{"as_of":"2026-08-08T20:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:21212fde1ace86a5d74c03b0d648562ae40658967b7bb2306ff4737b34afb334","coverage":[{"denominator":57,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":57,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-14T22:32:36.129552Z","state":"measured"},{"denominator":58,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":58,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T17:00:07.051978Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-06-28T17:02:24.004322Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"cited_work":{"arxiv_id":"2603.11917","doi":null,"metadata_source":"pith","pith_arxiv_id":"2603.11917","snapshot_observed_at":"2026-06-28T17:02:24.004322Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","venue":"cs.CV","work_id":"3ade4907-11e9-401a-a09b-7eab2f048a29","year":2026},"citing_paper":{"arxiv_id":"2606.01271","last_updated":"2026-05-31T14:52:52Z","snapshot_observed_at":"2026-08-07T20:00:21.056453Z","submitted_at":"2026-05-31T14:52:52Z","title":"Exploiting In-Sensor Computing for Energy-Efficient Earth Observation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-28T17:00:07.051978Z"},"links":{"cited_paper":"/paper/2603.11917","citing_paper":"/paper/2606.01271"},"observation_digest":"sha256:b6a15c884a3b85aa19c69f80750b9f699d940539cdf3b2be63be7f69120ba585","observation_id":"1e313e83-5e31-40e4-9f9c-ed1cb0311a83","resolution":{"observed_at":"2026-06-28T17:02:24.005846Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2603.11917/citation-record","integrity":"/paper/2603.11917/integrity","json":"/paper/2603.11917/citation-record.json","paper":"/paper/2603.11917"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T22:32:36.129552Z","title":"Segment anything,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:6869697b5350c205a72090bce5a5117d12478337c3a05ed6323ab5b21e3e9119","observation_id":"871c7960-7223-44be-8272-2b07d9badfa3","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Sam2: Segment anything in images and videos,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/2408.00714","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:d4e8ac47bd6028828e4c2ada4d63bdd49823c0645f09860fdaea7380c53461e5","observation_id":"429dba50-21e3-42e2-8496-c08b7baa61d5","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.16719","last_updated":"2026-03-28T16:54:56Z","snapshot_observed_at":"2026-08-07T05:59:39.049027Z","submitted_at":"2025-11-20T18:59:56Z","title":"SAM 3: Segment Anything with Concepts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.16719","snapshot_observed_at":"2026-07-14T22:32:36.129552Z","title":"Sam 3: Segment anything with concepts,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/2511.16719","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:0629f19d9ec7efca5149d2ad17a51b8246306730226c051ff2431ad0970651f5","observation_id":"8eaae0ae-bbad-4dd4-b1fa-0a2fb56006ca","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Efficient remote sensing image target detection network with shape-location awareness enhance- ments,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:609d8915d167e7ed70ff6ce9af022cf815ba04811013258a22fe2c824890872b","observation_id":"d1681fba-195a-49d5-bf89-768cf8dca6d6","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Pi- cosam2: Low-latency segmentation in-sensor for edge vision applica- tions,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:662bcd634c416e02d16ecd4eea7f24b9796ace457c5d46b37ff10b4ad06832cd","observation_id":"5a7993fa-a020-4187-b0cf-1ac9b42171c2","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"A novel embedded deep learning wearable sensor for fall detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:e9288b36bb506b27cf022c6cd69277dd4c25455d678f60cda62b5664434a7afd","observation_id":"dc346267-95ea-4e0a-974c-d5c799afef62","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Low-power detection and classification for in-sensor predictive main- tenance based on vibration monitoring,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:231678a5b5e77ac6786e8242a5668eeb768d51267031d6b825e1ab6b5bc93a33","observation_id":"5e0a9eae-67cf-4641-8771-db56165b3f6c","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Ultra-efficient on-device object detection on ai-integrated smart glasses,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:b4126da0c0a9c9a9a6fef8e9689106b9cf614f915b543eee95c52380a2b6b8ac","observation_id":"81acb796-58df-485e-86b8-0b349f57a998","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Fann-on-mcu: An open-source toolkit for energy-efficient neural