{"as_of":"2026-08-04T20:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c384c9c215f4f202cc5f7a9e4b88431fe5f4a8ab2b273cfccab5aae5ae49bb5e","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":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":20,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T14:45:25.730104Z","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":"2026-07-04T17:29:59.598269Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2506.12040","last_updated":"2026-04-09T06:22:06Z","snapshot_observed_at":"2026-08-02T23:24:15.663595Z","submitted_at":"2025-05-24T03:57:19Z","title":"BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-19T14:03:35.214840Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2506.12040"},"observation_digest":"sha256:0ee27f39638093c645f3314b1f55cd4bff43e0c4df746613c574f27ad76c7dde","observation_id":"1a65a08d-29e5-4f7d-828b-3f25473f029d","resolution":{"observed_at":"2026-05-19T14:07:20.532683Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","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":14,"source":"pdf_text","source_observed_at":"2026-05-21T23:44:01.953344Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2508.06974"},"observation_digest":"sha256:48253749eae0f746d9db0cabe54606754ea9a2e9e36aac6d42c4be2895756037","observation_id":"11bbacbb-8d30-4d7a-ba15-e6e76bdae4f2","resolution":{"observed_at":"2026-05-21T23:44:26.527117Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-08-04T14:45:25.730104Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.23729","last_updated":"2026-06-22T01:59:29Z","snapshot_observed_at":"2026-08-04T14:45:06.856563Z","submitted_at":"2025-09-28T08:20:00Z","title":"LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-04T14:45:25.730104Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2509.23729"},"observation_digest":"sha256:ee007fa2b67a7f534124e61d081ebea3795d2576c8ec8cb115e0d2212fad099c","observation_id":"7b9e6b2c-648b-4a37-a865-b7c538e05716","resolution":{"observed_at":"2026-08-04T14:45:25.730104Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2510.04595","last_updated":"2026-04-12T08:00:47Z","snapshot_observed_at":"2026-08-04T00:21:27.591930Z","submitted_at":"2025-10-06T08:49:04Z","title":"SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-18T09:44:53.290259Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2510.04595"},"observation_digest":"sha256:bfd1492c9b90f90d972be037733407e8f2539498f2752a5491420ac8b813d8cb","observation_id":"484e2527-2485-4734-b792-761a3c65e4f0","resolution":{"observed_at":"2026-05-18T09:46:12.386959Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2512.21651","last_updated":"2026-05-15T03:51:16Z","snapshot_observed_at":"2026-07-06T22:40:02.746573Z","submitted_at":"2025-12-25T12:39:36Z","title":"Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-16T19:31:44.023679Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2512.21651"},"observation_digest":"sha256:ebcaad0098feadba15de75b18610ec0d0fe427f7499d68a3eff7cc244b0a3b83","observation_id":"d212f42f-ff90-49a5-b2bb-7f5777c66fa7","resolution":{"observed_at":"2026-05-16T19:33:20.045575Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2512.21651","last_updated":"2026-05-15T03:51:16Z","snapshot_observed_at":"2026-07-06T22:40:02.746573Z","submitted_at":"2025-12-25T12:39:36Z","title":"Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-21T16:43:01.704295Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2512.21651"},"observation_digest":"sha256:a05d217cdc604d196cea6dad4158230b481e87bb4435c1db91bb92a8d53f1ee7","observation_id":"ff87af45-80f1-478e-b383-526c913f3621","resolution":{"observed_at":"2026-05-21T16:44:16.051208Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2602.04163","last_updated":"2026-05-15T03:25:05Z","snapshot_observed_at":"2026-08-02T22:48:54.849826Z","submitted_at":"2026-02-04T02:54:37Z","title":"BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-21T14:10:32.706531Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2602.04163"},"observation_digest":"sha256:952d715696313cd15df5ee879ac317170eef1d5f973b2fee23c964fc6672cc0f","observation_id":"a8dbb3ec-b5cb-4742-a280-a340499c1734","resolution":{"observed_at":"2026-05-21T14:14:12.429098Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2604.08847","last_updated":"2026-04-10T01:09:24Z","snapshot_observed_at":"2026-07-06T22:57:50.266735Z","submitted_at":"2026-04-10T01:09:24Z","title":"DeFakeQ: Enabling Real-Time Deepfake Detection on Edge Devices via Adaptive Bidirectional Quantization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T16:40:23.170752Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2604.08847"},"observation_digest":"sha256:3eaf7fd007ad0a7a986f52311d7f9b917e7d2c5c3bbe711a8493f4e2fa26c149","observation_id":"14983f5b-f3ce-478e-8351-9f8e55a627e6","resolution":{"observed_at":"2026-05-11T08:25:58.454938Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2604.18556","last_updated":"2026-05-15T09:34:30Z","snapshot_observed_at":"2026-07-06T23:05:21.974248Z","submitted_at":"2026-04-20T17:45:47Z","title":"GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-10T05:29:51.182114Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2604.18556"},"observation_digest":"sha256:f1a66f1e26a757094d3b6a9b5b31f2204a6de0f3967673074fbb5e8d83739e69","observation_id":"01a2b157-3771-47ac-9d24-53ab3f1105c3","resolution":{"observed_at":"2026-05-10T06:11:20.901825Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2604.18556","last_updated":"2026-05-15T09:34:30Z","snapshot_observed_at":"2026-07-06T23:05:21.974248Z","submitted_at":"2026-04-20T17:45:47Z","title":"GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-19T18:01:08.514022Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2604.18556"},"observation_digest":"sha256:f1a21ac9b40ffe336b2ed77f750d7269dfbd93ff7a6ca07e9f2a9df6e2ba6282","observation_id":"b25976f0-233e-4e9c-b058-6f1085a9c777","resolution":{"observed_at":"2026-05-19T18:02:42.252920Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2604.22748","last_updated":"2026-06-08T04:24:27Z","snapshot_observed_at":"2026-08-02T10:58:24.119885Z","submitted_at":"2026-04-24T17:48:47Z","title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","version":1},"reference_index":151,"source":"arxiv_source","source_observed_at":"2026-05-08T12:02:07.027775Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2604.22748"},"observation_digest":"sha256:975990d876187aa8043963d77f239bab4c51872ff5a5da537940b1e08098a5bd","observation_id":"62e182d1-d659-4bf0-b781-2d94e0dc591f","resolution":{"observed_at":"2026-05-11T19:26:08.267403Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2604.22748","last_updated":"2026-06-08T04:24:27Z","snapshot_observed_at":"2026-08-02T10:58:24.119885Z","submitted_at":"2026-04-24T17:48:47Z","title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","version":2},"reference_index":151,"source":"arxiv_source","source_observed_at":"2026-07-04T17:29:43.764085Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2604.22748"},"observation_digest":"sha256:4ad33889391f30e357963fc622ef379194f06790d119ccc443bace80c009eec2","observation_id":"f8184116-a3ff-45f7-823b-0d92410c0264","resolution":{"observed_at":"2026-07-04T17:29:59.600173Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2605.08568","last_updated":"2026-05-09T00:02:33Z","snapshot_observed_at":"2026-08-02T23:13:09.763052Z","submitted_at":"2026-05-09T00:02:33Z","title":"Different Prompts, Different Ranks: Prompt-aware Dynamic Rank Selection for SVD-based LLM Compression","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-12T02:22:51.541981Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2605.08568"},"observation_digest":"sha256:18a7b5867cf48a60d9503713b98de2d332bbadef742e6469557a8955734c87bd","observation_id":"e8b3629a-5b40-4cf3-8760-ea834bed7624","resolution":{"observed_at":"2026-05-12T07:41:33.931244Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2605.11558","last_updated":"2026-05-12T05:41:36Z","snapshot_observed_at":"2026-08-02T05:04:14.603060Z","submitted_at":"2026-05-12T05:41:36Z","title":"A Composite Activation Function for Learning Stable Binary