{"as_of":"2026-08-08T02:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7bc54692290ad415c5bb40e5396fcc16b3efac5b85e385d14972e25bfdba5ca6","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:20:01.135021Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2507.08765/citation-record","integrity":"/paper/2507.08765/integrity","json":"/paper/2507.08765/citation-record.json","paper":"/paper/2507.08765"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:00.905628Z","title":"Segment anything,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.905628Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:2aec4dcfc2c3ad5597a2ad9eabbb46decec351431fa4c55120f16138bbdfcb63","observation_id":"3b38b576-c9f9-4232-b6ec-665a428b5c0a","resolution":{"observed_at":"2026-08-06T18:20:00.905628Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.00924","last_updated":"2024-09-02T03:40:07Z","snapshot_observed_at":"2026-08-07T18:20:42.834568Z","submitted_at":"2024-09-02T03:40:07Z","title":"MedSAM-U: Uncertainty-Guided Auto Multi-Prompt Adaptation for Reliable MedSAM","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.00924","snapshot_observed_at":"2026-08-06T18:20:00.911194Z","title":"Medsam-u: Uncertainty-guided auto multi-prompt adaptation for reliable medsam,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.911194Z"},"links":{"cited_paper":"/paper/2409.00924","citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:ee37e309fbaae8a2ca4b8a97fc943de03a0983b87d419b71a7cb6d57ef2e661c","observation_id":"7290ac4e-7934-40f6-953a-9caf96713376","resolution":{"observed_at":"2026-08-06T18:20:00.911194Z","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":"2026-08-06T18:20:01.812902Z","title":"Segment anything in high quality,","venue":null,"work_id":"b6502c71-76ec-4562-81a3-9db72d16577f","year":2023},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.916618Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:111233b19a6d1bc1a2d0d0ec5db97edc5bcffafd6fff9c27743ba4eeec86da61","observation_id":"088e3ba1-acae-4532-8fbb-3ec3b33a6170","resolution":{"observed_at":"2026-08-06T18:20:01.820763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09579","last_updated":"2023-12-15T07:21:12Z","snapshot_observed_at":"2026-08-04T23:02:53.446031Z","submitted_at":"2023-12-15T07:21:12Z","title":"MobileSAMv2: Faster Segment Anything to Everything","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09579","snapshot_observed_at":"2026-08-06T18:20:00.924093Z","title":"Mobilesamv2: Faster segment anything to everything,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.924093Z"},"links":{"cited_paper":"/paper/2312.09579","citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:aab175d4f119383396b1cb15e1fde78c0ef10d1301bf2cd27577c8fd31c29a60","observation_id":"a058d4da-82a0-456f-a638-7b63f7dcdfd6","resolution":{"observed_at":"2026-08-06T18:20:00.924093Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.00714","last_updated":"2024-10-28T16:37:57Z","snapshot_observed_at":"2026-07-06T18:55:41.459417Z","submitted_at":"2024-08-01T17:00:08Z","title":"SAM 2: Segment Anything in Images and Videos","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.00714","snapshot_observed_at":"2026-08-06T18:20:00.931060Z","title":"Sam 2: Segment anything in images and videos,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.931060Z"},"links":{"cited_paper":"/paper/2408.00714","citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:d7c4b7056b76ed0d144973b66d1294ea2a4c5cf1aeda85fa235bb44502bdc9de","observation_id":"3b02a9c1-e73a-47b9-b9a8-2e4143658b47","resolution":{"observed_at":"2026-08-06T18:20:00.931060Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.06660","last_updated":"2025-09-07T19:09:41Z","snapshot_observed_at":"2026-07-06T17:00:00.321552Z","submitted_at":"2023-12-11T18:59:52Z","title":"EdgeSAM: Prompt-In-the-Loop Distillation for SAM","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.06660","snapshot_observed_at":"2026-08-06T18:20:00.943870Z","title":"Edgesam: Prompt-in-the- loop distillation for on-device deployment of sam,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.943870Z"},"links":{"cited_paper":"/paper/2312.06660","citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:a35641a8520ec2c6677f7ef278d04497e7282a3bf992837f49379da5793e3bab","observation_id":"6a8b9a16-ab44-4497-9e82-d1d90006f5f2","resolution":{"observed_at":"2026-08-06T18:20:00.943870Z","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":"2026-08-06T18:20:01.799850Z","title":"Efficientsam: Leveraged masked image pretraining for efficient segment anything,","venue":null,"work_id":"495074d4-5cf5-4277-ba56-f7b3add94ed3","year":2024},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.951707Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:599909fd44132c49a5cf52a7109c3d9be9889e1991541d936de10bdaf9e500d9","observation_id":"8826e435-889a-4457-abe9-d7eb2310ae3b","resolution":{"observed_at":"2026-08-06T18:20:01.804497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:20:01.784810Z","title":"Tinysam: Pushing the envelope for efficient segment anything model,","venue":null,"work_id":"c6dd84f7-d5a5-4e9d-bc24-60d57eed6c58","year":2025},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.962006Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:a344500b10433538f3f6469228fe3ef4605d85e19c07ce415c56f5ff2c37b6eb","observation_id":"1e7b2e09-99b3-45ef-ae5d-002e05d4f97c","resolution":{"observed_at":"2026-08-06T18:20:01.788740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:00.968151Z","title":"Segment anything in medical images,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.968151Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:667b0b090dc9bf5d250c1484cd4f4d428bb1a876b8656e53ed469443c698cd2f","observation_id":"f86dbcae-1b4e-445f-8e6e-3f849018729c","resolution":{"observed_at":"2026-08-06T18:20:00.968151Z","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":"2023.09602","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:01.456217Z","title":"An empir- ical study of catastrophic forgetting in large language models during continual fine-tuning,","venue":null,"work_id":"d771ae3a-5bb9-4ab4-b911-2178375b8dfe","year":2023},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.971632Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:a23150530a4521d7d853350b520bbd2666e2389f7a339ff10d99817e1d1872a1","observation_id":"7cde8883-c7cc-4001-a2f8-af7f4ed3c8a4","resolution":{"observed_at":"2026-08-06T18:20:01.468268Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:20:01.766703Z","title":"A survey on model compression for large language models,","venue":null,"work_id":"63d5be46-7621-482a-8010-525eafd3ae8b","year":2024},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.979029Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:7980dc9c24546210054848ee482571441dfae78645abc3904a4bd35969671a66","observation_id":"68ee955b-6ebe-4121-bbe0-7fa8c7719933","resolution":{"observed_at":"2026-08-06T18:20:01.771776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:20:01.748487Z","title":"Model compression for deep neural networks: A survey,","venue":null,"work_id":"64205747-1cb1-4db9-a488-c8d39c554424","year":2023},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.983591Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:dc8de69ded13c5ee1147bbd09fcd905efd6928e0713c9f6a33d09adbf1179bc8","observation_id":"c9768f39-bc30-47dd-b71b-a79f94097d03","resolution":{"observed_at":"2026-08-06T18:20:01.754527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2409.00592","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:01.372783Z","title":"Hyper-compression: Model compression via hyperfunction,","venue":null,"work_id":"70d9d521-76c6-45b3-b10a-22af99c01cd9","year":2024},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.987310Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:28f07906efd74084b1a799a702fa48e915ce2b5b43ff38e6a96a758fc6bd39c2","observation_id":"4709eb13-f5af-453c-8fdc-8bf401c368ad","resolution":{"observed_at":"2026-08-06T18:20:01.377558Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:00.991117Z","title":"Microsoft coco: Common objects in context,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.991117Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:4750bf64a9f2404d21ff52259884a092129c3de53fa390787a7badc8359a857f","observation_id":"392d0f39-2fac-473a-9dd0-9ae6b222bdc0","resolution":{"observed_at":"2026-08-06T18:20:00.991117Z","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":"2026-08-06T18:20:01.727508Z","title":"Lvis: A dataset for large vocabulary instance