network inference at the edge of the internet of things,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:9da7fd377cf375c85b52a9ec84da95b601637cd3ebb524731d6ee807528f1d96","observation_id":"261024c3-7b0f-4396-a14b-a59f84520d20","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Survey and comparison of milliwatts micro controllers for tiny machine learning at the edge,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:17efab129b0c57957619a36e8a6b577627387b82cc845c5c6f8d13022f81f372","observation_id":"1218550e-317f-48e4-9e0f-53793e03ee44","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Low latency visual inertial odom- etry with on-sensor accelerated optical flow for resource-constrained uavs,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:3276e8991d5c2eeeee4449472adde83a055b9890012dc0b751ed82171d6cfcf8","observation_id":"3a8c7221-5b47-416f-802b-c9126ed813fe","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"A real-time intelligent system based on machine-learning methods for improving communication in sign language,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:7010b8a9b5ada8fb7238c8a6e939b120da010d4c9e87d92a56d43088eb9a4383","observation_id":"eb251672-dbe1-4618-a37e-7e1d59ba6a3c","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Design and implementation of a resnet-lstm-ghost architecture for gas concentration estimation of electronic noses,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:6269aa1d66b2bc08487bad77688c60beaa1f2df2eea475ade92481458495399c","observation_id":"ae53a18d-c58c-41ed-92cd-e3ee84ec029e","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"A mixture-gas edge-computing multisensor device with generative learning framework,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:ee8a1a4b1ce5a88260f82df429e0c1046ebacda0badc2c8eaf5981e5957b7d56","observation_id":"f8188428-dc96-4dcc-be4d-dee577011472","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Aviear: An iot-based low-power solution for acoustic monitoring of avian species,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:9ed5475e38077c29e5dfaa31423150a6c41869ba702d3781fdb8aac5853b5b85","observation_id":"ef8ee4be-1c8e-4aa5-b4d1-80cf53257303","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Sim- ulation, design, and application of intelligent-edge-based soft magnetic tactile sensor with super-resolution,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:05b449b427f29de0ef498f680af8bc5c9b7939d26a56d0726933ffdebac7acbc","observation_id":"1fe5a6e0-2a06-4f53-b9dd-aa5e0972c97e","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Design and implemen- tation of an arm-based ai module for ectopic beat classification using custom and structural pruned lightweight cnn,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:2c5b16883771f30e582298ea4ec2a6f3f22ec9c9ffcca257baf75dd18045081d","observation_id":"b3a18011-c0f1-42aa-bb3b-cc92dd62a70e","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Preliminary analysis of the exploitation of qvar sensor for gesture recognition,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:5a4a731db4355477938cbaff9431d223b668da77c3b9ad43ba612ce566b510ba","observation_id":"a336d834-7df9-4005-9fa5-264689809092","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Sony imx500,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:bf3b89669dd17fc219bd073c691ad47207d1a1a4456d1872c8fc553d89065b04","observation_id":"5df8b94c-f692-4a0d-bb3b-43f171afa658","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"A 1/2.3inch 12.3mpixel with on-chip 4.97tops/w cnn processor back- illuminated stacked cmos image sensor,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:47ac4f1556ddd11defe21fc0bdd084e71a2ce94621bb108f64840ed7390d7cec","observation_id":"e35562c1-92fc-4d9f-bdee-e7827c62a9c1","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Tinytracker: Ultra- fast and ultra-low-power edge vision for in-sensor gaze estimation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:5fb4a12816ebb838596ee6b25b781b58e9afd75f807023a41321d22571142389","observation_id":"81d8674d-ad5d-429a-814c-2bc8ec41debe","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Near-sensor and in-sensor computing,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:94e0b0964cd896f0c7aef65cf199191701ee05534edd311a3bed4fe1931fb7c4","observation_id":"5406a069-e97e-4f84-9889-153babf10849","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-06T17:06:29.162729Z","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":"2026-07-14T22:32:36.129552Z","title":"Tinysam: Pushing the envelope for efficient segment anything