{"as_of":"2026-08-15T22:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b5337c67323d7b198a4f2f4135c419a31bc911a0406dffe078458270bbff7b72","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":"2026-08-15T06:32:42.880941+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":"2026-07-31T05:04:00.337750Z","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":"2026-07-03T04:57:38.354280Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.01043","last_updated":"2026-07-29T08:00:39Z","snapshot_observed_at":"2026-08-14T01:09:32.052334Z","submitted_at":"2025-05-02T06:33:25Z","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","version":2},"cited_work":{"arxiv_id":"2505.01043","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.01043","snapshot_observed_at":"2026-07-30T01:18:51.459998Z","title":"Low-precision training of large language models: Methods, challenges, and opportunities","venue":null,"work_id":"bf4a3b3b-fb8b-47f4-bc34-9c5da16141a0","year":2025},"citing_paper":{"arxiv_id":"2508.03306","last_updated":"2026-04-13T02:05:53Z","snapshot_observed_at":"2026-07-06T22:08:03.422557Z","submitted_at":"2025-08-05T10:27:57Z","title":"Reliable Evaluation Protocol for Low-Precision Retrieval","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-19T00:55:54.623814Z"},"links":{"cited_paper":"/paper/2505.01043","citing_paper":"/paper/2508.03306"},"observation_digest":"sha256:ceaeb44f864a75117bafd81ff17e98c30862e3b1f59e576b6fc2f96e9c36a1f7","observation_id":"59bbba49-12f8-46e9-84de-abfb8f8bae93","resolution":{"observed_at":"2026-07-30T01:18:51.459998Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.01043","last_updated":"2026-07-29T08:00:39Z","snapshot_observed_at":"2026-08-14T01:09:32.052334Z","submitted_at":"2025-05-02T06:33:25Z","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","version":2},"cited_work":{"arxiv_id":"2505.01043","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.01043","snapshot_observed_at":"2026-07-30T01:18:51.459998Z","title":"Low-precision training of large language models: Methods, challenges, and opportunities","venue":null,"work_id":"bf4a3b3b-fb8b-47f4-bc34-9c5da16141a0","year":2025},"citing_paper":{"arxiv_id":"2510.04212","last_updated":"2026-04-18T01:36:25Z","snapshot_observed_at":"2026-08-11T09:38:23.812338Z","submitted_at":"2025-10-05T14:01:24Z","title":"Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-18T10:01:56.131253Z"},"links":{"cited_paper":"/paper/2505.01043","citing_paper":"/paper/2510.04212"},"observation_digest":"sha256:b9853ffec665acb2c6998a42c877055fb82601509af3aea0fbfae72d0e79ca6f","observation_id":"51ef9cb5-1de1-4065-b39d-0102ff8bb07f","resolution":{"observed_at":"2026-07-30T01:18:51.459998Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.01043","last_updated":"2026-07-29T08:00:39Z","snapshot_observed_at":"2026-08-14T01:09:32.052334Z","submitted_at":"2025-05-02T06:33:25Z","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","version":2},"cited_work":{"arxiv_id":"2505.01043","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.01043","snapshot_observed_at":"2026-07-30T01:18:51.459998Z","title":"Low-precision training of large language models: Methods, challenges, and opportunities","venue":null,"work_id":"bf4a3b3b-fb8b-47f4-bc34-9c5da16141a0","year":2025},"citing_paper":{"arxiv_id":"2604.15416","last_updated":"2026-04-16T17:55:36Z","snapshot_observed_at":"2026-08-15T05:22:14.623643Z","submitted_at":"2026-04-16T17:55:36Z","title":"StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-10T12:10:44.802059Z"},"links":{"cited_paper":"/paper/2505.01043","citing_paper":"/paper/2604.15416"},"observation_digest":"sha256:319e4f853b8dad6f6cceef375f49c0c2c01219fa8cfe66bd5e7f9773b04fab14","observation_id":"39dce1fe-0db1-4a7d-9f44-71a1270f71df","resolution":{"observed_at":"2026-07-30T01:18:51.459998Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.01043","last_updated":"2026-07-29T08:00:39Z","snapshot_observed_at":"2026-08-14T01:09:32.052334Z","submitted_at":"2025-05-02T06:33:25Z","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","version":2},"cited_work":{"arxiv_id":"2505.01043","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.01043","snapshot_observed_at":"2026-07-30T01:18:51.459998Z","title":"Low-precision