{"as_of":"2026-08-18T18:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f84673cf118ee42a049ba08b4960082c2a8c8b476d950803537faf741269c9c7","coverage":[{"denominator":63,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":63,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:28:02.289894Z","state":"measured"},{"denominator":63,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":63,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.04861/citation-record","integrity":"/paper/2505.04861/integrity","json":"/paper/2505.04861/citation-record.json","paper":"/paper/2505.04861"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:28:03.137640Z","title":"Crowd-SAM: Sam as a smart annotator for object detection in crowded scenes","venue":null,"work_id":"8f69ed17-0caf-47ae-a299-1e7570ff83e1","year":2024},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.059704Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:9e06b65e6b4f9664c6a34a70ccf469da909e89996162340cd7dab00be6c5ec70","observation_id":"87245482-f018-47c7-ad17-436aa2a9bc53","resolution":{"observed_at":"2026-08-15T23:28:03.141859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:03.127017Z","title":"DearKD: Data-efficient early knowledge distillation for vision transformers","venue":null,"work_id":"3c974a1f-5b59-442c-9eba-d4bc557ea4ec","year":2022},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.064161Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:9f6cdef9d364e84a053b961f7ef14fb7cf498dc0d339074b9d2e678d51d2e40d","observation_id":"8727467c-24cb-4141-a5ba-e9b9d0c9fb9e","resolution":{"observed_at":"2026-08-15T23:28:03.130374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.16772","last_updated":"2024-09-02T13:19:40Z","snapshot_observed_at":"2026-08-17T23:10:54.080424Z","submitted_at":"2024-08-14T17:19:56Z","title":"An Effective Information Theoretic Framework for Channel Pruning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.16772","snapshot_observed_at":"2026-08-15T23:28:02.067796Z","title":"An effective in- formation theoretic framework for channel pruning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.067796Z"},"links":{"cited_paper":"/paper/2408.16772","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:0a316753984551ce182392a3f54a5d4ae4ec2f51e7af918e5b350c2cef802911","observation_id":"762bec37-1efa-4c18-b0e4-59ac1260c066","resolution":{"observed_at":"2026-08-15T23:28:02.067796Z","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":"2026-08-15T23:28:03.117171Z","title":"Tracking any- thing with decoupled video segmentation","venue":null,"work_id":"fbcd23b9-204c-450d-ac8d-6c8a17dc0940","year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.071868Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:424f17e6ef46744005114ed09c88ab24b4b1cf9cc0275ab7db5c1ce536e5e6f9","observation_id":"d6604d28-af0c-4c8c-bd57-3dda960a38c9","resolution":{"observed_at":"2026-08-15T23:28:03.120419Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:03.107085Z","title":"Low-bit quantization of neural networks for efficient inference","venue":null,"work_id":"ea1f4ab3-bfe8-4aac-9bed-69000135ddd9","year":2019},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.075953Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:7c03d29d35a92af4186fbdfa1f4312ba6d8b202c687e8b4b58cfaea49fc2e9bf","observation_id":"9b04cf27-bfca-413d-85f1-58cbb7a86885","resolution":{"observed_at":"2026-08-15T23:28:03.110395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05657","last_updated":"2025-04-08T02:55:27Z","snapshot_observed_at":"2026-08-17T23:10:28.649500Z","submitted_at":"2023-07-11T15:56:00Z","title":"Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic Programming","version":2},"cited_work":{"arxiv_id":"2307.05657","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.05657","snapshot_observed_at":"2026-08-15T23:28:02.514686Z","title":"Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic Programming","venue":"cs.NE","work_id":"ec91f365-939a-4c37-b59c-30f73286c677","year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.079983Z"},"links":{"cited_paper":"/paper/2307.05657","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:193566ecd0d4103c99076ff14fdd2c6b275158beb633c0212c649e496e913b0e","observation_id":"a7b910ed-8c97-4d8d-b58d-c40f64b690a5","resolution":{"observed_at":"2026-08-15T23:28:02.519114Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:03.096178Z","title":"CVXPY: A python-embedded modeling language for convex op- timization","venue":null,"work_id":"61851a61-cfb4-434e-a8d2-4a352c643c12","year":2016},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.084153Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:2859e106aca366fd4696f6fb47fe76015012c0c155b410d95c579f61b88d66d4","observation_id":"ffce265c-3407-4dbb-9e8f-76a9c42916d4","resolution":{"observed_at":"2026-08-15T23:28:03.100183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:03.084152Z","title":"Towards