model,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/2312.13789","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:af098091ea034c950899452f6679973d3df2a1c5f3b8a5b5035f9a9153c13b86","observation_id":"58324791-3a71-4f90-b6a4-fb17f7b53680","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Edgesam: Prompt-in-the-loop distillation for on-device deployment of sam,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/2312.06660","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:396bf5fc614b9ebc1aaa8de8bc7d466e52fdb98d5f5404286e1ca499dc5e21ec","observation_id":"a19a1bfa-2296-415c-a073-5203642ca4e1","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-07-14T22:32:36.129552Z","title":"Mo- bilesamv2: Faster segment anything to everything,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/2312.09579","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:cb1e7994f02eb58be756eaca90454e2f8aad86a186448ed75c87fd4548c87f01","observation_id":"239530f7-d564-4821-9210-e9aaef263fbd","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Lite-sam is actually what you need for segment everything,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:76d919395e7c5e3bb92402ae331be42cddb49ad346971831182ce3a49f52bc98","observation_id":"b161ed76-9cd2-4e70-a776-9fc9c00cf2e1","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Efficient deep learning: A survey on making deep learning models smaller, faster, and better,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:da3c093efe9ab61b39610e5b60db43a0d9437b35c436f6f6bc9d1b46ec403300","observation_id":"32c74882-adbd-480e-a77e-f740668d27ea","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Mobilenetv4: Universal models for the mobile ecosystem,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:693e752688cf6c3e7585cb2886e53910c959030677657ba08bdb3d910875313d","observation_id":"c262278e-b0c3-4f36-b90a-a9e314599513","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Eca-net: Efficient channel attention for deep convolutional neural networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:c1523ff3b290c7ec6d1305900a144c50091bbbe42c4c47f50ecfa9f34f17cdf7","observation_id":"bcf25206-201f-4213-ba90-21af2a4df683","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.06211","last_updated":"2024-10-19T13:37:59Z","snapshot_observed_at":"2026-07-06T15:40:58.515223Z","submitted_at":"2023-05-12T07:21:59Z","title":"A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.06211","snapshot_observed_at":"2026-07-14T22:32:36.129552Z","title":"A survey on segment anything model (sam): Vision foundation model meets prompt engineering,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/2306.06211","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:3a8988e8565704c3c5d26a2a538a34f7acc6560b5b70774e625e11b006e9f0cb","observation_id":"757b6ce0-f81f-49b4-86ad-394e0ecac6f5","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-07-14T22:32:36.129552Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:e220a835399c106ccb1bb0c82f8e0c23ac969ffbaee83d01142dbc2a6433e942","observation_id":"7b430b2f-c8cd-44b4-a30f-4915cf5e30d4","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Fast segment anything,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:7ec789896e3c0d634f3d62f706136851da3ae70d9f001130dc34045632a22afb","observation_id":"42724c2f-7820-4d4d-9f0d-75e74a6b3485","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-08-08T16:17:33.420400Z","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":"2026-07-14T22:32:36.129552Z","title":"Faster segment anything: Towards lightweight sam for mobile applications,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/2306.14289","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:fd8df1fa5e400edd1eb8c3111fe333d6b4fd51931e9a645eac281ea2b2803f82","observation_id":"e71f9e02-4c4a-4627-a131-7e5af323f714","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Expediting large-scale vision transformer for dense prediction without fine-tuning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:c0a07185195cd4acd3d87be0bc38a5a8d03b73ca648b3a3697095b6a25c39469","observation_id":"5e7ed4de-3af9-4411-8d15-e846d5c47ccc","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.05284","last_updated":"2024-09-26T05:41:56Z","snapshot_observed_at":"2026-07-06T16:58:59.299777Z","submitted_at":"2023-12-08T12:48:53Z","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.05284","snapshot_observed_at":"2026-07-14T22:32:36.129552Z","title":"0.1% data makes segment anything