segmentation,","venue":null,"work_id":"bdeed374-9a63-48d9-9f1f-afa379336e85","year":2019},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.994753Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:c104983c25fa040f70b8676228e935037c02f35cfa1314129811b8544e09c29b","observation_id":"55d66ed7-262d-466d-a5ce-c21a25d94be6","resolution":{"observed_at":"2026-08-06T18:20:01.731708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:20:01.705867Z","title":"Sparsegpt: Massive language models can be accurately pruned in one-shot,","venue":null,"work_id":"06be5642-21d1-4809-80ef-26b22946ccb5","year":2023},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:00.998426Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:7a75a79cd719b890a9479a47aab78d70d175006425fc4cb97fbd55f50c7f08bc","observation_id":"a7e2e2c9-2db7-45f1-a162-24fa290efbfb","resolution":{"observed_at":"2026-08-06T18:20:01.717545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:20:01.008284Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.008284Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:aad2c819ef92b52052266b2aeb1242b1c9f41b75317a655a03b1ceaf95af0d28","observation_id":"2206c33f-bf82-46a3-8000-9f14f329172d","resolution":{"observed_at":"2026-08-06T18:20:01.008284Z","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":"2026-08-06T18:20:01.014383Z","title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.014383Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:072931791c6d22e51326055f9d66697a8da4e6d7d7a93eb685a767efe4927cde","observation_id":"02d2a591-d8d3-4235-8fe6-95a5e41e45c2","resolution":{"observed_at":"2026-08-06T18:20:01.014383Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08204","last_updated":"2024-03-13T02:56:31Z","snapshot_observed_at":"2026-07-06T17:43:44.153710Z","submitted_at":"2024-03-13T02:56:31Z","title":"AutoDFP: Automatic Data-Free Pruning via Channel Similarity Reconstruction","version":1},"cited_work":{"arxiv_id":"2403.08204","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.08204","snapshot_observed_at":"2026-08-06T18:20:01.279733Z","title":"AutoDFP: Automatic Data-Free Pruning via Channel Similarity Reconstruction","venue":"cs.LG","work_id":"22c5d1ea-e0bb-4a25-b567-eb0abbd44914","year":2024},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.020855Z"},"links":{"cited_paper":"/paper/2403.08204","citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:6482b26e5cef1ab8fd63137355edf954d416eda853e4ca69bdc2d939190886a9","observation_id":"9d2a95b6-d6ef-4d7c-be95-f122268d9f79","resolution":{"observed_at":"2026-08-06T18:20:01.287341Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-04T05:18:02.925670Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-08-06T18:20:01.035710Z","title":"Billm: Pushing the limit of post-training quantization for llms,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.035710Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:97e2f4b6b8212b7a4bec5d605b0dfc6e0b7aa91f8ef7b2342b68ccfd412e51eb","observation_id":"5876c83d-ada5-4daa-9847-d99eefed92db","resolution":{"observed_at":"2026-08-06T18:20:01.035710Z","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":"2026-08-06T18:20:01.672171Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference,","venue":null,"work_id":"531120c5-bbb3-45bd-b0fe-cc63dcdec4c1","year":2018},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.043310Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:5468e707169a966c2c789b73b9fece0794cd90d6220e6c9046c5c7a64f48875f","observation_id":"1f6326bb-1c54-4468-a449-e8334b8b23fc","resolution":{"observed_at":"2026-08-06T18:20:01.676153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.09602","last_updated":"2020-04-20T19:59:22Z","snapshot_observed_at":"2026-07-06T09:13:49.452689Z","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":"2026-08-06T18:20:01.054268Z","title":"Integer quanti- zation for deep learning inference: Principles and empirical evaluation,","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.054268Z"},"links":{"cited_paper":"/paper/2004.09602","citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:7d2024fd8670b35fe2a1e89441e64a35f5dda3cac230815e311504266d4d22b6","observation_id":"b3b3f99f-06db-4ab7-a298-b7d592d8ec7a","resolution":{"observed_at":"2026-08-06T18:20:01.054268Z","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":"2026-08-06T18:20:01.658839Z","title":"Low-bit quantiza- tion of neural networks for efficient