accurate post-training quan- tization for vision transformer","venue":null,"work_id":"cb39f410-1e23-46fa-ab63-670c21d47be7","year":2022},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.087846Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:9193f39866f132161e629e2948c7511293d28feea08adab677afabaa7be1f705","observation_id":"b2a92965-945d-48ea-8dfa-2a0771199528","resolution":{"observed_at":"2026-08-15T23:28:03.088374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:03.070191Z","title":"HAWQ: Hessian aware quantization of neural networks with mixed-precision","venue":null,"work_id":"67e47edf-d8d9-44c7-99be-9f6d6d7c3fc4","year":2019},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.091408Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:54c5ca4a0a677c63fd93f20b1ec88944480c819e77883d1f3a9184d340b0315a","observation_id":"45c4045a-20fe-43d4-b6cf-569bd80fe0b4","resolution":{"observed_at":"2026-08-15T23:28:03.074854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:03.056822Z","title":"HAWQ- V2: Hessian aware trace-weighted quantization of neural networks","venue":null,"work_id":"ec4e5c09-7a81-467f-a09e-b7ec5e59bda0","year":2020},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.094848Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:4d58f64d313eb8f90eface4855170173bfb292c2e3bc666d8c40b62912f48adc","observation_id":"b3aed52d-bee4-451f-a963-c73f943c5dc9","resolution":{"observed_at":"2026-08-15T23:28:03.061211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.12594","last_updated":"2021-08-28T07:51:47Z","snapshot_observed_at":"2026-08-16T18:00:24.128704Z","submitted_at":"2021-08-28T07:51:47Z","title":"Layer-wise Model Pruning based on Mutual Information","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.12594","snapshot_observed_at":"2026-08-15T23:28:02.098410Z","title":"Layer-wise model pruning based on mutual information","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.098410Z"},"links":{"cited_paper":"/paper/2108.12594","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:ca052f2932a82c7305fe548fc2ab0126eb50315c4b9e87f30ab7e61f7a3faffb","observation_id":"02ca7676-1cbc-473b-82a1-bf21b0cdf50c","resolution":{"observed_at":"2026-08-15T23:28:02.098410Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.08430","last_updated":"2021-08-06T03:22:14Z","snapshot_observed_at":"2026-08-17T22:45:24.694319Z","submitted_at":"2021-07-18T12:55:11Z","title":"YOLOX: Exceeding YOLO Series in 2021","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.08430","snapshot_observed_at":"2026-08-15T23:28:02.102310Z","title":"YOLOX: Exceeding yolo series in 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.102310Z"},"links":{"cited_paper":"/paper/2107.08430","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:2c5153a59f3bfb1a8dd92d04a42de5740da9c8e77f25d98ac81bb9d96debbed5","observation_id":"5ec90ce1-e24a-412a-b426-05d1178a41e7","resolution":{"observed_at":"2026-08-15T23:28:02.102310Z","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":"2026-08-15T23:28:03.042546Z","title":"Soft filter pruning for accelerating deep convolutional neural networks","venue":null,"work_id":"d402619d-9235-4f30-901f-92b3a219ffaf","year":2018},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.106654Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:dc7b3bc1bdbe17051cb97555c409c47915b3e7f6e865808d88876feb73a092d1","observation_id":"1423703a-5f23-4b71-bba5-4ff57a284836","resolution":{"observed_at":"2026-08-15T23:28:03.046898Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:03.031418Z","title":"Quantization and train- ing of neural networks for efficient integer-arithmetic- only inference","venue":null,"work_id":"04e58776-ee67-4a4a-ac8a-b209531c8203","year":2018},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.110325Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:50aec802d3ba9236872bc530e94f6644fefc3a8f70314258ed8a1af392e30ab2","observation_id":"da1d4575-451f-4307-b463-ec9838119404","resolution":{"observed_at":"2026-08-15T23:28:03.035141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:03.020794Z","title":"Detrs with hybrid matching","venue":null,"work_id":"f5289b67-0021-4718-9d72-e104aadda02a","year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.114099Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:6cacaf0187331624311087039a0718fc89c5298071736df19d7a3b808fc3917f","observation_id":"937a8c48-4077-4614-900d-c3410adb6c93","resolution":{"observed_at":"2026-08-15T23:28:03.024578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:03.010088Z","title":"Segment anything in high