{"as_of":"2026-08-10T11:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1e0ee07cad2f65a2753ca52b46426ce6b917cc3d13a0a8eaf30dc0e1793d8c60","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":10,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":10,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":10,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":10,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T04:22:45.225224Z","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":"2026-07-04T08:19:44.242007Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.17691","last_updated":"2024-11-27T02:51:04Z","snapshot_observed_at":"2026-08-10T08:51:36.594216Z","submitted_at":"2024-11-26T18:57:58Z","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.17691","snapshot_observed_at":"2026-08-07T15:41:08.080609Z","title":"Low-bit quantization favors undertrained llms: Scaling laws for quantized llms with 100t training tokens.arXiv preprint arXiv:2411.17691, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.14302","last_updated":"2025-05-20T12:54:43Z","snapshot_observed_at":"2026-08-07T15:43:23.244437Z","submitted_at":"2025-05-20T12:54:43Z","title":"Scaling Law for Quantization-Aware Training","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T15:41:08.080609Z"},"links":{"cited_paper":"/paper/2411.17691","citing_paper":"/paper/2505.14302"},"observation_digest":"sha256:b8399659b5f5d9a691e3497c1392ed067658b89eda98622282f922b016c9e9d5","observation_id":"6c252e7d-47d1-4d0f-9ca1-9490a2a02c51","resolution":{"observed_at":"2026-08-07T15:41:08.080609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.17691","last_updated":"2024-11-27T02:51:04Z","snapshot_observed_at":"2026-08-10T08:51:36.594216Z","submitted_at":"2024-11-26T18:57:58Z","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.17691","snapshot_observed_at":"2026-08-06T22:47:52.264775Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20752","last_updated":"2025-06-25T18:25:08Z","snapshot_observed_at":"2026-08-09T12:08:21.616173Z","submitted_at":"2025-06-25T18:25:08Z","title":"Characterization and Mitigation of Training Instabilities in Microscaling Formats","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-06T22:47:52.264775Z"},"links":{"cited_paper":"/paper/2411.17691","citing_paper":"/paper/2506.20752"},"observation_digest":"sha256:113aa0c70867eca8e9e8657fa9e149ee270c9664e703ca3ad7a5a2af973a36bb","observation_id":"f2ea6853-3d3e-4e80-bfc8-c247008de273","resolution":{"observed_at":"2026-08-06T22:47:52.264775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.17691","last_updated":"2024-11-27T02:51:04Z","snapshot_observed_at":"2026-08-10T08:51:36.594216Z","submitted_at":"2024-11-26T18:57:58Z","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","version":2},"cited_work":{"arxiv_id":"2411.17691","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.17691","snapshot_observed_at":"2026-07-04T08:19:44.242007Z","title":"Low-bit quantization favors undertrained LLMs: Scaling laws for quantized LLMs with 100t training tokens","venue":null,"work_id":"9095d0c3-b9f7-4b56-b439-d78fb9c53c24","year":2024},"citing_paper":{"arxiv_id":"2508.06974","last_updated":"2026-05-18T12:47:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-08-09T13:00:16Z","title":"Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-21T23:44:01.953344Z"},"links":{"cited_paper":"/paper/2411.17691","citing_paper":"/paper/2508.06974"},"observation_digest":"sha256:852ceab540849c51859e0b140df96094c96b5e4dd28cfc9d52386a3c01301021","observation_id":"7fddf69d-67b1-4f3b-b97f-3c33b387aaf9","resolution":{"observed_at":"2026-05-21T23:44:26.595598Z","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":"2411.17691","last_updated":"2024-11-27T02:51:04Z","snapshot_observed_at":"2026-08-10T08:51:36.594216Z","submitted_at":"2024-11-26T18:57:58Z","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","version":2},"cited_work":{"arxiv_id":"2411.17691","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.17691","snapshot_observed_at":"2026-07-04T08:19:44.242007Z","title":"Low-bit quantization favors undertrained LLMs: Scaling