{"as_of":"2026-08-12T21:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:87fbaa1ee1d559443693f5439034ebccde42b60931b482a550acc3f90c327c84","coverage":[{"denominator":17,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":17,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T23:44:53.416936Z","state":"measured"},{"denominator":17,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":17,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2608.09091/citation-record","integrity":"/paper/2608.09091/integrity","json":"/paper/2608.09091/citation-record.json","paper":"/paper/2608.09091"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2004.13390","last_updated":"2020-04-28T09:42:41Z","snapshot_observed_at":"2026-08-12T17:39:33.442623Z","submitted_at":"2020-04-28T09:42:41Z","title":"Meta-Learning for Few-Shot Land Cover Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.13390","snapshot_observed_at":"2026-08-11T23:44:53.329943Z","title":"Meta-Learning for Few-Shot Land Cover Classification , journal =","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.329943Z"},"links":{"cited_paper":"/paper/2004.13390","citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:4b174118ea3488e0d89343ef6abc52ae080866f5aea3af51f0dae1db37bec172","observation_id":"0ec7a7f7-d492-416b-addb-6a6db513ac9f","resolution":{"observed_at":"2026-08-11T23:44:53.329943Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:44:53.731503Z","title":null,"venue":null,"work_id":"2230fe1b-8b0c-49d1-be7e-7a7608806778","year":null},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.335588Z"},"links":{"citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:a2ad9f56158d40dbb83db064c9b2bcfb3a4ad3e9187ee548761ec252fa53ae45","observation_id":"0b121eed-a053-4f9f-b21c-e7ee1268466a","resolution":{"observed_at":"2026-08-11T23:44:53.736361Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:44:53.715313Z","title":"Hughes and Marcel Salath","venue":null,"work_id":"122386df-136c-4aca-aa41-910398202f4f","year":2015},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.341931Z"},"links":{"citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:22ec6aa5275ff4146fa9983c7aa33eec798bd2f3e28687777775bf8ada05ca86","observation_id":"32e353ae-f252-4294-90da-98d747889c12","resolution":{"observed_at":"2026-08-11T23:44:53.720305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:44:53.697965Z","title":null,"venue":null,"work_id":"b9336228-ef8d-4b9f-b115-eb0a71692018","year":null},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.347238Z"},"links":{"citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:3bb10912d68a92d3d69c2d183fb7db75931b0fee3b508cf0fb5d271f16cf55f3","observation_id":"c8ee5f11-e78c-46cf-86a6-02be4521d5b4","resolution":{"observed_at":"2026-08-11T23:44:53.703347Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:44:53.679836Z","title":"2009 IEEE conference on computer vision and pattern recognition , pages =","venue":null,"work_id":"d48948dc-1378-4552-891c-5542a6c8b99e","year":2009},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.353019Z"},"links":{"citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:5182df86236694911f87ecc6ea4eb338bc35da87c66fe592ced7179598893086","observation_id":"d7b6cca4-b83e-4aa1-9cf7-7aac737380df","resolution":{"observed_at":"2026-08-11T23:44:53.686080Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:44:53.661120Z","title":"2009 , type =","venue":null,"work_id":"f785d285-a337-4166-85d7-68219b087be1","year":2009},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.357790Z"},"links":{"citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:7605f202fa5ace89a134efa43ad3d267c59c09ffb81c6df57a2d6eb7bb7ed9f2","observation_id":"05c29922-0810-4faf-a622-7fde8a441b2b","resolution":{"observed_at":"2026-08-11T23:44:53.666813Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-11T23:44:53.362691Z","title":"Microsoft","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.362691Z"},"links":{"cited_paper":"/paper/1405.0312","citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:c9f3279bb93951ded92d0765056b6051236a66143bae272c3e44726e21dba88f","observation_id":"6e46714d-c994-4cd4-9d5f-65cbd98fb221","resolution":{"observed_at":"2026-08-11T23:44:53.362691Z","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":"10.1186/1746-4811-9-38","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:44:53.465458Z","title":"An online database for plant image analysis software tools , journal =","venue":null,"work_id":"a5402e85-15d5-4d6e-986f-e5db9ccc5f47","year":2013},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.368094Z"},"links":{"citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:612844c45cdb26262a7b25d0c0caeee5ab9bfc1968698cf7362d4ff09c6b323c","observation_id":"707b853b-4c70-41a9-85f7-a9b63ef407de","resolution":{"observed_at":"2026-08-11T23:44:53.471863Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.00982","last_updated":"2020-02-21T15:15:33Z","snapshot_observed_at":"2026-08-12T19:54:45.676411Z","submitted_at":"2018-11-02T16:58:28Z","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.00982","snapshot_observed_at":"2026-08-11T23:44:53.374068Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.374068Z"},"links":{"cited_paper":"/paper/1811.00982","citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:2ee48261b3a378268b5bb529be7d9ffe6cf0150924e8fc90f6cb06935484ca10","observation_id":"eb401a73-6cad-4f5c-b9ec-1cff663c736c","resolution":{"observed_at":"2026-08-11T23:44:53.374068Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T23:44:53.379237Z","title":"Learning multiple layers of features from tiny images , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.379237Z"},"links":{"citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:4a55e1c9d7fe04798b1b5578777e0d807c8d0a993fffde67dc79a86bc341fc88","observation_id":"614285cb-96bf-4267-b0ad-2596edabcd3c","resolution":{"observed_at":"2026-08-11T23:44:53.379237Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.09960","last_updated":"2019-10-20T20:09:20Z","snapshot_observed_at":"2026-08-10T17:16:59.473676Z","submitted_at":"2019-01-28T19:37:07Z","title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.09960","snapshot_observed_at":"2026-08-11T23:44:53.384423Z","title":"CoRR , volume =","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.384423Z"},"links":{"cited_paper":"/paper/1901.09960","citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:22800a08129b69ff4a57ea9db4745576cf23ab999fd10965c68cfb291b7edc5c","observation_id":"7cc678e4-ffd8-4a8f-91f1-b7b2e1f48c4e","resolution":{"observed_at":"2026-08-11T23:44:53.384423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1702.08690","last_updated":"2017-06-06T11:51:03Z","snapshot_observed_at":"2026-07-06T05:31:42.551086Z","submitted_at":"2017-02-28T08:40:44Z","title":"Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning","version":2},"cited_work":{"arxiv_id":"1702.08690","doi":null,"metadata_source":"pith","pith_arxiv_id":"1702.08690","snapshot_observed_at":"2026-08-11T23:44:53.565145Z","title":"Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning","venue":"cs.CV","work_id":"7387bdb4-1ade-4a43-8d7b-650959ea089a","year":2017},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.390174Z"},"links":{"cited_paper":"/paper/1702.08690","citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:6cd7d9cc561f68fb7c7fab1afd36c7c1deb1e1228fa51ac87bf73ca18605d876","observation_id":"7e5eb6a4-4153-40fb-b0b5-238efefe04a5","resolution":{"observed_at":"2026-08-11T23:44:53.571060Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.05987","last_updated":"2019-06-11T13:13:46Z","snapshot_observed_at":"2026-08-06T12:40:13.289534Z","submitted_at":"2019-03-14T13:32:31Z","title":"To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.05987","snapshot_observed_at":"2026-08-11T23:44:53.395352Z","title":"Peters and Sebastian Ruder and Noah A","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.395352Z"},"links":{"cited_paper":"/paper/1903.05987","citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:565ae8f7c3f5408da0fe3e5f44c49149e0e38f24abd177108596d27a0bd86264","observation_id":"d4f456af-8efc-4a39-88fe-d229aec6eb5a","resolution":{"observed_at":"2026-08-11T23:44:53.395352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.10054","last_updated":"2022-02-21T09:03:34Z","snapshot_observed_at":"2026-08-11T01:24:45.524652Z","submitted_at":"2022-02-21T09:03:34Z","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.10054","snapshot_observed_at":"2026-08-11T23:44:53.400340Z","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution , publisher =","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.400340Z"},"links":{"cited_paper":"/paper/2202.10054","citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:7a421b4cf0be4919ba99e4dfc3d700a95998710208cbef11795cd54721aefc0f","observation_id":"505b3263-5b26-4641-9751-b5b1cb9bc497","resolution":{"observed_at":"2026-08-11T23:44:53.400340Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.04617","last_updated":"2021-10-25T21:16:56Z","snapshot_observed_at":"2026-08-06T00:26:44.558284Z","submitted_at":"2021-09-10T02:01:43Z","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","version":2},"cited_work":{"arxiv_id":"2109.04617","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.04617","snapshot_observed_at":"2026-08-11T23:44:53.524416Z","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","venue":"cs.LG","work_id":"1e106451-0be7-4517-b878-e5c651221958","year":2021},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.405714Z"},"links":{"cited_paper":"/paper/2109.04617","citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:6bbab709c69ba7f129b0c2f55ac15ca7cec53f98cea05dcb825891fcde85abd7","observation_id":"daa71cf9-f772-4379-b5e0-4cb8bd549d44","resolution":{"observed_at":"2026-08-11T23:44:53.531371Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2008.11687","last_updated":"2021-01-14T20:32:39Z","snapshot_observed_at":"2026-08-01T15:48:57.385214Z","submitted_at":"2020-08-26T17:23:40Z","title":"What is being transferred in transfer learning?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.11687","snapshot_observed_at":"2026-08-11T23:44:53.411664Z","title":"CoRR , volume =","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.411664Z"},"links":{"cited_paper":"/paper/2008.11687","citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:05dd88964ab7bef273deeb1ecbd259393ca99553c3033d8404a9e2de92f0f2c4","observation_id":"230ad801-34bc-47fc-bf27-2f99e8614178","resolution":{"observed_at":"2026-08-11T23:44:53.411664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.00414","last_updated":"2019-07-19T14:59:45Z","snapshot_observed_at":"2026-07-06T07:49:47.294073Z","submitted_at":"2019-05-01T17:57:26Z","title":"Similarity of Neural Network Representations Revisited","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.00414","snapshot_observed_at":"2026-08-11T23:44:53.416936Z","title":"Hinton , title =","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-11T23:44:53.416936Z"},"links":{"cited_paper":"/paper/1905.00414","citing_paper":"/paper/2608.09091"},"observation_digest":"sha256:0f7925778cdbb516ed0cdfe43666cd45b3d860f1ef103de216329097715c4453","observation_id":"7f6dfc14-3ef1-47a8-bac1-87de6b18e576","resolution":{"observed_at":"2026-08-11T23:44:53.416936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.09091","last_updated":"2026-08-10T03:42:54Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T20:18:56.383694Z","submitted_at":"2026-08-10T03:42:54Z","title":"TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset"},"reference_resolution":{"displayed":17,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":3,"verified_fuzzy":3},"total_outbound_references":17},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 0 inbound Pith citation observations for arXiv:2608.09091."}