quality","venue":null,"work_id":"c8dfea45-62d1-4351-b1dd-9b508df37560","year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.117757Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:fb642894cc94985ca545cdb539e454f23c1b5ef3ddd0535fcfad269aaad2f0b0","observation_id":"2b24f66c-382e-4a7d-8d89-40c76b464843","resolution":{"observed_at":"2026-08-15T23:28:03.013798Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.998914Z","title":"SAM-Net: self-attention based feature matching with spatial transformers and knowledge distillation","venue":null,"work_id":"85366d69-89e9-4690-bc34-56806bcf17db","year":2024},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.121386Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:8140c133b929fb53a3969c25e3b127fba3f68c48eef3a2847707d27a88b8ca31","observation_id":"826d2e52-2311-490e-9552-cb20c1adf2a6","resolution":{"observed_at":"2026-08-15T23:28:03.003238Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.988111Z","title":"Segment anything","venue":null,"work_id":"8901fd5a-bfd4-4318-9e7c-49a2bdce0486","year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.124977Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:1acaacdfe606af0ab95c0e23d792e7b39234a68633c001ab88ea80f52b6fd3a9","observation_id":"a73d9e03-755b-49f4-a4eb-8be5e406e217","resolution":{"observed_at":"2026-08-15T23:28:02.991855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.976100Z","title":"Optimizing expo- nent bias for sub-8bit floating-point inference of fine- tuned transformers","venue":null,"work_id":"9ded627a-8f4a-4d0b-945f-44f04eaf4a0e","year":2022},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.128497Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:64069736ec010c8d68d0a2b3d09d6096ddb4b2af9a320eb671041c92e6365cb4","observation_id":"26f9bb15-d40d-441c-9b23-e1c1edbbc359","resolution":{"observed_at":"2026-08-15T23:28:02.979970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.967520Z","title":"FlexRound: Learnable rounding based on element-wise division for post-training quantiza- tion","venue":null,"work_id":"571057c9-e368-457c-981e-1c4a894a0411","year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.132013Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:7deebb5c4327c6f0a6350f66adcf133ca36354bc43a0b66811e618016feeb488","observation_id":"be9baadb-e2a4-465e-b4da-10f2de65436d","resolution":{"observed_at":"2026-08-15T23:28:02.970630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.08010","last_updated":"2024-04-15T06:08:51Z","snapshot_observed_at":"2026-08-16T14:02:13.210026Z","submitted_at":"2024-04-10T03:22:58Z","title":"Differentiable Search for Finding Optimal Quantization Strategy","version":2},"cited_work":{"arxiv_id":"2404.08010","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.08010","snapshot_observed_at":"2026-08-15T23:28:02.475929Z","title":"Differentiable Search for Finding Optimal Quantization Strategy","venue":"cs.LG","work_id":"243a6283-7690-4ed0-b5df-ed85610b4bdb","year":2024},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.135530Z"},"links":{"cited_paper":"/paper/2404.08010","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:291739eab5c9316eab1025b7566b5b63642d84076dccf140e1ce2c118926bf78","observation_id":"0b38942a-0138-4ed2-9008-98acfc8989bc","resolution":{"observed_at":"2026-08-15T23:28:02.482032Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.05426","last_updated":"2021-07-25T09:34:39Z","snapshot_observed_at":"2026-08-18T09:07:09.396960Z","submitted_at":"2021-02-10T13:46:16Z","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.05426","snapshot_observed_at":"2026-08-15T23:28:02.139392Z","title":"BRECQ: Pushing the limit of post-training quantization by block reconstruction","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.139392Z"},"links":{"cited_paper":"/paper/2102.05426","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:0dbd34337d06bacc3f66ebf45dd563ba0336fe7f3cdc821e2d08427c7bc781bd","observation_id":"778a77cf-f79b-4571-8701-800b9b4fb17a","resolution":{"observed_at":"2026-08-15T23:28:02.139392Z","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":"2026-08-15T23:28:02.957830Z","title":"RepQ-ViT: Scale reparameterization for post- training quantization of vision transformers","venue":null,"work_id":"76ffc262-cb34-4185-9823-2b88e4797697","year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.143171Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:bdd59b9cf3ed81488edce597880e674ac69c72f942a7976601c074689afd6755","observation_id":"a6d7ae2b-9868-4295-ba30-5b139a6bfa27","resolution":{"observed_at":"2026-08-15T23:28:02.961164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.948740Z","title":"Knowledge distillation via the target- aware