{"as_of":"2026-08-15T19:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a32e9dd08625fe3debe2e3129aee71d9183117766211cc6bcd6a5327e0352495","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-20T12:15:10.404261Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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":"2026-08-01T11:43:11.216668Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.18013","snapshot_observed_at":"2026-08-01T11:43:11.216668Z","title":"Tinysam 2: Extreme mem- ory compression for efficient track anything model,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.19811","last_updated":"2026-07-22T06:42:27Z","snapshot_observed_at":"2026-08-15T13:15:09.881095Z","submitted_at":"2026-07-22T06:42:27Z","title":"Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T11:43:11.216668Z"},"links":{"cited_paper":"/paper/2605.18013","citing_paper":"/paper/2607.19811"},"observation_digest":"sha256:087a4bc82d4292e357ca16e6c2c9e011b64c3fc14f3c46363de18a1cf6663ceb","observation_id":"c67e17da-b85a-43d2-9b1b-fdaafcfbe305","resolution":{"observed_at":"2026-08-01T11:43:11.216668Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2605.18013/citation-record","integrity":"/paper/2605.18013/integrity","json":"/paper/2605.18013/citation-record.json","paper":"/paper/2605.18013"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"709f9a45-d2d6-46af-aaab-aef9774dd8a1","year":2022},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:764d14fe4a6f958a2a3b3f9eb8d3e8c00cf4fa1d833d88953447f87e4341a99b","observation_id":"ede6d64d-0d7b-42e2-81d4-23820965aaa9","resolution":{"observed_at":"2026-05-20T12:18:17.475014Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Rethink- ing space-time networks with improved memory coverage for efficient video object segmentation","venue":null,"work_id":"7beea0a2-2724-4390-829a-0224cbdaa878","year":2021},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:69d7b79d3089ee5118356666ff83159c1e9254cf1d9976343aabdf6da079a304","observation_id":"50681918-f5a8-436e-a915-f941c704f0ea","resolution":{"observed_at":"2026-05-20T12:18:17.458102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Modular interactive video object segmentation: Interaction-to-mask, propagation and difference-aware fusion","venue":null,"work_id":"01ec0c93-4679-44df-9f37-2dce659e371d","year":2021},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:ac31b4f4662101620cec081bcd27d0a9f1da263dab0f0ac61adcf92747d030ac","observation_id":"352d936e-de60-4109-8e38-778afdb835f8","resolution":{"observed_at":"2026-05-20T12:18:17.455909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Tracking anything with decoupled video segmentation","venue":null,"work_id":"7a83395d-76a1-4468-9225-d47d3b0ffae0","year":2023},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:b47507da3f610d5eae6f9f2f9f723ea2ed275634c63e7fc0582a14b5cc97bba3","observation_id":"795d21e1-016f-4330-ae73-ca676cc1ff76","resolution":{"observed_at":"2026-05-20T12:18:17.471280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Price, Joon-Young Lee, and Alexander G","venue":null,"work_id":"b5adf4a3-c089-4894-872d-7a8cbf9535e5","year":2024},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:364f9ee7b6e625f4970045b16b95e8b5b94b4c50bd95636cffb78d995027c643","observation_id":"62202ecf-59d7-4c80-8511-09f088628af5","resolution":{"observed_at":"2026-05-20T12:18:17.451818Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Putting the object back into video object segmentation","venue":null,"work_id":"f1d5bc7a-bcdc-4345-aa92-4ddd729455f8","year":2024},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:eb2140f5a2e26a804cc02d0ba822a0fb1fabb5bc9f4eb0798d848b2b51c0246e","observation_id":"0f1cbe8b-bec4-4d4c-a8f8-57ee97bddd6d","resolution":{"observed_at":"2026-05-20T12:18:17.473267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Interac- tive video object segmentation using global and local trans- fer