training of large language models: Methods, challenges, and opportunities","venue":null,"work_id":"bf4a3b3b-fb8b-47f4-bc34-9c5da16141a0","year":2025},"citing_paper":{"arxiv_id":"2605.20402","last_updated":"2026-06-02T02:26:08Z","snapshot_observed_at":"2026-08-15T03:35:20.310092Z","submitted_at":"2026-05-19T18:59:26Z","title":"Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-05-21T07:59:43.755196Z"},"links":{"cited_paper":"/paper/2505.01043","citing_paper":"/paper/2605.20402"},"observation_digest":"sha256:2d36b6837e1b7613cc1002bd1f3a081ff8687a10b658d32e5e3701fffd8963ab","observation_id":"36ec92df-01cd-4af2-b355-d84a91ac7ecf","resolution":{"observed_at":"2026-07-30T01:18:51.459998Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.01043","last_updated":"2026-07-29T08:00:39Z","snapshot_observed_at":"2026-08-14T01:09:32.052334Z","submitted_at":"2025-05-02T06:33:25Z","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","version":2},"cited_work":{"arxiv_id":"2505.01043","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.01043","snapshot_observed_at":"2026-07-30T01:18:51.459998Z","title":"Low-precision training of large language models: Methods, challenges, and opportunities","venue":null,"work_id":"bf4a3b3b-fb8b-47f4-bc34-9c5da16141a0","year":2025},"citing_paper":{"arxiv_id":"2605.20402","last_updated":"2026-06-02T02:26:08Z","snapshot_observed_at":"2026-08-15T03:35:20.310092Z","submitted_at":"2026-05-19T18:59:26Z","title":"Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-05-25T05:49:08.484663Z"},"links":{"cited_paper":"/paper/2505.01043","citing_paper":"/paper/2605.20402"},"observation_digest":"sha256:6a8784ec5d9aee47af9b35dcd43b9b512f5925a4c03e924a5addbbef402f38f5","observation_id":"abc6f417-a4f1-4143-805a-dffdfe2e8334","resolution":{"observed_at":"2026-07-30T01:18:51.459998Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.01043","last_updated":"2026-07-29T08:00:39Z","snapshot_observed_at":"2026-08-14T01:09:32.052334Z","submitted_at":"2025-05-02T06:33:25Z","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","version":2},"cited_work":{"arxiv_id":"2505.01043","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.01043","snapshot_observed_at":"2026-07-30T01:18:51.459998Z","title":"Low-precision training of large language models: Methods, challenges, and opportunities","venue":null,"work_id":"bf4a3b3b-fb8b-47f4-bc34-9c5da16141a0","year":2025},"citing_paper":{"arxiv_id":"2605.20402","last_updated":"2026-06-02T02:26:08Z","snapshot_observed_at":"2026-08-15T03:35:20.310092Z","submitted_at":"2026-05-19T18:59:26Z","title":"Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-06-30T18:01:38.509794Z"},"links":{"cited_paper":"/paper/2505.01043","citing_paper":"/paper/2605.20402"},"observation_digest":"sha256:25de5856ef0c817a67776ecf6d27b835647dcdf7f8cccf630ccd4f3d29046c9a","observation_id":"9c233b99-177d-4c2d-b369-b680d2585e10","resolution":{"observed_at":"2026-07-30T01:18:51.459998Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.01043","last_updated":"2026-07-29T08:00:39Z","snapshot_observed_at":"2026-08-14T01:09:32.052334Z","submitted_at":"2025-05-02T06:33:25Z","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","version":2},"cited_work":{"arxiv_id":"2505.01043","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.01043","snapshot_observed_at":"2026-07-30T01:18:51.459998Z","title":"Low-precision training of large language models: Methods, challenges, and opportunities","venue":null,"work_id":"bf4a3b3b-fb8b-47f4-bc34-9c5da16141a0","year":2025},"citing_paper":{"arxiv_id":"2605.25704","last_updated":"2026-05-25T11:02:05Z","snapshot_observed_at":"2026-08-12T13:45:58.344833Z","submitted_at":"2026-05-25T11:02:05Z","title":"PowLU: An Activation Function for Stable Pre-Training of