_paper":{"arxiv_id":"2606.07495","last_updated":"2026-06-05T17:49:19Z","snapshot_observed_at":"2026-08-05T16:38:31.972892Z","submitted_at":"2026-06-05T17:49:19Z","title":"Second-Order Path Kernel Interpolation Formulas in Machine Learning","version":1},"reference_index":162,"source":"arxiv_source","source_observed_at":"2026-06-27T22:20:15.074286Z"},"links":{"cited_paper":"/paper/2310.04564","citing_paper":"/paper/2606.07495"},"observation_digest":"sha256:0a3eee437170d7e64148a5bdf0b97f69e103aab6ef18c11389b085331822969a","observation_id":"e2b2e5c2-07be-427a-9258-b8e15e13b9cd","resolution":{"observed_at":"2026-07-02T16:47:10.323933Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","version":1},"cited_work":{"arxiv_id":"2310.04564","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.04564","snapshot_observed_at":"2026-07-04T10:39:45.481307Z","title":"Relu strikes back: Exploiting activation sparsity in large language models","venue":null,"work_id":"f7aa58e5-b867-424f-8eab-054e4374bda9","year":2023},"citing_paper":{"arxiv_id":"2606.23419","last_updated":"2026-06-22T14:42:34Z","snapshot_observed_at":"2026-07-06T23:58:11.694332Z","submitted_at":"2026-06-22T14:42:34Z","title":"GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-26T08:38:32.577228Z"},"links":{"cited_paper":"/paper/2310.04564","citing_paper":"/paper/2606.23419"},"observation_digest":"sha256:58d89d4cb99cbb4cdcb8b3b40d6f0f13dc00cdffd591ad940878df25b7d64671","observation_id":"df2560b8-dcd8-4468-b7d2-f7cab059ea2e","resolution":{"observed_at":"2026-07-04T10:39:45.482722Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04564","snapshot_observed_at":"2026-08-01T17:31:48.435407Z","title":"Relu strikes back: Exploiting activation sparsity in large language models.arXiv:2310.04564,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17624","last_updated":"2026-07-20T07:26:17Z","snapshot_observed_at":"2026-08-07T13:43:21.717264Z","submitted_at":"2026-07-20T07:26:17Z","title":"Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T17:31:48.435407Z"},"links":{"cited_paper":"/paper/2310.04564","citing_paper":"/paper/2607.17624"},"observation_digest":"sha256:e263691b280bc390160114276cf474a81e23fd0dbf046476b99f2288341638b0","observation_id":"046a4b1d-a727-4c83-8e61-70a51656693c","resolution":{"observed_at":"2026-08-01T17:31:48.435407Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04564","snapshot_observed_at":"2026-08-01T16:14:37.754503Z","title":"Relu strikes back: Exploiting activation sparsity in large language models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18081","last_updated":"2026-07-20T15:48:33Z","snapshot_observed_at":"2026-08-09T00:33:39.066758Z","submitted_at":"2026-07-20T15:48:33Z","title":"SelectInfer: Selective Neuron Loading and Computation for On-Device LLMs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T16:14:37.754503Z"},"links":{"cited_paper":"/paper/2310.04564","citing_paper":"/paper/2607.18081"},"observation_digest":"sha256:2b0368151381ac22f7d814292dbea7fb52904ef65c58179679e6e6d504d34835","observation_id":"f4298369-c51b-4d2d-b6cc-71adf6e1b86a","resolution":{"observed_at":"2026-08-01T16:14:37.754503Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2310.04564/citation-record","integrity":"/paper/2310.04564/integrity","json":"/paper/2310.04564/citation-record.json","paper":"/paper/2310.04564"},"outbound":[],"paper":{"arxiv_id":"2310.04564","last_updated":"2023-10-06T20:01:33Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-05T22:58:03.938093Z","submitted_at":"2023-10-06T20:01:33Z","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 14 inbound Pith citation observations for arXiv:2310.04564."}