inference,","venue":null,"work_id":"8d94fba3-cc44-47a8-bd33-39c7b3f59ac4","year":2019},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.061223Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:0815de1e917f1bbed23247e10d4bfe538a0399ef0ab36d4e70147dda17bdab22","observation_id":"5eed493c-504c-45ad-ad9a-c7e3c29c74e6","resolution":{"observed_at":"2026-08-06T18:20:01.664565Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:20:01.648519Z","title":"Zeroq: A novel zero shot quantization framework,","venue":null,"work_id":"eb7ea5e5-efb7-45c3-b439-7897aa9b1188","year":2021},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.068113Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:97c1ab0911ee5c498cd183578185a2a83f87be885e8610cb250b7a7698f143f3","observation_id":"fa441994-60f0-4354-b808-291ac2c7ae64","resolution":{"observed_at":"2026-08-06T18:20:01.652280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:20:01.636880Z","title":"Tensor-train decomposition,","venue":null,"work_id":"d052f461-c57a-4fa9-a63e-4fa26c5a892e","year":2011},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.072396Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:5f1782f76e3e329cfdd28aa91cd41e1bb084c55639c43f1585d6c6e371329138","observation_id":"46fe9380-95c6-4e1b-b6fb-42998ff258ca","resolution":{"observed_at":"2026-08-06T18:20:01.640927Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.05535","last_updated":"2016-06-17T14:40:18Z","snapshot_observed_at":"2026-08-07T12:29:52.495806Z","submitted_at":"2016-06-17T14:40:18Z","title":"Tensor Ring Decomposition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.05535","snapshot_observed_at":"2026-08-06T18:20:01.077415Z","title":"Tensor ring decomposition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.077415Z"},"links":{"cited_paper":"/paper/1606.05535","citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:787a1a609e23b142dcf32a8d4c7f00680981192e30be0bc8f9c39a618940346c","observation_id":"7c0b7b17-ae73-4fd8-b8cb-4db1cfb69e45","resolution":{"observed_at":"2026-08-06T18:20:01.077415Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16319","last_updated":"2025-02-24T07:41:18Z","snapshot_observed_at":"2026-07-06T17:35:18.965223Z","submitted_at":"2024-02-26T05:51:47Z","title":"Data-free Weight Compress and Denoise for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16319","snapshot_observed_at":"2026-08-06T18:20:01.082405Z","title":"Data- freeweight compress and denoise for large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.082405Z"},"links":{"cited_paper":"/paper/2402.16319","citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:306b48478bc4327b7b1e5bae2c61c60c0969f784f85b621710741a1fa4160636","observation_id":"c9feef32-523d-41e2-8d48-216a813d3df6","resolution":{"observed_at":"2026-08-06T18:20:01.082405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-06T18:20:01.086655Z","title":"Distilling the knowledge in a neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.086655Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:8b5e8895e315568d2a101150ee29c8a0c8dda52214900c0703bd3ccbea0f3fd2","observation_id":"b0722066-8566-4aea-8f39-bfbfff077365","resolution":{"observed_at":"2026-08-06T18:20:01.086655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.14289","last_updated":"2023-07-01T07:26:22Z","snapshot_observed_at":"2026-07-06T15:46:29.060519Z","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":"2026-08-06T18:20:01.091074Z","title":"Faster segment anything: Towards lightweight sam for mobile applications,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.091074Z"},"links":{"cited_paper":"/paper/2306.14289","citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:1b4f08ecd13dd1b9f344b6b6f48714ced7f5b0552af5716c0f2484208af7033b","observation_id":"5971c516-2150-45cb-8bbc-db871cc69197","resolution":{"observed_at":"2026-08-06T18:20:01.091074Z","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":"2026-08-06T18:20:01.625079Z","title":"Ptq4sam: Post-training quantization for segment