{"as_of":"2026-08-10T23:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:87f502455f8fced2607cd9507d76fdd72ed238ff91f6c8bc46d96927124ba864","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":7,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":7,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":7,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":7,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T17:18:51.447148Z","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":"2026-05-25T07:45:29.229067Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.20650","last_updated":"2024-10-28T01:12:20Z","snapshot_observed_at":"2026-08-03T13:26:49.608015Z","submitted_at":"2024-10-28T01:12:20Z","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.20650","snapshot_observed_at":"2026-08-09T17:18:51.447148Z","title":"Neuzip: Memory-efficient training and inference with dynamic compression of neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00922","last_updated":"2025-02-02T21:23:42Z","snapshot_observed_at":"2026-08-09T17:10:43.456007Z","submitted_at":"2025-02-02T21:23:42Z","title":"Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-09T17:18:51.447148Z"},"links":{"cited_paper":"/paper/2410.20650","citing_paper":"/paper/2502.00922"},"observation_digest":"sha256:bdc861b870e6ef86a941ebfa879d06df30955439bbd4cd1ecfbf41fec586a324","observation_id":"c5cb69f3-2a45-4c8c-a276-0dcbc753bf1a","resolution":{"observed_at":"2026-08-09T17:18:51.447148Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.20650","last_updated":"2024-10-28T01:12:20Z","snapshot_observed_at":"2026-08-03T13:26:49.608015Z","submitted_at":"2024-10-28T01:12:20Z","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.20650","snapshot_observed_at":"2026-08-07T13:06:24.124343Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22922","last_updated":"2025-05-28T22:51:43Z","snapshot_observed_at":"2026-08-10T19:45:26.924147Z","submitted_at":"2025-05-28T22:51:43Z","title":"Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T13:06:24.124343Z"},"links":{"cited_paper":"/paper/2410.20650","citing_paper":"/paper/2505.22922"},"observation_digest":"sha256:5258710bdb06692feb01e49709624085a18b1a0cb687ac0160fd29e44d61471e","observation_id":"e7f802d2-1356-4c3c-b566-b92d52f02a8f","resolution":{"observed_at":"2026-08-07T13:06:24.124343Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.20650","last_updated":"2024-10-28T01:12:20Z","snapshot_observed_at":"2026-08-03T13:26:49.608015Z","submitted_at":"2024-10-28T01:12:20Z","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","version":1},"cited_work":{"arxiv_id":"2410.20650","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.20650","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Neuzip: Memory-efficient training and inference with dynamic compression of neu- ral networks.arXiv preprint arXiv:2410.20650","venue":null,"work_id":"ad6450e5-d1a7-4e5a-b9ed-90a09261dbcd","year":2024},"citing_paper":{"arxiv_id":"2601.21198","last_updated":"2026-05-22T06:53:25Z","snapshot_observed_at":"2026-08-09T02:36:25.829599Z","submitted_at":"2026-01-29T02:51:59Z","title":"ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-25T07:43:24.937953Z"},"links":{"cited_paper":"/paper/2410.20650","citing_paper":"/paper/2601.21198"},"observation_digest":"sha256:078b5e40eee7a1ba6589c4ac59f64e5b0f1662c280e463f0ed20b90cd7733302","observation_id":"d01755f6-112e-43d7-ba2e-0552ac3dbdbe","resolution":{"observed_at":"2026-05-25T07:45:29.232988Z","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":"2410.20650","last_updated":"2024-10-28T01:12:20Z","snapshot_observed_at":"2026-08-03T13:26:49.608015Z","submitted_at":"2024-10-28T01:12:20Z","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","version":1},"cited_work":{"arxiv_id":"2410.20650","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.20650","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Neuzip: Memory-efficient training and inference with dynamic compression of neu- ral networks.arXiv preprint arXiv:2410.20650","venue":null,"work_id":"ad6450e5-d1a7-4e5a-b9ed-90a09261dbcd","year":2024},"citing_paper":{"arxiv_id":"2604.17172","last_updated":"2026-04-21T04:46:04Z","snapshot_observed_at":"2026-08-02T14:49:40.944781Z","submitted_at":"2026-04-19T00:05:36Z","title":"UCCL-Zip: Lossless Compression Supercharged GPU