laws for quantized LLMs with 100t training tokens","venue":null,"work_id":"9095d0c3-b9f7-4b56-b439-d78fb9c53c24","year":2024},"citing_paper":{"arxiv_id":"2604.19167","last_updated":"2026-04-21T07:25:02Z","snapshot_observed_at":"2026-07-06T23:05:53.378585Z","submitted_at":"2026-04-21T07:25:02Z","title":"LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation","version":1},"reference_index":100,"source":"arxiv_source","source_observed_at":"2026-05-10T03:04:14.900791Z"},"links":{"cited_paper":"/paper/2411.17691","citing_paper":"/paper/2604.19167"},"observation_digest":"sha256:83b2644a15de13469d53dcc1229ea5f603a85f297b4c5a9c1f07702a760626c8","observation_id":"8927b930-967d-4780-bf3a-ff9f647b04da","resolution":{"observed_at":"2026-05-11T12:46:04.726341Z","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":"2411.17691","last_updated":"2024-11-27T02:51:04Z","snapshot_observed_at":"2026-08-10T08:51:36.594216Z","submitted_at":"2024-11-26T18:57:58Z","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","version":2},"cited_work":{"arxiv_id":"2411.17691","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.17691","snapshot_observed_at":"2026-07-04T08:19:44.242007Z","title":"Low-bit quantization favors undertrained LLMs: Scaling laws for quantized LLMs with 100t training tokens","venue":null,"work_id":"9095d0c3-b9f7-4b56-b439-d78fb9c53c24","year":2024},"citing_paper":{"arxiv_id":"2604.21254","last_updated":"2026-07-02T01:19:03Z","snapshot_observed_at":"2026-08-06T10:48:44.855597Z","submitted_at":"2026-04-23T03:46:14Z","title":"Hyperloop Transformers","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-09T23:09:35.640412Z"},"links":{"cited_paper":"/paper/2411.17691","citing_paper":"/paper/2604.21254"},"observation_digest":"sha256:f15ad514befbf6170e20402b8d52c8609e14cfa31147a46d8a17adba9e6d0adb","observation_id":"634a03fe-9213-4221-ace5-09bea61f201f","resolution":{"observed_at":"2026-05-11T14:16:04.399141Z","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":"2411.17691","last_updated":"2024-11-27T02:51:04Z","snapshot_observed_at":"2026-08-10T08:51:36.594216Z","submitted_at":"2024-11-26T18:57:58Z","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","version":2},"cited_work":{"arxiv_id":"2411.17691","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.17691","snapshot_observed_at":"2026-07-04T08:19:44.242007Z","title":"Low-bit quantization favors undertrained LLMs: Scaling laws for quantized LLMs with 100t training tokens","venue":null,"work_id":"9095d0c3-b9f7-4b56-b439-d78fb9c53c24","year":2024},"citing_paper":{"arxiv_id":"2604.24273","last_updated":"2026-04-27T10:03:37Z","snapshot_observed_at":"2026-07-06T23:10:20.676482Z","submitted_at":"2026-04-27T10:03:37Z","title":"BitRL: Reinforcement Learning with 1-bit Quantized Language Models for Resource-Constrained Edge Deployment","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-08T04:23:26.079298Z"},"links":{"cited_paper":"/paper/2411.17691","citing_paper":"/paper/2604.24273"},"observation_digest":"sha256:80f6f339890fe1878e4e406e16fad457c7bd8263c0fb096cf12ba014b67b14a1","observation_id":"38216f5d-312e-456c-bafe-110d40f0bde7","resolution":{"observed_at":"2026-05-11T21:46:43.044744Z","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":"2411.17691","last_updated":"2024-11-27T02:51:04Z","snapshot_observed_at":"2026-08-10T08:51:36.594216Z","submitted_at":"2024-11-26T18:57:58Z","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","version":2},"cited_work":{"arxiv_id":"2411.17691","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.17691","snapshot_observed_at":"2026-07-04T08:19:44.242007Z","title":"Low-bit quantization favors undertrained LLMs: Scaling laws for quantized LLMs with 100t training tokens","venue":null,"work_id":"9095d0c3-b9f7-4b56-b439-d78fb9c53c24","year":2024},"citing_paper":{"arxiv_id":"2605.21171","last_updated":"2026-05-20T13:41:53Z","snapshot_observed_at":"2026-07-06T23:31:37.061253Z","submitted_at":"2026-05-20T13:41:53Z","title":"FTerViT: Fully Ternary Vision