modules","venue":null,"work_id":"77f41abf-d128-411a-a481-67d245a2a4e2","year":2020},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:efca068feb2eaa58d789f5b474983742163c069953d98333ab3311175c596c9e","observation_id":"1618f641-2c5e-45a4-ad6a-bd7078c05841","resolution":{"observed_at":"2026-05-20T12:18:17.476949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Unsupervised video object segmentation using motion saliency-guided spatio-temporal propagation","venue":null,"work_id":"ed70114b-7409-4e5e-b324-90c1eeab297c","year":2018},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:d315affe3ad161760793cdb524f493be0bc62bc5af6ba75795bbbc1a162a35db","observation_id":"fe3bba5a-4845-46fb-ac3d-072cd2a0f799","resolution":{"observed_at":"2026-05-20T12:18:17.469456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Berg, Wan-Yen Lo, Piotr Dollar, and Ross Girshick","venue":null,"work_id":"b8e0f82c-f9b2-442c-b0d6-3c13cd563ae0","year":2023},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:2a31228bb26928d26f58e9304280b0b02269635878254bcb3a967c8b0eea87df","observation_id":"68d0dce5-51f4-4612-8f50-579e30154098","resolution":{"observed_at":"2026-05-20T12:18:17.486622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Recurrent dynamic embedding for video ob- ject segmentation","venue":null,"work_id":"f0b7fc78-c35b-409c-b50f-620c6fbcf827","year":2022},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:4ef0639f857fdb8a0c4c841cd9e8291b90913425f045400ab23351779c15cb47","observation_id":"e9ef6b82-3706-431c-955b-e5834e52d406","resolution":{"observed_at":"2026-05-20T12:18:17.497123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Unsupervised video object segmenta- tion with motion-based bilateral networks","venue":null,"work_id":"846c04e7-cee5-41d0-9618-e6a6c430682a","year":2018},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:b44786abdb0821075bfbb543cfc6e8f2f050003844bde4a28570c03f72b00088","observation_id":"8c0b26ed-b29c-4d12-93e2-80419c37130d","resolution":{"observed_at":"2026-05-20T12:18:17.462639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-07-09T00:25:49.265602Z","title":"Decoupled weight de- cay regularization","venue":null,"work_id":"aaa4d44f-b81a-449f-a3ea-e9a244634864","year":2019},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:b3fd09c5aa58bb03c9747900e117d0df7f864c7c9651594fc8b7fd23f11521a4","observation_id":"329f18a4-35ca-47ca-afd7-5051f8e754e1","resolution":{"observed_at":"2026-05-20T12:18:17.488746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"See more, know more: Unsuper- vised video object segmentation with co-attention siamese networks","venue":null,"work_id":"fccbf01e-9b5c-438a-9e90-95bc96a02386","year":null},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:cd3ccccb65a0f5b304fbfd8e1988741b3f698bc2a9ae9d1f61ed22fe6f8840cc","observation_id":"ad5b204a-8c15-408c-ad20-f3cd7028c7b6","resolution":{"observed_at":"2026-05-20T12:18:17.499050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Segment anything in medical images.Nature Communications, 15(1):654","venue":null,"work_id":"b20f4965-641c-4f24-8296-d536fd410d50","year":2024},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:9f2708ba06aeac5d0a6d9def313591ca8be1194fdadd0e2d90c20c6ecebfe254","observation_id":"077016a3-aedb-4342-a052-ca21548e4caf","resolution":{"observed_at":"2026-05-20T12:18:17.505212Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Segment anything model for medical image analysis: an experimental study","venue":null,"work_id":"ee907308-bf5c-48d2-9df1-8acc8e00373e","year":2023},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:9e87dfa992e940be24c19bf874b17f6a6405623389ec81f1942214678784a7ed","observation_id":"2e7c519b-be98-4fcb-b0b3-5faab76f2433","resolution":{"observed_at":"2026-05-20T12:18:17.445804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Sam- i2v: Upgrading sam to support promptable video segmen- tation with less than 0.2% training