anything,","venue":null,"work_id":"cf59975f-651b-402d-ba45-2e4ca07ad78a","year":2024},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.096585Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:89a4c5d25efc3ca5812480c79152a8c2858251cfcf0321628da3039be8a53a8b","observation_id":"6a995ba9-e428-453e-8b41-3e8b3369e7f0","resolution":{"observed_at":"2026-08-06T18:20:01.629112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:20:01.605569Z","title":null,"venue":null,"work_id":"336cbd66-0468-41d9-a200-50a2a8cdb3de","year":2012},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.101799Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:054f25dbbe6a777d4384ddfda05a0cdbe753b16a2d4cabeeca53b3d6acf61743","observation_id":"d1abb24c-638a-4fd5-8a43-13d4bfe58538","resolution":{"observed_at":"2026-08-06T18:20:01.610329Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:20:01.591276Z","title":"Vector quantization,","venue":null,"work_id":"21bac9d2-6fa1-4cc2-9c4c-cca7202eb898","year":1984},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.105563Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:6447c85466acdd1dd2b2c84805a0343bbba808bc4664d8e803cdde5db3e3da9a","observation_id":"0902caff-a80a-4045-8c0b-43a0e7a8679b","resolution":{"observed_at":"2026-08-06T18:20:01.595960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.05740","last_updated":"2023-02-21T11:24:41Z","snapshot_observed_at":"2026-07-06T12:46:41.057346Z","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":"2026-08-06T18:20:01.113405Z","title":"Qdrop: Randomly dropping quantization for extremely low-bit post-training quantization,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.113405Z"},"links":{"cited_paper":"/paper/2203.05740","citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:6ebeb9187a6b699e3076e3ded5749ef8646abd27110484a6a0a3fa5b4c3775a1","observation_id":"f9313f3f-3547-4483-9261-2d551fef9c30","resolution":{"observed_at":"2026-08-06T18:20:01.113405Z","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":"2026-08-06T18:20:01.569950Z","title":"Exploring plain vision transformer backbones for object detection,","venue":null,"work_id":"800dd688-ee22-4584-a9c6-5ff6c181c367","year":2022},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.118220Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:7ea3efdf60658ffc1912e4fab928a40ad8d61ef13c33e9ae77d17ff762a1ce39","observation_id":"97ad7334-a29c-4f8b-b580-6e5d62673f1e","resolution":{"observed_at":"2026-08-06T18:20:01.574698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.08430","last_updated":"2021-08-06T03:22:14Z","snapshot_observed_at":"2026-07-06T11:30:06.143581Z","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":"2026-08-06T18:20:01.123198Z","title":"Yolox: Exceeding yolo series in 2021,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.123198Z"},"links":{"cited_paper":"/paper/2107.08430","citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:a520c89e8b0bd1197fc86a695700f095920fd3e849064aefc21cd5b05fb0c397","observation_id":"2caba76f-b815-4115-9953-5f23af9e2718","resolution":{"observed_at":"2026-08-06T18:20:01.123198Z","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":"2026-08-06T18:20:01.545033Z","title":"Up or down? adaptive rounding for post-training quantization,","venue":null,"work_id":"403890a6-b01d-4630-ba33-d3abc720ecef","year":2020},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.127556Z"},"links":{"citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:70f1e5aa8010397c161d164f5eed6c2e80934310100c5d68065281f3e3b5a2b8","observation_id":"966bca85-63d2-4646-8515-567e0786d2dc","resolution":{"observed_at":"2026-08-06T18:20:01.549267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.05426","last_updated":"2021-07-25T09:34:39Z","snapshot_observed_at":"2026-08-04T09:21:27.169501Z","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":"2026-08-06T18:20:01.135021Z","title":"Brecq: Pushing the limit of post-training quantization by block reconstruction,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T18:20:01.135021Z"},"links":{"cited_paper":"/paper/2102.05426","citing_paper":"/paper/2507.08765"},"observation_digest":"sha256:4d438fc48840bf7d636b72aec3dda166497f2c83b3ace9b7f9e207ebd05783c2","observation_id":"e113b409-bfdf-4e43-b994-4cbf424d735f","resolution":{"observed_at":"2026-08-06T18:20:01.135021Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.08765","last_updated":"2025-07-11T17:21:06Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T23:42:59.261042Z","submitted_at":"2025-07-11T17:21:06Z","title":"Compress Any Segment Anything Model (SAM)"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":3,"verified_fuzzy":15},"total_outbound_references":37},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2507.08765."}