Communication","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-10T06:36:43.101810Z"},"links":{"cited_paper":"/paper/2410.20650","citing_paper":"/paper/2604.17172"},"observation_digest":"sha256:5aef7bfe3aa28845ffd90e9ed392424c91d924f9e709fa5c90117b265d9046cd","observation_id":"9378b614-90c0-49a7-8f23-605dda2ee45d","resolution":{"observed_at":"2026-05-10T06:41:37.149321Z","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":"2410.20650","last_updated":"2024-10-28T01:12:20Z","snapshot_observed_at":"2026-08-03T13:26:49.608015Z","submitted_at":"2024-10-28T01:12:20Z","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","version":1},"cited_work":{"arxiv_id":"2410.20650","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.20650","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Neuzip: Memory-efficient training and inference with dynamic compression of neu- ral networks.arXiv preprint arXiv:2410.20650","venue":null,"work_id":"ad6450e5-d1a7-4e5a-b9ed-90a09261dbcd","year":2024},"citing_paper":{"arxiv_id":"2604.27844","last_updated":"2026-04-30T13:29:59Z","snapshot_observed_at":"2026-07-06T23:13:15.994987Z","submitted_at":"2026-04-30T13:29:59Z","title":"ZipCCL: Efficient Lossless Data Compression of Communication Collectives for Accelerating LLM Training","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-07T05:22:35.487173Z"},"links":{"cited_paper":"/paper/2410.20650","citing_paper":"/paper/2604.27844"},"observation_digest":"sha256:da78aa0d71edde2d7e410d05293843415d0d27fa7f52bdd2da47c49d67b9d85e","observation_id":"1c7d173a-9662-4077-91b5-607f13790b52","resolution":{"observed_at":"2026-05-12T10:36:30.660630Z","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":"2410.20650","last_updated":"2024-10-28T01:12:20Z","snapshot_observed_at":"2026-08-03T13:26:49.608015Z","submitted_at":"2024-10-28T01:12:20Z","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","version":1},"cited_work":{"arxiv_id":"2410.20650","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.20650","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Neuzip: Memory-efficient training and inference with dynamic compression of neu- ral networks.arXiv preprint arXiv:2410.20650","venue":null,"work_id":"ad6450e5-d1a7-4e5a-b9ed-90a09261dbcd","year":2024},"citing_paper":{"arxiv_id":"2605.19195","last_updated":"2026-05-18T23:51:02Z","snapshot_observed_at":"2026-07-06T23:29:57.003383Z","submitted_at":"2026-05-18T23:51:02Z","title":"The Thermodynamic Costs of Simple Linear Regression","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-20T07:03:21.987679Z"},"links":{"cited_paper":"/paper/2410.20650","citing_paper":"/paper/2605.19195"},"observation_digest":"sha256:432bb51eddb5b5970da0cafe0879b634d93deeec0fce83b3fde877f8bfd0f050","observation_id":"58226f75-2db8-4e39-a2fd-3460920d3b47","resolution":{"observed_at":"2026-05-20T07:03:23.209733Z","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":"2410.20650","last_updated":"2024-10-28T01:12:20Z","snapshot_observed_at":"2026-08-03T13:26:49.608015Z","submitted_at":"2024-10-28T01:12:20Z","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.20650","snapshot_observed_at":"2026-08-04T13:34:08.176469Z","title":"arXiv preprint arXiv:2410.20650 , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02162","last_updated":"2026-08-03T12:42:55Z","snapshot_observed_at":"2026-08-10T16:23:30.774671Z","submitted_at":"2026-08-03T12:42:55Z","title":"Lossless Tensor Compression as Program Synthesis","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-04T13:34:08.176469Z"},"links":{"cited_paper":"/paper/2410.20650","citing_paper":"/paper/2608.02162"},"observation_digest":"sha256:821647668af01d09ccdbe5d1f61d740b0daead12c2a0e1e43b7bb5aa31c901bc","observation_id":"ce395b26-780c-4223-921c-b93eea05ab65","resolution":{"observed_at":"2026-08-04T13:34:08.176469Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2410.20650/citation-record","integrity":"/paper/2410.20650/integrity","json":"/paper/2410.20650/citation-record.json","paper":"/paper/2410.20650"},"outbound":[],"paper":{"arxiv_id":"2410.20650","last_updated":"2024-10-28T01:12:20Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-03T13:26:49.608015Z","submitted_at":"2024-10-28T01:12:20Z","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks"},"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 7 inbound Pith citation observations for arXiv:2410.20650."}