LLMs","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-29T21:48:45.339523Z"},"links":{"cited_paper":"/paper/2505.01043","citing_paper":"/paper/2605.25704"},"observation_digest":"sha256:1ba080be7f6697043f675231215f82c0ee1dd9a26d787c33a509d62b64e56d19","observation_id":"c77a3e84-30d4-4fc4-a870-dbab44402c3f","resolution":{"observed_at":"2026-07-30T01:18:51.459998Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.01043","last_updated":"2026-07-29T08:00:39Z","snapshot_observed_at":"2026-08-14T01:09:32.052334Z","submitted_at":"2025-05-02T06:33:25Z","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","version":2},"cited_work":{"arxiv_id":"2505.01043","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.01043","snapshot_observed_at":"2026-07-30T01:18:51.459998Z","title":"Low-precision training of large language models: Methods, challenges, and opportunities","venue":null,"work_id":"bf4a3b3b-fb8b-47f4-bc34-9c5da16141a0","year":2025},"citing_paper":{"arxiv_id":"2606.10531","last_updated":"2026-07-01T03:38:14Z","snapshot_observed_at":"2026-08-14T20:45:52.009680Z","submitted_at":"2026-06-09T08:02:56Z","title":"LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-27T13:32:32.996055Z"},"links":{"cited_paper":"/paper/2505.01043","citing_paper":"/paper/2606.10531"},"observation_digest":"sha256:a31614eb4ac4806633f3b55289b8b7f738a1f67465614cf84b8074c598be51ae","observation_id":"f575022c-f983-4bbd-a8ee-d7a055aee18d","resolution":{"observed_at":"2026-07-30T01:18:51.459998Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.01043","last_updated":"2026-07-29T08:00:39Z","snapshot_observed_at":"2026-08-14T01:09:32.052334Z","submitted_at":"2025-05-02T06:33:25Z","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","version":2},"cited_work":{"arxiv_id":"2505.01043","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.01043","snapshot_observed_at":"2026-07-30T01:18:51.459998Z","title":"Low-precision training of large language models: Methods, challenges, and opportunities","venue":null,"work_id":"bf4a3b3b-fb8b-47f4-bc34-9c5da16141a0","year":2025},"citing_paper":{"arxiv_id":"2606.10531","last_updated":"2026-07-01T03:38:14Z","snapshot_observed_at":"2026-08-14T20:45:52.009680Z","submitted_at":"2026-06-09T08:02:56Z","title":"LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-02T22:47:05.759610Z"},"links":{"cited_paper":"/paper/2505.01043","citing_paper":"/paper/2606.10531"},"observation_digest":"sha256:b986ab18245500d85bfb061c1fbc83866466b1b396e040030eca6a84b8f4a168","observation_id":"e8f262cc-5885-442e-bd3d-e59dd40bb7d3","resolution":{"observed_at":"2026-07-30T01:18:51.459998Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.01043","last_updated":"2026-07-29T08:00:39Z","snapshot_observed_at":"2026-08-14T01:09:32.052334Z","submitted_at":"2025-05-02T06:33:25Z","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.01043","snapshot_observed_at":"2026-07-31T05:04:00.337750Z","title":"Low-precision training of large language models: Methods, challenges, and opportunities.arXiv preprint arXiv:2505.01043, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24953","last_updated":"2026-07-27T18:03:34Z","snapshot_observed_at":"2026-08-15T17:10:34.457103Z","submitted_at":"2026-07-27T18:03:34Z","title":"Stable FP4 Training via Transposition-Invariant Block Quantization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-31T05:04:00.337750Z"},"links":{"cited_paper":"/paper/2505.01043","citing_paper":"/paper/2607.24953"},"observation_digest":"sha256:a4786391a71f3a171b9dcbe384a0c7257b9b04db48b541aea32f2ee9f26813d3","observation_id":"8351f110-4e6f-40bb-b4c0-54b4054b48ed","resolution":{"observed_at":"2026-07-31T05:04:00.337750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.01043/citation-record","integrity":"/paper/2505.01043/integrity","json":"/paper/2505.01043/citation-record.json","paper":"/paper/2505.01043"},"outbound":[],"paper":{"arxiv_id":"2505.01043","last_updated":"2026-07-29T08:00:39Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T01:09:32.052334Z","submitted_at":"2025-05-02T06:33:25Z","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 10 inbound Pith citation observations for arXiv:2505.01043."}