transformer","venue":null,"work_id":"a132867b-6013-4d7d-9be7-2de82d29750e","year":null},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.146541Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:ccf4d3a3a0ba31c540986fe78b86b1ce0e1ca11f07a41490d32720349ef653e8","observation_id":"e546f497-16eb-496a-b621-5e7db663cdf5","resolution":{"observed_at":"2026-08-15T23:28:02.951895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.938536Z","title":"Microsoft COCO: Com- mon objects in context","venue":null,"work_id":"ade82f2c-7314-4145-a8ea-9cbc3463b841","year":2014},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.149894Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:b3f6f35788abe378952cf58167df38dc91fd23e8c6788a510f79ea9ebb556549","observation_id":"dd113ceb-0e32-4400-a014-3c0772020a33","resolution":{"observed_at":"2026-08-15T23:28:02.942333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.927174Z","title":"FQ-ViT: Post-training quantization for fully quantized vision transformer","venue":null,"work_id":"dcf4885b-03b7-4e56-a182-5624ee457922","year":2022},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.153411Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:bf13721adc31d0ecea9075069c54042565cd6274b353210b8fe2b0aaaddd69ca","observation_id":"0c55ba2e-054e-4058-8588-da3128fe33e9","resolution":{"observed_at":"2026-08-15T23:28:02.931128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.915458Z","title":"Perceptual-sensitive gan for generating adversarial patches","venue":null,"work_id":"39c7456c-a8ed-4410-ad01-56aaf71299e3","year":2019},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.156618Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:7de2ebf1be9acbd8a16bac014bbd2a6e3b3248f71309091bf080a52f2423aa2e","observation_id":"e3f4fe7d-36db-41c6-aa7d-fb93452138e5","resolution":{"observed_at":"2026-08-15T23:28:02.919526Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.903722Z","title":"PD-Quant: Post- training quantization based on prediction difference metric","venue":null,"work_id":"1bfed46d-06e5-4375-8793-a8286cfc00eb","year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.159790Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:266a6bae8448698d454544cd583c959282caf9f32e50521b1571cfc866a07a68","observation_id":"60b8fc4d-55d2-4e55-89b8-76c79214c54d","resolution":{"observed_at":"2026-08-15T23:28:02.907964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.892250Z","title":"PQ-SAM: Post-training quantization for segment anything model","venue":null,"work_id":"417c37e6-f7e8-4c7b-9b1d-dd747e367d9e","year":2024},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.163527Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:09801e92a7d7c9d0b1035a700fd7baa94ee3caef8b302d8c5e48330efd2fb9b3","observation_id":"b5e210a4-a033-4087-afaa-ac6858d2a029","resolution":{"observed_at":"2026-08-15T23:28:02.896263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.881515Z","title":"NoisyQuant: Noisy bias-enhanced post-training activation quantization for vision transformers","venue":null,"work_id":"9b609594-e3dd-4507-bc2c-820b11cd68bd","year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.167077Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:53f52d02e541e07f2d26181455850d6225de6fca7e29c08585a1571abe0c0395","observation_id":"869a468e-55ca-437e-af8e-4d5ea3ee69f6","resolution":{"observed_at":"2026-08-15T23:28:02.885348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.869934Z","title":"Post-training quantization for vision transformer","venue":null,"work_id":"ce8a780f-ba98-4118-b6bb-b314c7bdfb32","year":2021},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.170537Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:87c48ed3fdbec4edad36e5a09aec34715500b197177ce8d48d54dab3f8cc99e2","observation_id":"198532d3-7770-49b5-b133-20bdb96dd04b","resolution":{"observed_at":"2026-08-15T23:28:02.874324Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.858568Z","title":"AutoQ: Automated kernel-wise neural network quantization","venue":null,"work_id":"d64f0399-3ae0-48e3-bdbc-41cdcaad2466","year":null},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.174199Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:00cb08dd72dd76a083ca23fdc2c806daf95f6c0a88b0c3b3f0f4176415ff7616","observation_id":"91c569e1-4fe7-4e0c-8e1f-1f2d4c9bc7b3","resolution":{"observed_at":"2026-08-15T23:28:02.862760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.846900Z","title":"DeepBurning-MixQ: An open source mixed-precision neural network accelerator de- sign framework for fpgas","venue":null,"work_id":"6acf5dd6-9a64-4a06-b7f3-9ca0ff133ab4","year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.177850Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:c45f3ca11f3a0f49875c0238863ad0229f9d6a9c19edfa31bdf88b48c0c3b7ed","observation_id":"d0308f70-2c16-4dc1-9523-a5f90414c966","resolution":{"observed_at":"2026-08-15T23:28:02.851148Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.835389Z","title":"PTQ4SAM: Post-training quan- tization for segment