slim,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/2312.05284","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:2b336eaac506e6d4bb459d9d646008652d03237047b1934cb19e6cb67c81e135","observation_id":"a71aa81d-29ef-4d08-a571-1a6a6ab7ff40","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Ptq4sam: Post-training quantization for segment anything,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:99479bbe53702c5dd29ea0b75d36ebc98e8361e14e569217999c8ce43f96c226","observation_id":"2d0b5ed2-56be-48d4-8e0e-046e163517f0","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Pq-sam: Post-training quantization for segment anything model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:7fba8b9b97b7e863a60affb558fb8a44703ef7386d90a6f5765f2a64a0542ec3","observation_id":"77454bca-ad01-4c42-932a-3ee3d34e02db","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Post training 4-bit quantization of convolutional networks for rapid-deployment,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:c79452348d4cb15c79221a6e6451dabefce7304665234b41806296befef4682c","observation_id":"bdfb3d53-ce5e-4096-b470-723d0b4380da","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Up or down? adaptive rounding for post-training quantization,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:1044dbeba437a59d966757a6e779f88f561a1b33212226ed4fa46846a3a8cf94","observation_id":"4e436f36-177c-4dd0-96ef-5d0ebbeeeaa8","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Hiera: A hierarchical vision transformer without the bells-and-whistles,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:aa1d3fa4737094dbac546f3a47324376db2f05c69736f50bb5ce9ab2dfe7a051","observation_id":"6ca90036-a152-4974-acb6-b03abb8b3c1a","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Masked autoencoders are scalable vision learners,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:19fd1cf956122d36bdb850f134c2a837aade162737e46c4ec90af5bd6f637860","observation_id":"617d086d-cf1b-4fcc-be89-da129f55a1a6","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Autoppn: Learning to design promptable pyramid networks for efficient segmentation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:f39d31e19fe4be09b3c052f17a9b6d1c3ace87ba73720d6dbb08f8740c518488","observation_id":"7306ba4b-f65b-443d-b67a-d62bcdbc2bf0","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.13429","last_updated":"2025-03-04T18:20:36Z","snapshot_observed_at":"2026-07-06T15:07:15.095030Z","submitted_at":"2023-03-23T16:50:08Z","title":"Interacting Particle Langevin Algorithm for Maximum Marginal Likelihood Estimation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.13429","snapshot_observed_at":"2026-07-14T22:32:36.129552Z","title":"Litevit: Towards efficient vision transformers with enhanced token mixing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/2303.13429","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:d0a466c0de6e70186597f6d088b121000054f79746bff4d0ae87d67ad88abcf6","observation_id":"f359a5b6-a89e-41d2-9414-c567ec9dc79c","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Edge AI-enabled chicken health detection based on enhanced FCOS-Lite and knowledge distillation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:f18359c530d5480cf344caa754b2f93548495183a3dfe7924bd20926cd0edbdd","observation_id":"55e7f143-b95b-4b2d-ac33-f328953b59af","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Pedestrian Warning: Intelligent Vision Sensor vs. Edge AI with LTE C-V2X in a Smart City,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:feabc08ada938e1e5a1bbfc3692b0b1fa2885d53f87e4ea63bad10227e54ca12","observation_id":"41fed04d-505c-4978-ad99-9f2fe1a8c0f8","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"U-Net: Convolutional net- works for biomedical image segmentation,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:8921ef83e6409b16ae45fd79b37b7ea4cea3cffdda15295eabdad78f44e38f0c","observation_id":"42b096b8-c1ac-4cb6-a9d6-97e328af32b1","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Xception: Deep learning with depthwise separable convolu- tions,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:2933844bb673e143b972f61a4631b2b987207f042d0ecad028a819b57c36d8f1","observation_id":"11057fa2-39e8-4af5-add3-d755bcfddd67","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Distilling the knowledge in a neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:d8fd3fa53b9e76d5c5192c465e04b840138c99dd241d22da9d1e22c5c2bcc97f","observation_id":"40764b99-9763-46ed-940b-64a4ac0a3b04","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"V-net: Fully convolutional neural networks for volumetric medical image