Representations","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-13T02:03:42.456988Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2605.11558"},"observation_digest":"sha256:1ad060079a146fd4f4bea0f146dba74be9a6dc78463f1e39f892e5efa6c1821e","observation_id":"198e1cda-1994-40b0-8805-c112939a89ed","resolution":{"observed_at":"2026-05-13T02:07:07.889038Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2606.04050","last_updated":"2026-06-29T14:48:51Z","snapshot_observed_at":"2026-08-02T11:21:40.769275Z","submitted_at":"2026-06-02T08:52:04Z","title":"LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-06-28T11:14:03.535306Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2606.04050"},"observation_digest":"sha256:b78be5404917ae506b46be74ce8371e8bc7c61c129e344cbe0a2ab59d9a85e2a","observation_id":"c6d3918c-db8d-4859-9499-d1f268594e5c","resolution":{"observed_at":"2026-07-02T02:06:27.021816Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2606.04050","last_updated":"2026-06-29T14:48:51Z","snapshot_observed_at":"2026-08-02T11:21:40.769275Z","submitted_at":"2026-06-02T08:52:04Z","title":"LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-06-30T11:17:53.736872Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2606.04050"},"observation_digest":"sha256:0066d7665c350a07d8fb13f2873098e4e382f20fc6d1b986a5eaeed9cac58f68","observation_id":"04611a71-ae80-4987-907f-f98a45a393df","resolution":{"observed_at":"2026-06-30T11:24:38.268077Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2606.04349","last_updated":"2026-06-05T07:15:28Z","snapshot_observed_at":"2026-08-03T07:13:29.397921Z","submitted_at":"2026-06-03T02:05:10Z","title":"MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-28T07:16:45.665440Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2606.04349"},"observation_digest":"sha256:682ee991b4194ddc0c5dfb9a918b76ba28c90fda34fb284aa50ec72ab8e82591","observation_id":"aaa755f9-e6a9-4844-a821-f6f040bd8598","resolution":{"observed_at":"2026-07-02T06:56:44.636154Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2606.05429","last_updated":"2026-06-03T20:51:52Z","snapshot_observed_at":"2026-08-01T01:29:54.377180Z","submitted_at":"2026-06-03T20:51:52Z","title":"Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-28T06:09:42.838355Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2606.05429"},"observation_digest":"sha256:7bf55435bd209eed7a08c17f0f9c41a8126afb27bdb7673dc2d8940fee8f15ec","observation_id":"cf02dd73-87d5-4c53-a505-2d2c622e2adc","resolution":{"observed_at":"2026-07-02T08:16:48.283866Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":"2402.04291","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-07-04T17:29:59.598269Z","title":"Billm: Pushing the limit of post-training quantization for llms","venue":null,"work_id":"5ad1f303-8e85-433c-9085-ff3267c2fb8c","year":2024},"citing_paper":{"arxiv_id":"2606.07116","last_updated":"2026-06-05T10:11:34Z","snapshot_observed_at":"2026-08-02T05:47:51.742987Z","submitted_at":"2026-06-05T10:11:34Z","title":"OffQ: Taming Structured Outliers in LLM Quantization by Offsetting","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-27T22:37:21.676141Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2606.07116"},"observation_digest":"sha256:48aa9a5017033bd2a63a9ac63655e025ccee89b31e5b27d06c64ec90d28b12bb","observation_id":"347e9c7b-18b6-4ab6-859a-48634cbf0a36","resolution":{"observed_at":"2026-07-02T16:27:09.699784Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-08-02T01:35:43.424174Z","title":"Huang et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-04T20:30:06.535481Z","submitted_at":"2026-07-16T06:47:52Z","title":"Cross-Layer Error Compensation and Finite-Sample Feature-Statistics Matching for Extreme Low-Bit Quantization of Large Language Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:43.424174Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:bbc8a7d13210fc86dc80bb5ae449a4c962b870592686aa9637b7537bc311b951","observation_id":"d39fd99e-8550-427d-bc25-842c1b824fa9","resolution":{"observed_at":"2026-08-02T01:35:43.424174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.04291/citation-record","integrity":"/paper/2402.04291/integrity","json":"/paper/2402.04291/citation-record.json","paper":"/paper/2402.04291"},"outbound":[],"paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 20 inbound Pith citation observations for arXiv:2402.04291."}