{"as_of":"2026-08-08T10:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8e27f2e7ab476421f1f0d80406c8929ff76148ebab40e8e77fe0ef6036e0bf02","coverage":[{"denominator":19,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":19,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:26:17.271389Z","state":"measured"},{"denominator":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-26T01:10:00.373247Z","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":"2026-07-04T15:59:57.441183Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"cited_work":{"arxiv_id":"2505.19235","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.19235","snapshot_observed_at":"2026-07-04T15:59:57.441183Z","title":"arXiv preprint arXiv:2505.19235 (2025)","venue":null,"work_id":"9634fb41-c872-4f25-8671-54fb9f14a825","year":2025},"citing_paper":{"arxiv_id":"2606.24156","last_updated":"2026-06-23T05:24:50Z","snapshot_observed_at":"2026-08-08T04:43:36.112271Z","submitted_at":"2026-06-23T05:24:50Z","title":"Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-06-26T01:10:00.373247Z"},"links":{"cited_paper":"/paper/2505.19235","citing_paper":"/paper/2606.24156"},"observation_digest":"sha256:0d7048e4da476935bfe73cd4b7654c19215616cd7d2fdca924ac735a72944c2a","observation_id":"983b60a4-d0bc-4255-ba7c-c9c910567d87","resolution":{"observed_at":"2026-07-04T15:59:56.742663Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"cited_work":{"arxiv_id":"2505.19235","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.19235","snapshot_observed_at":"2026-07-04T15:59:57.441183Z","title":"arXiv preprint arXiv:2505.19235 (2025)","venue":null,"work_id":"9634fb41-c872-4f25-8671-54fb9f14a825","year":2025},"citing_paper":{"arxiv_id":"2606.24165","last_updated":"2026-06-23T05:39:52Z","snapshot_observed_at":"2026-08-02T01:56:55.495306Z","submitted_at":"2026-06-23T05:39:52Z","title":"Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-06-26T01:04:20.802531Z"},"links":{"cited_paper":"/paper/2505.19235","citing_paper":"/paper/2606.24165"},"observation_digest":"sha256:51be3b6ee72daf0843d93efa85ed2ac9966df9c400cda01a92eac6dfa292bd56","observation_id":"d213ce1e-51e3-4e07-9c40-c7843f744771","resolution":{"observed_at":"2026-07-04T15:59:57.442445Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.19235/citation-record","integrity":"/paper/2505.19235/integrity","json":"/paper/2505.19235/citation-record.json","paper":"/paper/2505.19235"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.11514","last_updated":"2024-07-30T23:37:20Z","snapshot_observed_at":"2026-07-06T17:04:50.608413Z","submitted_at":"2023-12-12T18:57:08Z","title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11514","snapshot_observed_at":"2026-08-07T14:26:17.201744Z","title":"C., Rastegari, M., and Fara- jtabar, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.201744Z"},"links":{"cited_paper":"/paper/2312.11514","citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:c666a13ada32f087f0b3865c626d75ee4048abe5a7fea85789c0d0fdec2c9128","observation_id":"363fa428-9e58-4982-93c0-61d1468f4cde","resolution":{"observed_at":"2026-08-07T14:26:17.201744Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.00876","last_updated":"2025-03-21T13:30:33Z","snapshot_observed_at":"2026-08-06T17:48:57.425700Z","submitted_at":"2024-12-01T16:32:31Z","title":"Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.00876","snapshot_observed_at":"2026-08-07T14:26:17.210434Z","title":"Dynamic-llava: Efficient multimodal large language models via dynamic vision-language context sparsification","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.210434Z"},"links":{"cited_paper":"/paper/2412.00876","citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:523ca5ce6d332a2fa20506a07d3962966b95a264aefdc330c63693bbc3f0ed41","observation_id":"17d12eee-c0e0-48c2-9b01-acc626a45d1b","resolution":{"observed_at":"2026-08-07T14:26:17.210434Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10355","last_updated":"2023-10-26T02:52:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-17T16:34:01Z","title":"Evaluating Object Hallucination in Large Vision-Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10355","snapshot_observed_at":"2026-08-07T14:26:17.222667Z","title":"X., and Wen, J.-R","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.222667Z"},"links":{"cited_paper":"/paper/2305.10355","citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:5ca26ddc5b98cb7c775e822d1a5a7813edc2bab7093faf1c12eaa4c884b7fa5c","observation_id":"e3ebb722-0bd6-4819-9e16-e66099588199","resolution":{"observed_at":"2026-08-07T14:26:17.222667Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.10742","last_updated":"2025-04-24T14:53:57Z","snapshot_observed_at":"2026-08-07T20:41:48.821228Z","submitted_at":"2025-03-13T17:47:52Z","title":"Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing","version":2},"cited_work":{"arxiv_id":"2503.10742","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.10742","snapshot_observed_at":"2026-08-07T14:26:17.425104Z","title":"Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing","venue":"cs.LG","work_id":"40e3dc88-ffda-407d-a468-4374eee165e8","year":2025},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.230770Z"},"links":{"cited_paper":"/paper/2503.10742","citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:c4a8887e2a1a37b4389a08025043681c1f1e9001cffe16c7589172d28c5eb8dc","observation_id":"847a243a-9c9c-4f22-89d6-eae1454cc240","resolution":{"observed_at":"2026-08-07T14:26:17.428918Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.12456","last_updated":"2024-12-12T12:38:12Z","snapshot_observed_at":"2026-08-07T20:41:48.188566Z","submitted_at":"2023-12-16T02:27:00Z","title":"PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.12456","snapshot_observed_at":"2026-08-07T14:26:17.238480Z","title":"Powerinfer: Fast large language model serving with a consumer-grade gpu","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.238480Z"},"links":{"cited_paper":"/paper/2312.12456","citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:5572e1143ac86c12c6b841cdc1ff38bd93a3a767a9500d2c2726f1b6c0dc60cd","observation_id":"69b87f83-9793-4573-9514-e99b11547a90","resolution":{"observed_at":"2026-08-07T14:26:17.238480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-07T14:26:17.242204Z","title":"Llama: Open and efficient foundation lan- guage models","venue":null,"work_id":null,"year":1954},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.242204Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:fb4781e8baecae0cb132b4856293f8f40c377752209df8afd295d461bf5078b4","observation_id":"73c96792-fa40-40c6-b281-cf0d08d9d302","resolution":{"observed_at":"2026-08-07T14:26:17.242204Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.18311","last_updated":"2024-10-23T22:45:23Z","snapshot_observed_at":"2026-08-07T20:43:00.298932Z","submitted_at":"2024-10-23T22:45:23Z","title":"CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation","version":1},"cited_work":{"arxiv_id":"2410.18311","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.18311","snapshot_observed_at":"2026-08-07T14:26:17.324460Z","title":"CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation","venue":"cs.LG","work_id":"5f83bfbf-fcb1-40e4-9c77-c64e74933aff","year":2024},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.245997Z"},"links":{"cited_paper":"/paper/2410.18311","citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:b90c71ceb67a8a6bc3fad4959fb6b807cd6d97e19a9a160782db16a9b702213c","observation_id":"63e2338c-e391-4c6d-a94d-3b3bac0356ca","resolution":{"observed_at":"2026-08-07T14:26:17.330358Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.12275","last_updated":"2025-03-03T09:05:52Z","snapshot_observed_at":"2026-07-06T18:32:44.452493Z","submitted_at":"2024-06-18T05:05:12Z","title":"VoCo-LLaMA: Towards Vision Compression with Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.12275","snapshot_observed_at":"2026-08-07T14:26:17.253571Z","title":"V oco-llama: Towards vision compression with large lan- guage models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.253571Z"},"links":{"cited_paper":"/paper/2406.12275","citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:838447440675417882311c7e13429adaf82ce60f006daedec3cb570940153d36","observation_id":"085c94df-aa16-4d8f-926b-7d6a5fec40e2","resolution":{"observed_at":"2026-08-07T14:26:17.253571Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.02490","last_updated":"2024-12-01T05:46:03Z","snapshot_observed_at":"2026-08-08T03:31:37.699253Z","submitted_at":"2023-08-04T17:59:47Z","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.02490","snapshot_observed_at":"2026-08-07T14:26:17.256913Z","title":"Mm-vet: Evaluating large multi- modal models for integrated capabilities","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.256913Z"},"links":{"cited_paper":"/paper/2308.02490","citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:457b4132acfe84d0abfac72328ae212ab7bd0b2acbedc61f07d803f48dc9e0f1","observation_id":"7261ab2b-1af0-436b-b90f-01406ffec30e","resolution":{"observed_at":"2026-08-07T14:26:17.256913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:26:17.611229Z","title":"The document is organized as follows: •A- Related Work •B- Algorithm •C- Assumption Explanation •D- Experiments Settings •E- Additional Experiments •F- Visualization of Results A","venue":null,"work_id":"f2065b35-1b05-4c44-a9f2-4902fd8e62b1","year":2023},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.260758Z"},"links":{"citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:8f1d9177a5f6200eada3f89cc4d5c9b5df6e9b7c27f10fddc5468a7f7a4b8481","observation_id":"de2889b6-1e29-4376-90cc-83afba36bce3","resolution":{"observed_at":"2026-08-07T14:26:17.615715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:26:17.602170Z","title":"For example, in the OPT-30B, a single token activates only approximately 10% of the neurons (Alizadeh et al., 2023)","venue":null,"work_id":"0517e377-3231-4987-b189-d58cc6257e6f","year":2023},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.264565Z"},"links":{"citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:7475f0b873918d19249a917422724b5f6d30ae895ff08704216a4ce6340b9c6a","observation_id":"925b7f91-2ca0-48ee-804d-cb98d7094966","resolution":{"observed_at":"2026-08-07T14:26:17.605538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:26:17.593029Z","title":"CoreInfer identifies a set of core neurons that most frequently and strongly activated for each input