{"as_of":"2026-08-21T13:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fc600eecb8df03bbcdc72eb9d0f165234d295db1e27f01c9abeb18b3be78153c","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T13:59:09.094315Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2607.26059/citation-record","integrity":"/paper/2607.26059/integrity","json":"/paper/2607.26059/citation-record.json","paper":"/paper/2607.26059"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T13:59:02.852614Z","title":"Loss of plasticity in continual deep reinforcement learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:02.852614Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:2ba1bb2b538802286febdf875bdd145d6d4d92a085d33868d48c4c6d735fdcc4","observation_id":"8f6acdc3-f647-4df5-9419-6e12040f2f94","resolution":{"observed_at":"2026-08-02T13:59:02.852614Z","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":"2026-08-02T13:59:02.999994Z","title":"Database-friendly random projections: J ohnson-- L indenstrauss with binary coins","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:02.999994Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:39dad98b5516a53febc8094747ea8b7d410589ca6b0e273f04fad39ac82510e3","observation_id":"d819f2f7-3da8-41a1-a10e-eed5581eeb87","resolution":{"observed_at":"2026-08-02T13:59:02.999994Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.13255","last_updated":"2020-12-22T07:42:30Z","snapshot_observed_at":"2026-08-18T15:17:24.628404Z","submitted_at":"2020-12-22T07:42:30Z","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.13255","snapshot_observed_at":"2026-08-02T13:59:03.104886Z","title":"Intrinsic dimensionality explains the effectiveness of language model fine-tuning","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:03.104886Z"},"links":{"cited_paper":"/paper/2012.13255","citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:17bd3bd734ca1323add93a73d93f02b8bfe55888ddaa62ab9bf955f9c6116bae","observation_id":"b31f9d26-ec54-4dfe-8363-e3cea7a3fc57","resolution":{"observed_at":"2026-08-02T13:59:03.104886Z","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":"2026-08-02T13:59:03.239734Z","title":"Unsupervised state representation learning in A tari","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:03.239734Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:ab31925d0e0b87a347e00565a3b642a2f4f48353805dd67d0c317a960d746044","observation_id":"ac239ff2-0078-4e0b-a5aa-f98518eb0e7b","resolution":{"observed_at":"2026-08-02T13:59:03.239734Z","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":"2026-08-02T13:59:03.372467Z","title":"SGD with large step sizes learns sparse features","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:03.372467Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:db06dc0684be60a8fcc05128a3090b46190a6131dfac2bf89918eecab0f753d0","observation_id":"882cf573-3468-4b80-b1a0-64036cad5a39","resolution":{"observed_at":"2026-08-02T13:59:03.372467Z","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":"2026-08-02T13:59:03.494383Z","title":"DiffuserCam : lensless single-exposure 3D imaging","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:03.494383Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:2d38516cc0c15fc7be20878473ee074096bb67a5cb1b08d39bc7324c82cb729d","observation_id":"a838838b-1b89-4bf7-83cd-95ab7806898b","resolution":{"observed_at":"2026-08-02T13:59:03.494383Z","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":"2026-08-02T13:59:03.670215Z","title":"Random projection in dimensionality reduction: applications to image and text data","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:03.670215Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:dcbdc0554411f32ce365495c20ba47513db97eff9c92769493957c1c8bb27c57","observation_id":"81c4b804-91e4-422b-b46e-43d1c802ba06","resolution":{"observed_at":"2026-08-02T13:59:03.670215Z","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":"2026-08-02T13:59:03.799841Z","title":"Robust uncertainty principles","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:03.799841Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:4faa09d65fa2db20de03440b4160b9207c391363040e766dcd6bbd701d0a0f8c","observation_id":"35b39ab9-b586-41be-b676-bddbc51ba49c","resolution":{"observed_at":"2026-08-02T13:59:03.799841Z","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":"2026-08-02T13:59:03.902646Z","title":"Reinforcement learning with convolutional reservoir computing","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:03.902646Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:85997f7890384aa98d233e898b34611d7ee23a280f5be6de25d56a349243f1ea","observation_id":"8f57858f-8466-4663-911a-3162eca65cd9","resolution":{"observed_at":"2026-08-02T13:59:03.902646Z","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":"2026-08-02T13:59:04.062196Z","title":"What makes freezing layers effective? arXiv preprint, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:04.062196Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:20eecbfed6448f020f31fe33dd3810bd1cc26bdaf18e601588c0d6b8a9d1e13a","observation_id":"027dbc31-accd-4ebb-ba98-823d1ba3d605","resolution":{"observed_at":"2026-08-02T13:59:04.062196Z","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":"2026-08-02T13:59:04.185856Z","title":"Playing