segmentation,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:d308cdf5f40c4a2da188278f5c240ff14ab1bec0b46befa1faa60f8db75e9f40","observation_id":"74f92a9a-63e4-4605-8e6e-99a1eacc5ce3","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"V-net: Fully convolutional neu- ral networks for volumetric medical image segmentation,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:46df94461ec6504e78d90f0d48e152cb89c9052f2553b4b673004b9657aea534","observation_id":"8751d904-0e14-46e1-90cd-ae95c3ce8077","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.01108","last_updated":"2020-03-01T02:57:50Z","snapshot_observed_at":"2026-08-07T19:07:36.327251Z","submitted_at":"2019-10-02T17:56:28Z","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.01108","snapshot_observed_at":"2026-07-14T22:32:36.129552Z","title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter,","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/1910.01108","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:754ae0baaafc2dee91e6a74fc0c8aed9b850efb747e9cbadd1428ceec7168280","observation_id":"200c0354-6089-41a9-9fc3-933ae605adb0","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Decoupled weight decay regularization,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:52e4fd588f2b1b44bab0e4ade73c49701625d346c6ab242ca40626bb09713626","observation_id":"131a405a-4f9e-43a8-a176-63b30ba45752","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1405.0312","last_updated":"2015-02-21T01:48:49Z","snapshot_observed_at":"2026-07-06T03:42:37.507458Z","submitted_at":"2014-05-01T21:43:32Z","title":"Microsoft COCO: Common Objects in Context","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1405.0312","snapshot_observed_at":"2026-07-14T22:32:36.129552Z","title":"Microsoft coco: Common objects in context,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/1405.0312","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:cc81d080c790ca72d162befc3d2de5dc4e4ebb40d37e1e8a3635e3325fa1d59f","observation_id":"f32dbdec-b7e1-479d-a706-903ed838648d","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.09113","last_updated":"2021-11-16T08:44:39Z","snapshot_observed_at":"2026-08-07T19:17:54.161941Z","submitted_at":"2021-09-19T12:45:01Z","title":"HPTQ: Hardware-Friendly Post Training Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.09113","snapshot_observed_at":"2026-07-14T22:32:36.129552Z","title":"Hptq: Hardware-friendly post training quantization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/2109.09113","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:7a3ea88c392ad439a097d50f55134ddfcd1b5a72a9fa9c838cf8b586008ba931","observation_id":"ca81d943-5024-4ec6-a82c-73ebc74c3538","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Eptq: Enhanced post- training quantization via hessian-guided network-wise optimization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:2b216c13a2fc2cbd5371a81de8ad1f5ede6e2a86f1b303a52006a1ed1210ebb8","observation_id":"a6957b24-5333-495e-85b9-26cccb4df47f","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","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":"2026-07-14T22:32:36.129552Z","title":"Data generation for hardware-friendly post-training quantization,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:4d5672298c982618e683b1d42fcfaf25db154568d1453bd667231c14c7b68daa","observation_id":"c818c689-7b89-4ee2-a179-aee85044e83a","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.13630","last_updated":"2021-06-21T21:01:12Z","snapshot_observed_at":"2026-07-06T10:53:11.986981Z","submitted_at":"2021-03-25T06:57:11Z","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.13630","snapshot_observed_at":"2026-07-14T22:32:36.129552Z","title":"A survey of quantization methods for efficient neural network inference,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","version":4},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-07-14T22:32:36.129552Z"},"links":{"cited_paper":"/paper/2103.13630","citing_paper":"/paper/2603.11917"},"observation_digest":"sha256:ae7f6126b257493f660755c2169e7ef3cf7863f320ba694f09cb674ee8fb9308","observation_id":"19e7a59f-1396-4116-b23e-28ada2ad86db","resolution":{"observed_at":"2026-07-14T22:32:36.129552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.11917","last_updated":"2026-06-19T06:31:29Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T09:49:05.377173Z","submitted_at":"2026-03-12T13:31:43Z","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation"},"reference_resolution":{"displayed":57,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":57,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":57},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 1 inbound Pith citation observation for arXiv:2603.11917."}