cost","venue":null,"work_id":"4e0c61d4-ad12-4be6-b0c7-794232d362fd","year":2025},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:b3c1d75e7b47b90f097dd1f6048e56ecc5b11929b52331517acbf6defb12d23e","observation_id":"8ce7ee30-72bd-4ba6-a8e7-0ff621918c07","resolution":{"observed_at":"2026-05-20T12:18:17.464895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Memory aggrega- tion networks for efficient interactive video object segmen- tation","venue":null,"work_id":"792ea617-682f-422f-a2c7-c96a8cb3a0d0","year":null},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:14dda7bae2e7549c3646ea41c3f98d77f207e6eba71ab3b5d3cce4691013a3aa","observation_id":"d83ea97a-df12-4503-887c-30ff0c9c468a","resolution":{"observed_at":"2026-05-20T12:18:17.443764Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Fast user-guided video object segmentation by interaction-and-propagation networks","venue":null,"work_id":"76e88d3f-ac5e-456c-ad77-e18308b2663b","year":2019},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:dd48ff84dc2a463ba7e00a6f1d892f8fd57e38429e4164c3f242ae5773439076","observation_id":"7cedb340-7504-4412-9d92-408c92007430","resolution":{"observed_at":"2026-05-20T12:18:17.460233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"The 2017 davis challenge on video object segmentation","venue":null,"work_id":"879838dc-bb70-436f-adee-f185c674d14b","year":2017},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:e208952ef89e050d824d59628a3ca6e5661d8aa858193b3beb7551680d0f76e8","observation_id":"46e688f3-833e-42a4-a3ca-97557495f664","resolution":{"observed_at":"2026-05-20T12:18:17.467418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-07-09T07:06:04.106790Z","title":"Sam 2: Segment anything in images and videos","venue":null,"work_id":"7859b4d2-fab5-4c76-a8d0-48c8a9564214","year":null},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:9bed777613526630ee24296d1325168d47287341b366bc188027287719badaf5","observation_id":"8226b73c-4fb3-42d7-a32a-a491458ebb2c","resolution":{"observed_at":"2026-05-20T12:18:17.448102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Hiera: A hi- erarchical vision transformer without the bells-and-whistles","venue":null,"work_id":"385a9f1a-e83c-42aa-bca5-5bf4b78669dd","year":2023},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:836ed881b4ba5c00539a4d42a5d12a27cb89cb932e8208f58e93cabc7a4a7a1b","observation_id":"928023fa-611f-4c89-b0b0-74890fac7116","resolution":{"observed_at":"2026-05-20T12:18:17.453872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Ef- ficient video object segmentation via modulated cross- attention memory","venue":null,"work_id":"b9f8e9a8-b4f3-407e-89c8-beda96859d80","year":null},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:c6a48d4635c37de5fb7b65c1a8ddb8e1196efdf6e2f0d4427991bc7a92e820a8","observation_id":"47c6fda8-7484-4c54-acb1-f978c9563fa0","resolution":{"observed_at":"2026-05-20T12:18:17.449970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Tinysam: Pushing the envelope for efficient segment any- thing model","venue":null,"work_id":"cea91013-a9bb-4e14-a64f-bb53b81d5abd","year":2025},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:5dae08f34e4e37bf9d17b53a0277fbe6c7861ef399843996a6307fe33317bf7f","observation_id":"3451defe-77a4-430f-bf0c-c241cd7446b6","resolution":{"observed_at":"2026-05-20T12:18:17.479309Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Dycoke: Dynamic compression of tokens for fast video large language models","venue":null,"work_id":"b5bb03b3-9f6d-468d-a86f-6fb493d126fb","year":2025},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:2d7f81bf91e81bd66f505ab943a96a3c36a2e890dc4613c44f776311ed64e78a","observation_id":"b1fef65c-c9ea-48c6-a2c8-21188b42fc40","resolution":{"observed_at":"2026-05-20T12:23:28.388652Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"A distractor-aware memory for visual object tracking with sam2","venue":null,"work_id":"81809dc1-0640-4f5e-8d35-b2ae9792b84a","year":2025},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:74665fb7d9ef9ac2952749f6202dfc82477e44a7082f961fa7f34c8d63758534","observation_id":"3d284b79-e87c-40b0-be83-d7fca67ab9b5","resolution":{"observed_at":"2026-05-20T12:18:17.507450Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Repvit: Revisiting mobile cnn from vit perspective","venue":null,"work_id":"833ca112-9988-45c9-8995-0b5e32fe2c78","year":null},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:260a870d35d5d434d10307f62d945892e1308cdd1ad48610ded267368dde9883","observation_id":"40b685f7-d086-4077-a182-b0db35cfa00b","resolution":{"observed_at":"2026-05-20T12:18:17.509600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Learning unsupervised video object segmentation through visual attention","venue":null,"work_id":"fd154ae5-54a4-42ef-9a47-f73824d5e65c","year":2019},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:a18bc9976506e3ee2fc92d040fd6205a7833326a5cdf057b2ba27dbdacc01c3b","observation_id":"3dd1dabd-a748-42fb-a5cd-3d37923b1d37","resolution":{"observed_at":"2026-05-20T12:23:28.392185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Medical sam adapter: Adapting segment anything model for medical im- age segmentation.Medical image analysis, 102:103547","venue":null,"work_id":"8c65c63c-d4bc-42ab-b6aa-fbfe880b22d9","year":null},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:072c158d938a5efe380234f8924bae859921d7f672b453c8dd84e5c1acd7e815","observation_id":"adc57abc-47e9-49e3-87e6-2dc328cf1d05","resolution":{"observed_at":"2026-05-20T12:18:17.503217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Efficientsam: Leveraged masked image pretraining for efficient segment anything","venue":null,"work_id":"2bc55b0b-c853-486d-9170-3c85c11fe7ca","year":2024},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:5c7069e5f8d286f6008ce34567e1c7d11b50d738eaee90ce09c01a446904afca","observation_id":"76b3b19a-d30d-4c13-bafb-cfb151291dff","resolution":{"observed_at":"2026-05-20T12:18:17.493024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Efficient track anything","venue":null,"work_id":"3bca7794-dd19-4022-93ad-aa136e0084ab","year":2024},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:5f44d69d3911500e6ed8345246d4da3efb071ee6833744fdd472ba9d5ba637ef","observation_id":"1e741841-1965-4a4d-8457-67687d51bcfd","resolution":{"observed_at":"2026-05-20T12:18:17.494997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Youtube-vos: A large-scale video object segmentation benchmark","venue":null,"work_id":"32f18f13-07c5-46ff-b0e2-3a14624aade7","year":2018},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:4ca54918f0ed979fc8781ed5cec7cc3fc60d327e3a236035547638fb4f939210","observation_id":"7957a08d-31b0-464b-85c1-9360065a7996","resolution":{"observed_at":"2026-05-20T12:18:17.500972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Track anything: Segment anything meets videos","venue":null,"work_id":"94fc6319-9cf8-4d81-ae9e-bd4bf959be41","year":2023},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:eaee1c7f89ca16943100d59d265042ee099c0136eacb5a7e4d11e05e3eb50113","observation_id":"9883c472-6caf-4b25-ae86-81f3f5cffdfc","resolution":{"observed_at":"2026-05-20T12:23:28.390291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Scalable video object seg- mentation with identification mechanism.IEEE Transac- tions on Pattern Analysis and Machine Intelligence, 46(9): 6247–6262","venue":null,"work_id":"ddc77a3b-905b-4a4e-bdde-7699d31aba8e","year":2024},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:3def7ea65aeee3f383d4df2ee94db58e8f4ebe2f5662073e1a503745c4456ff2","observation_id":"77d1178f-3c85-4ba4-a6d1-ec85859eff2c","resolution":{"observed_at":"2026-05-20T12:18:17.490920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.14289","last_updated":"2023-07-01T07:26:22Z","snapshot_observed_at":"2026-08-12T07:11:05.316372Z","submitted_at":"2023-06-25T16:37:25Z","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","version":2},"cited_work":{"arxiv_id":"2306.14289","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.14289","snapshot_observed_at":"2026-07-04T21