sentence","venue":null,"work_id":"7806c66c-b6e1-4d4a-a2b8-ba82dbf611ea","year":null},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.268140Z"},"links":{"citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:c86efc32f8c0daae41e2bb28a0fe99f7864c91fe4c88784212370c9056c818fd","observation_id":"52ba59d7-3135-475e-9d01-410b2ed34eb6","resolution":{"observed_at":"2026-08-07T14:26:17.596385Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:26:17.582126Z","title":"(18) which means∥y i∥= √η∥Ai∥","venue":null,"work_id":"839a1c8a-7301-44ff-a4ea-e09d3e6edff2","year":2017},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.271389Z"},"links":{"citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:817c16b5d776c21d067d4b98f7c256bd87042ac7be4d355eed2e3b060240bfe6","observation_id":"e908ccf6-380b-4ca4-b6a4-82c934980c44","resolution":{"observed_at":"2026-08-07T14:26:17.585496Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.14165","last_updated":"2020-07-22T19:47:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-05-28T17:29:03Z","title":"Language Models are Few-Shot Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.14165","snapshot_observed_at":"2026-08-07T14:26:17.206295Z","title":null,"venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.206295Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:163caf6db48c2f9370c7dbb1a4779b583ccd79c4bf1f36e6db460e688d360642","observation_id":"8622f967-5baa-48a5-9900-8017aabc34f6","resolution":{"observed_at":"2026-08-07T14:26:17.206295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.12893","last_updated":"2025-02-27T01:32:58Z","snapshot_observed_at":"2026-08-07T18:08:32.968901Z","submitted_at":"2025-02-18T14:29:12Z","title":"H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.12893","snapshot_observed_at":"2026-08-07T14:26:17.214742Z","title":"H-cot: Hijack- ing the chain-of-thought safety reasoning mechanism to jailbreak large reasoning models, including openai o1/o3, deepseek-r1, and gemini 2.0 flash thinking","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.214742Z"},"links":{"cited_paper":"/paper/2502.12893","citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:906f958617fd2c2767ab797bcbf8ba9609f44b7637286f38fbb22aed882ec680","observation_id":"7fc2dd48-1964-45ee-85bd-ceed7ccac036","resolution":{"observed_at":"2026-08-07T14:26:17.214742Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:26:17.235271Z","title":"Dobi-svd: Differentiable svd for llm compression and some new perspectives","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.235271Z"},"links":{"citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:74bda340afbcfd91f7817a4b677d3ed77b6bef4ddeb6479e092e6287b5a5029a","observation_id":"a1730d2e-3987-4037-950b-481a06676dd0","resolution":{"observed_at":"2026-08-07T14:26:17.235271Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:26:17.227367Z","title":"Hippomm: Hippocampal-inspired multimodal memory for long audiovisual event understanding","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.227367Z"},"links":{"citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:a81e80d2f34b46cfb0245f1296d58ac3bb53b7e283a565d8f0a73eb0abbcce8c","observation_id":"8c2ae999-c555-43c2-ac74-490658923777","resolution":{"observed_at":"2026-08-07T14:26:17.227367Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06282","last_updated":"2024-12-12T12:24:18Z","snapshot_observed_at":"2026-08-06T16:06:48.213787Z","submitted_at":"2024-06-10T14:01:21Z","title":"PowerInfer-2: Fast Large Language Model Inference on a Smartphone","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06282","snapshot_observed_at":"2026-08-07T14:26:17.250081Z","title":"Powerinfer-2: Fast large language model inference on a smartphone","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.250081Z"},"links":{"cited_paper":"/paper/2406.06282","citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:db1cb4505862cc0d75da8e12509e467381d3734e049ce79a06a0d7c69513ac53","observation_id":"0f5c1124-bece-4e9b-a235-fd754a1aaa5e","resolution":{"observed_at":"2026-08-07T14:26:17.250081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.16125","last_updated":"2023-08-02T08:02:35Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-07-30T04:25:16Z","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.16125","snapshot_observed_at":"2026-08-07T14:26:17.218889Z","title":"Seed-bench: Benchmarking multimodal llms with gener- ative comprehension","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-07T14:26:17.218889Z"},"links":{"cited_paper":"/paper/2307.16125","citing_paper":"/paper/2505.19235"},"observation_digest":"sha256:0a97d3a463612b1896b04019542fd639521a787d5b72898cadc6735495f7c77a","observation_id":"968ccbce-b82b-4dd4-bebe-dd295d39af08","resolution":{"observed_at":"2026-08-07T14:26:17.218889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.19235","last_updated":"2025-05-25T17:16:34Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T20:41:54.292300Z","submitted_at":"2025-05-25T17:16:34Z","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models"},"reference_resolution":{"displayed":19,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":2,"verified_fuzzy":2},"total_outbound_references":19},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 2 inbound Pith citation observations for arXiv:2505.19235."}