anything","venue":null,"work_id":"523f8af0-1b87-434f-ab7b-ac68cc168a45","year":2024},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.181631Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:902c015f7c1a6f61f983317727da098fd6eb5e2bba9327da6969a99a1f51c525","observation_id":"08950e12-2a66-4fde-a09b-a07001a3a323","resolution":{"observed_at":"2026-08-15T23:28:02.839521Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.824300Z","title":"Seg- ment anything model for medical image analysis: an experimental study","venue":null,"work_id":"ccabb941-66c1-44b5-9e06-5615e3cb7c3b","year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.185015Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:ab78dd6aa460fc64874157ba336eb4a1a1e362089d953c5553cf59750f142424","observation_id":"d130b590-9144-459a-961e-316810ed5fba","resolution":{"observed_at":"2026-08-15T23:28:02.828190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.813892Z","title":"SAM-PM: Enhancing video camouflaged ob- ject detection using spatio-temporal attention","venue":null,"work_id":"834df869-9e10-4a7f-8254-a607d413b863","year":2024},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.189023Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:ab7db52beac50b21ba72331c8ee8d7a5a4b330e619b1165a5b74bb7d207a9e65","observation_id":"4b00c065-b5f4-4337-a200-8a62d975e1a5","resolution":{"observed_at":"2026-08-15T23:28:02.817261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.803419Z","title":"Up or down? adaptive rounding for post-training quantiza- tion","venue":null,"work_id":"2ef61388-152a-4a99-aad3-61bb2897d757","year":2020},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.192965Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:b6cd36af5b79ff7080b5866a996453e90e42f5be0ccb106ecb0595d86e6f5eec","observation_id":"dbd9b930-7882-44cd-b02f-3f7915aa9245","resolution":{"observed_at":"2026-08-15T23:28:02.806977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.11243","last_updated":"2024-01-20T14:53:19Z","snapshot_observed_at":"2026-08-16T14:25:55.587530Z","submitted_at":"2024-01-20T14:53:19Z","title":"LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.11243","snapshot_observed_at":"2026-08-15T23:28:02.196619Z","title":"LRP-QViT: Mixed-precision vision transformer quantization via layer-wise relevance propagation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.196619Z"},"links":{"cited_paper":"/paper/2401.11243","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:e80d7cde6016921c19396aa5bca9ee0a66c637b567663c76af9da6fd9ec3855e","observation_id":"78491f87-c2c5-4cc0-ae30-e0298b320b40","resolution":{"observed_at":"2026-08-15T23:28:02.196619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.06357","last_updated":"2025-01-10T21:36:20Z","snapshot_observed_at":"2026-08-16T12:59:14.529017Z","submitted_at":"2025-01-10T21:36:20Z","title":"Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.06357","snapshot_observed_at":"2026-08-15T23:28:02.200399Z","title":"Mix-QViT: Mixed-precision vision transformer quantization driven by layer importance and quantization sensitiv- ity","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.200399Z"},"links":{"cited_paper":"/paper/2501.06357","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:709a8d40e95ca1a29cd5494d9de0bd6959061a5194395fcf264faa1f2c22e729","observation_id":"ac1d3947-90c0-4c2c-b3ed-ffc1da70f673","resolution":{"observed_at":"2026-08-15T23:28:02.200399Z","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":"2026-08-15T23:28:02.769818Z","title":"Faster R-CNN: Towards real-time object detec- tion with region proposal networks","venue":null,"work_id":"c8b0b61b-644e-469b-8d52-73717e5b041a","year":2015},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.204157Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:af280116c2f32067cd0b08e25ba122468263a01147acc89171b1bc7fa88f3a40","observation_id":"bdc24428-ec97-400c-9506-925ee5252303","resolution":{"observed_at":"2026-08-15T23:28:02.784740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.759230Z","title":"Quantized-ViT efficient training via fisher matrix regularization","venue":null,"work_id":"161ccc51-3457-4c7d-a40a-05745540a9df","year":null},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.207556Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:7504a1bf8c12a231112007b6e86602b60f9b0d5fe904706d6d7cb955fa5955e4","observation_id":"de41e63d-8969-41df-aac8-66040cf3d9d2","resolution":{"observed_at":"2026-08-15T23:28:02.763088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.10261","last_updated":"2023-04-19T16:39:51Z","snapshot_observed_at":"2026-08-16T15:39:12.999327Z","submitted_at":"2023-04-19T16:39:51Z","title":"Anything-3D: Towards Single-view Anything Reconstruction in the Wild","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.10261","snapshot_observed_at":"2026-08-15T23:28:02.211151Z","title":"Anything-3D: Towards single-view anything recon- struction in the wild","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.211151Z"},"links":{"cited_paper":"/paper/2304.10261","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:03798e1ce70e4186616166fe344e74f781b636bbf5e71207f937c6f2c2b9312b","observation_id":"f129aaa3-b021-4511-9bd6-80ac1456277d","resolution":{"observed_at":"2026-08-15T23:28:02.211151Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.13789","last_updated":"2025-01-08T10:01:20Z","snapshot_observed_at":"2026-08-16T14:32:37.800593Z","submitted_at":"2023-12-21T12:26:11Z","title":"TinySAM: Pushing the Envelope for Efficient Segment Anything Model","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.13789","snapshot_observed_at":"2026-08-15T23:28:02.214828Z","title":"TinySAM: Pushing the envelope for efficient segment anything model","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.214828Z"},"links":{"cited_paper":"/paper/2312.13789","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:24dfbbd898b884eae22f245b1035540935dc4aef6b6e390247ba6fbf288adba0","observation_id":"f1b7d19e-ddae-4d5d-bf61-3ed262d0504a","resolution":{"observed_at":"2026-08-15T23:28:02.214828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14895","last_updated":"2024-02-01T02:05:02Z","snapshot_observed_at":"2026-08-16T14:24:13.857130Z","submitted_at":"2024-01-26T14:25:15Z","title":"MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14895","snapshot_observed_at":"2026-08-15T23:28:02.218818Z","title":"MPTQ-ViT: Mixed-precision post-training quantization for vision transformer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.218818Z"},"links":{"cited_paper":"/paper/2401.14895","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:2240faaaa7d882a2e8b7b477db0ea08c6685240f24082152c342c4c4d850e3a6","observation_id":"32fe6162-da8d-4c1e-a482-bdf072027a91","resolution":{"observed_at":"2026-08-15T23:28:02.218818Z","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":"2026-08-15T23:28:02.748361Z","title":"Mixed-precision neural network quantization via learned layer-wise importance","venue":null,"work_id":"1e8d1ce6-83a2-48cd-9c23-44ac7723ff01","year":2022},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.222778Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:74133df8a3cf7596cd7bd43896dabbd29f3b8317928a814b6453c6270261851b","observation_id":"f5490b35-8ba6-45c6-87e4-604d7c2c9f2a","resolution":{"observed_at":"2026-08-15T23:28:02.752136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.736602Z","title":"HAQ: Hardware-aware automated quantization with mixed precision","venue":null,"work_id":"4af6b9f1-d053-4a7b-91df-1cb85caecc7b","year":2019},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.226294Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:1122bdf73e053a7f0616c3ceb5f777e4be68e4eee556c3ff95c81ca4ae806f7c","observation_id":"0bf9839c-4db9-4165-926e-cd98ada42d3e","resolution":{"observed_at":"2026-08-15T23:28:02.740506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.05740","last_updated":"2023-02-21T11:24:41Z","snapshot_observed_at":"2026-08-16T17:15:24.808674Z","submitted_at":"2022-03-11T04:01:53Z","title":"QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.05740","snapshot_observed_at":"2026-08-15T23:28:02.229668Z","title":"Qdrop: Randomly dropping quantization for extremely low-bit post-training quan- tization","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.229668Z"},"links":{"cited_paper":"/paper/2203.05740","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:1db8f6299f567f65a50f7895408532079b4ab389750a52451d4d42e92024e5a5","observation_id":"7be40541-a935-40c9-a245-fb7796696425","resolution":{"observed_at":"2026-08-15T23:28:02.229668Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.00147","last_updated":"2025-02-03T11:55:40Z","snapshot_observed_at":"2026-08-16T13:03:59.997773Z","submitted_at":"2024-10-31T18:50:15Z","title":"Mutual Information Preserving Neural Network Pruning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.00147","snapshot_observed_at":"2026-08-15T23:28:02.233478Z","title":"Mutual information preserving neural network pruning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.233478Z"},"links":{"cited_paper":"/paper/2411.00147","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:4a495366190c074eeab0be663b71358105a4027c9f6d1a5f6157020b2ea7bdcb","observation_id":"fe916578-f469-4f43-9311-ca167b95c30d","resolution":{"observed_at":"2026-08-15T23:28:02.233478Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.09602","last_updated":"2020-04-20T19:59:22Z","snapshot_observed_at":"2026-08-14T00:25:24.218417Z","submitted_at":"2020-04-20T19:59:22Z","title":"Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.09602","snapshot_observed_at":"2026-08-15T23:28:02.237219Z","title":"Integer