Transformer","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-21T05:59:54.807460Z"},"links":{"cited_paper":"/paper/2411.17691","citing_paper":"/paper/2605.21171"},"observation_digest":"sha256:8a81d2467844c0f9850bcd0bd52048b029a9210ec957e38ee956ffbb638f7350","observation_id":"e24e0882-ef18-4a92-af51-d1b21124b206","resolution":{"observed_at":"2026-05-21T06:03:59.476277Z","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":"2411.17691","last_updated":"2024-11-27T02:51:04Z","snapshot_observed_at":"2026-08-10T08:51:36.594216Z","submitted_at":"2024-11-26T18:57:58Z","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","version":2},"cited_work":{"arxiv_id":"2411.17691","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.17691","snapshot_observed_at":"2026-07-04T08:19:44.242007Z","title":"Low-bit quantization favors undertrained LLMs: Scaling laws for quantized LLMs with 100t training tokens","venue":null,"work_id":"9095d0c3-b9f7-4b56-b439-d78fb9c53c24","year":2024},"citing_paper":{"arxiv_id":"2605.23901","last_updated":"2026-05-22T17:59:38Z","snapshot_observed_at":"2026-07-06T23:34:03.934151Z","submitted_at":"2026-05-22T17:59:38Z","title":"LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-25T04:30:35.962947Z"},"links":{"cited_paper":"/paper/2411.17691","citing_paper":"/paper/2605.23901"},"observation_digest":"sha256:059165bf466e8cb70e8a833a8bed84d8cb7667b54e671f7c35234f830955699b","observation_id":"dbd5c2c7-0cad-45fd-b40b-7b151f9c0f79","resolution":{"observed_at":"2026-05-25T04:35:21.786530Z","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":"2411.17691","last_updated":"2024-11-27T02:51:04Z","snapshot_observed_at":"2026-08-10T08:51:36.594216Z","submitted_at":"2024-11-26T18:57:58Z","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","version":2},"cited_work":{"arxiv_id":"2411.17691","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.17691","snapshot_observed_at":"2026-07-04T08:19:44.242007Z","title":"Low-bit quantization favors undertrained LLMs: Scaling laws for quantized LLMs with 100t training tokens","venue":null,"work_id":"9095d0c3-b9f7-4b56-b439-d78fb9c53c24","year":2024},"citing_paper":{"arxiv_id":"2606.22249","last_updated":"2026-06-20T22:22:26Z","snapshot_observed_at":"2026-08-06T20:47:52.441640Z","submitted_at":"2026-06-20T22:22:26Z","title":"On the Expressive Power of Weight Quantization in Large Language Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-26T11:53:45.787243Z"},"links":{"cited_paper":"/paper/2411.17691","citing_paper":"/paper/2606.22249"},"observation_digest":"sha256:790d41b094be2fd8a6063b1318d7207071de65438fbbf9b4fa790f21e2fc0638","observation_id":"15fb61d1-308b-4cc1-aa01-cebb11a8ea88","resolution":{"observed_at":"2026-07-04T08:19:44.243529Z","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":"2411.17691","last_updated":"2024-11-27T02:51:04Z","snapshot_observed_at":"2026-08-10T08:51:36.594216Z","submitted_at":"2024-11-26T18:57:58Z","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.17691","snapshot_observed_at":"2026-08-10T04:22:45.225224Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.06564","last_updated":"2026-08-06T20:22:21Z","snapshot_observed_at":"2026-08-10T10:10:18.637529Z","submitted_at":"2026-08-06T20:22:21Z","title":"Quantization Damage Is Multiplicative, Not Additive","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-10T04:22:45.225224Z"},"links":{"cited_paper":"/paper/2411.17691","citing_paper":"/paper/2608.06564"},"observation_digest":"sha256:cd0e1a17d312aaa34dbede8437716a4ef5039971ddb20a38ac7d9a87f7cfa583","observation_id":"7005b6a1-ea7b-48ef-b0fa-8a5d36162a49","resolution":{"observed_at":"2026-08-10T04:22:45.225224Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2411.17691/citation-record","integrity":"/paper/2411.17691/integrity","json":"/paper/2411.17691/citation-record.json","paper":"/paper/2411.17691"},"outbound":[],"paper":{"arxiv_id":"2411.17691","last_updated":"2024-11-27T02:51:04Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T08:51:36.594216Z","submitted_at":"2024-11-26T18:57:58Z","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens"},"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 10 inbound Pith citation observations for arXiv:2411.17691."}