:00:09.639501Z","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","venue":"cs.CV","work_id":"d159afc6-0f47-4693-a3c0-908e661ff652","year":2023},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"cited_paper":"/paper/2306.14289","citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:5c6c5e5bf4148e6171a13a444bbffefa85090bb83ed2234457d10e18ad8ea9f4","observation_id":"569c5346-ec4d-4ec0-a48b-9b8fe15953fa","resolution":{"observed_at":"2026-05-20T12:18:16.653195Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.12156","last_updated":"2023-06-21T10:08:29Z","snapshot_observed_at":"2026-08-13T11:12:44.426861Z","submitted_at":"2023-06-21T10:08:29Z","title":"Fast Segment Anything","version":1},"cited_work":{"arxiv_id":"2306.12156","doi":"10.48550/arxiv.2306.12156","metadata_source":"arxiv_reference","pith_arxiv_id":"2306.12156","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2306.12156 (2023) 31","venue":"arXiv (Cornell University)","work_id":"feed3d9f-cc9f-42db-90e6-e9ff051cef57","year":2023},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"cited_paper":"/paper/2306.12156","citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:c75462be14cd4a7633616a19bfd9914c6267bec487af6b60af56e2310ced1536","observation_id":"273504ca-132c-4d30-a738-611aa901af34","resolution":{"observed_at":"2026-05-20T12:18:16.650430Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.06660","last_updated":"2025-09-07T19:09:41Z","snapshot_observed_at":"2026-08-13T05:04:48.830788Z","submitted_at":"2023-12-11T18:59:52Z","title":"EdgeSAM: Prompt-In-the-Loop Distillation for SAM","version":3},"cited_work":{"arxiv_id":"2312.06660","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.06660","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2312.06660 (2023)","venue":null,"work_id":"1debc274-246e-4b95-b845-8f5199ef0e29","year":2023},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"cited_paper":"/paper/2312.06660","citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:8edb0fcb9691759b45f4f2d72a95df4f1ffec66bf47c4e008f724b0fb5c3aca2","observation_id":"4b5c28c1-d9d9-40d9-b8aa-0399555d036d","resolution":{"observed_at":"2026-05-20T12:18:16.656549Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Ed- getam: On-device track anything model","venue":null,"work_id":"1b8b49c3-ba20-47f5-a99f-9edcaeb8b18e","year":2025},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:7c8ad37c99e4d7a0b6ca2c358ac6c178c2c6952ee6cffdf227aec10947dea11c","observation_id":"a080f4a1-cfdf-45cd-a72c-45836c25ab30","resolution":{"observed_at":"2026-05-20T12:18:17.482912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Rmem: Restricted memory banks improve video object segmenta- tion","venue":null,"work_id":"3bcdb702-4c44-4122-adb6-b0b31c0b3239","year":2024},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:34dd53e4cf973a96e9a3b2881328d75f73db4a7e71b42ca462d2a5e6eb3139ea","observation_id":"a82e9b9b-0c4e-4b14-9291-0f0e91251b7e","resolution":{"observed_at":"2026-05-20T12:18:17.481165Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-06-05T21:23:00.469572Z","title":"Figure 5 illustrates the ability to accurately seg- ment movements among animals","venue":null,"work_id":"2626ac3f-4435-4f79-bc72-fca889ac39fd","year":null},"citing_paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-20T12:15:10.404261Z"},"links":{"citing_paper":"/paper/2605.18013"},"observation_digest":"sha256:061b11e2a5dcd50b0cc0604eaee0bc8ac157359f1d6d2ce60d483d6791d750ab","observation_id":"1cd5c504-be5f-449b-ade8-750be7fd906e","resolution":{"observed_at":"2026-05-20T12:18:17.484748Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.18013","last_updated":"2026-05-18T08:05:59Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T23:40:37.664848Z","submitted_at":"2026-05-18T08:05:59Z","title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":1,"verified_exact":3,"verified_fuzzy":35},"total_outbound_references":39},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2605.18013."}