quantization for deep learning inference: Principles and empirical evaluation","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.237219Z"},"links":{"cited_paper":"/paper/2004.09602","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:fa54b0edeb0fe0413a39d24200625f95874d3be898ace8dffae522873ea3e12b","observation_id":"d860aecf-3c99-4e78-820a-323e707235b5","resolution":{"observed_at":"2026-08-15T23:28:02.237219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.12620","last_updated":"2023-12-29T03:40:59Z","snapshot_observed_at":"2026-08-16T15:37:57.344654Z","submitted_at":"2023-04-25T07:34:22Z","title":"Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.12620","snapshot_observed_at":"2026-08-15T23:28:02.240818Z","title":"Medical sam adapter: Adapting segment anything model for medical image segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.240818Z"},"links":{"cited_paper":"/paper/2304.12620","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:58d4bed0a36f88d6bc7d3ce5e439666d150f3fd336205edbbc031933c7dcc599","observation_id":"0f0424aa-4f92-4457-8e36-b12c48067f31","resolution":{"observed_at":"2026-08-15T23:28:02.240818Z","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":"2026-08-15T23:28:02.726043Z","title":"AdaLog: Post-training quantization for vision transformers with adaptive log- arithm quantizer","venue":null,"work_id":"de9235c6-682c-41e6-b7ff-59b667466cc1","year":2025},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.244439Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:dcc7f9cf2dc2fb37735cf58c2525c971e89a272a2d7452b07f5abea908951d21","observation_id":"17c0c60c-f2ca-45c1-b263-87b87e290f9b","resolution":{"observed_at":"2026-08-15T23:28:02.729586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.715284Z","title":"Patch-wise mixed-precision quantization of vi- sion transformer","venue":null,"work_id":"7c59501a-03ce-44a1-8e4b-8c45f52bab7c","year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.248104Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:fc597ca33c30563ba1b7d94841dcf5911f67348ee98f64833bcdd3dfcac2f1e2","observation_id":"ff418a5f-e032-4a9a-bc74-835ea4443e27","resolution":{"observed_at":"2026-08-15T23:28:02.719182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.598164Z","title":"EfficientSAM: Lever- aged masked image pretraining for efficient segment anything","venue":null,"work_id":"113cb1e6-dc90-43e0-b1e9-dfeae2330a98","year":2024},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.252210Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:e4697e20799ff061306ed15201c782c2954bc1d1c6784b9bdf2768024644c870","observation_id":"1da0719f-5b88-482b-858d-6db7ad86cada","resolution":{"observed_at":"2026-08-15T23:28:02.706869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.585452Z","title":"Mixed precision quantization of transformer language models for speech recognition","venue":null,"work_id":"9fc7ed90-b067-4374-b1b7-cb66e1c257c5","year":2021},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.255767Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:9aae1649a725aef4cc6df7bc37183f1da7a4383f4cfc2874b914f0385e4bf3c6","observation_id":"aff9ec6d-f943-4f8d-8675-1bcbce4a70bf","resolution":{"observed_at":"2026-08-15T23:28:02.589932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:28:02.572491Z","title":"Global vi- sion transformer pruning with hessian-aware saliency","venue":null,"work_id":"0113654a-84ce-4a1f-a574-1e84cdb71ed4","year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.259267Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:2c601b8df19e9d9589cc22d6513efe1e98fce9b2d0a8c80d87e20af228352f3f","observation_id":"1fa1c05b-e2f7-490f-8b65-64cbf7ae6b9a","resolution":{"observed_at":"2026-08-15T23:28:02.577767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.11968","last_updated":"2023-04-28T03:21:27Z","snapshot_observed_at":"2026-08-17T08:48:49.593119Z","submitted_at":"2023-04-24T10:04:06Z","title":"Track Anything: Segment Anything Meets Videos","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.11968","snapshot_observed_at":"2026-08-15T23:28:02.262871Z","title":"Track Anything: Segment anything meets videos","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.262871Z"},"links":{"cited_paper":"/paper/2304.11968","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:624f770362187ab6c56dc495a96d58f01db09f498a049c141f627c69953f4d59","observation_id":"03e28815-1e0e-40f1-a570-263a22b3296f","resolution":{"observed_at":"2026-08-15T23:28:02.262871Z","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":"2026-08-15T23:28:02.560126Z","title":"Width & depth pruning for vision transformers","venue":null,"work_id":"3c550b46-0ed1-47a1-9896-1acf85004d7b","year":2022},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.266991Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:e95ae9c38f39588ca77660bb1906e407172aba4aa56f203e57d822c7e6362db9","observation_id":"d92c3b57-8f8f-40ac-8a0b-bbb24588325b","resolution":{"observed_at":"2026-08-15T23:28:02.563924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06790","last_updated":"2023-04-13T19:23:52Z","snapshot_observed_at":"2026-08-16T15:40:35.889657Z","submitted_at":"2023-04-13T19:23:52Z","title":"Inpaint Anything: Segment Anything Meets Image Inpainting","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06790","snapshot_observed_at":"2026-08-15T23:28:02.270591Z","title":"Inpaint Anything: Segment anything meets image inpainting","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.270591Z"},"links":{"cited_paper":"/paper/2304.06790","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:26f8066afda2621b7741d99b283f43f277148ea78169341c85ebdb16696b07ef","observation_id":"c3a10c91-84bb-4db8-a454-2bc187027e6d","resolution":{"observed_at":"2026-08-15T23:28:02.270591Z","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":"2026-08-15T23:28:02.548713Z","title":"PTQ4ViT: Post-training quantiza- tion for vision transformers with twin uniform quan- tization","venue":null,"work_id":"02883931-4c26-4925-935a-cacf01994a5d","year":2022},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.274117Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:44f845f2d17aa531548135d06e442f7754c1c06651cca5b5310c76865744f7f2","observation_id":"556d3132-1ae9-4d75-ba35-7da75f63e4fa","resolution":{"observed_at":"2026-08-15T23:28:02.552510Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.14289","last_updated":"2023-07-01T07:26:22Z","snapshot_observed_at":"2026-08-12T07:11:05.316372Z","submitted_at":"2023-06-25T16:37:25Z","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.14289","snapshot_observed_at":"2026-08-15T23:28:02.277300Z","title":"Faster Segment Any- thing: Towards lightweight sam for mobile applica- tions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.277300Z"},"links":{"cited_paper":"/paper/2306.14289","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:15cbe129325c1654ec8c28ba214ab6f79f667e38556e68ddc78aa6486ffb88a5","observation_id":"8f5f46c2-32c2-4a01-a5b4-32370e020b37","resolution":{"observed_at":"2026-08-15T23:28:02.277300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.03605","last_updated":"2022-07-11T10:30:29Z","snapshot_observed_at":"2026-08-18T07:50:02.322273Z","submitted_at":"2022-03-07T18:55:26Z","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.03605","snapshot_observed_at":"2026-08-15T23:28:02.281787Z","title":"DINO: DETR with improved denois- ing anchor boxes for end-to-end object detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.281787Z"},"links":{"cited_paper":"/paper/2203.03605","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:73038eebaa6743b496f70951fc0519f6abb57ea643d9221cd83b3559bb8145c7","observation_id":"305081b0-f7db-4dd4-a253-77d3dbce7278","resolution":{"observed_at":"2026-08-15T23:28:02.281787Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.12156","last_updated":"2023-06-21T10:08:29Z","snapshot_observed_at":"2026-08-16T15:22:17.250833Z","submitted_at":"2023-06-21T10:08:29Z","title":"Fast Segment Anything","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.12156","snapshot_observed_at":"2026-08-15T23:28:02.286033Z","title":"Fast segment anything","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.286033Z"},"links":{"cited_paper":"/paper/2306.12156","citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:161732afb458ca74ea8977e0aff3728ef244f9930dc94a47baeddc1a5784a9b2","observation_id":"886701a5-48a0-4a69-aba7-ead861ff1d20","resolution":{"observed_at":"2026-08-15T23:28:02.286033Z","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":"2026-08-15T23:28:02.537756Z","title":"DarkSAM: Fooling segment anything model to segment nothing","venue":null,"work_id":"d5bdab21-8215-493e-af6b-6c75cb0ff59d","year":null},"citing_paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T23:28:02.289894Z"},"links":{"citing_paper":"/paper/2505.04861"},"observation_digest":"sha256:ceaf67abc59fb67ccfdc66b644e20881cdbab313a7d1b1e2c0f66dd7a8123506","observation_id":"79005f7c-d723-418c-ae8a-4383fd756455","resolution":{"observed_at":"2026-08-15T23:28:02.541453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.04861","last_updated":"2025-05-08T00:08:31Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T09:08:50.583164Z","submitted_at":"2025-05-08T00:08:31Z","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model"},"reference_resolution":{"displayed":63,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":2,"verified_fuzzy":43},"total_outbound_references":63},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 0 inbound Pith citation observations for arXiv:2505.04861."}