A tari with six neurons","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:04.185856Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:89df2da3cf728c8d478765a05e855f140b4eeba7cae6838f46264e9f44f6494f","observation_id":"d7054120-c05a-47c5-94ea-f8f170e2c51b","resolution":{"observed_at":"2026-08-02T13:59:04.185856Z","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":"2026-08-02T13:59:04.330386Z","title":"An elementary proof of a theorem of J ohnson and L indenstrauss","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:04.330386Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:0c0b23f4ec28baf4372075af0e63796ab06bfe27f98dac61e53c328029482700","observation_id":"020fbfe3-3cff-468f-87e8-a7e7c496abea","resolution":{"observed_at":"2026-08-02T13:59:04.330386Z","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":"2026-08-02T13:59:04.388503Z","title":"The interplay between sparsity and training in deep reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:04.388503Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:1ca0d4c85acd28aa5ba328a37029153ad8b89fd7a965efca0a5a7b4399963a32","observation_id":"bd7efaa2-3a2e-4d36-b472-33bf2d43c484","resolution":{"observed_at":"2026-08-02T13:59:04.388503Z","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":"2026-08-02T13:59:04.553125Z","title":"Loss of plasticity in deep continual learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:04.553125Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:856294edf2459c9ebeb70075964130226c2a0439d49d3e608449672b40ab3ba5","observation_id":"eb479d54-cca2-48f5-87a0-6eba45f29353","resolution":{"observed_at":"2026-08-02T13:59:04.553125Z","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":"2026-08-02T13:59:04.671635Z","title":"Compressed sensing","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:04.671635Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:73711a8f5916c78c847630357c66f13ecb74e996bb8d527530efeeb9232079f8","observation_id":"59c5a0be-eaf0-4040-bba4-f3aa29437020","resolution":{"observed_at":"2026-08-02T13:59:04.671635Z","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":"2026-08-02T13:59:04.764764Z","title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:04.764764Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:73dfed593b77f3eb3f64eca1a08f5a13810fa4b303049971f587f6d33be96a8e","observation_id":"ae776114-7f85-41bd-bea3-941f1abb0a48","resolution":{"observed_at":"2026-08-02T13:59:04.764764Z","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":"2026-08-02T13:59:04.887703Z","title":"Why random pruning is all we need to start sparse","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:04.887703Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:0890d538932e6d4a6ddb8f07f77db484c7d7e67099a49fc83893af4ea98e03eb","observation_id":"8dd0b217-1576-499d-8780-e247ae5326b1","resolution":{"observed_at":"2026-08-02T13:59:04.887703Z","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":"2026-08-02T13:59:05.012960Z","title":"Weight agnostic neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:05.012960Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:943724ac0d0109a6ce8c5933507884c71e645d2654df7d54a0488e760000c565","observation_id":"f7e1ac90-f830-4e24-9805-179ad3778421","resolution":{"observed_at":"2026-08-02T13:59:05.012960Z","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":"2026-08-02T13:59:05.127044Z","title":"Implicit regularization in matrix factorization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:05.127044Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:2f1c957762c4e624b2410ae407ffb7fd9e9f24953002fff8e870cb4151f018af","observation_id":"dad5906b-aa9f-42d5-8753-c07da7aa4653","resolution":{"observed_at":"2026-08-02T13:59:05.127044Z","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":"2026-08-02T13:59:05.254279Z","title":"Learning both weights and connections for efficient neural networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:05.254279Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:f34763c75b0f9cf020fda0bff375f3005c7c2f97a2743508976e3efffca81158","observation_id":"ab98531e-0cd4-48a9-abe8-b0e6dd9c2249","resolution":{"observed_at":"2026-08-02T13:59:05.254279Z","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":"2026-08-02T13:59:05.373285Z","title":"Delving deep into rectifiers","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:05.373285Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:59a5c29d5cc1fcb31eaaed7760db9f9371847df577f241d8247f7e8775899a66","observation_id":"b9aca7d9-e2a7-4769-b138-ee97173186e5","resolution":{"observed_at":"2026-08-02T13:59:05.373285Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-20T11:47:17.477107Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-02T13:59:05.498028Z","title":"LoRA : Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:05.498028Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:82aacc745b03e0b529b5dfcd6092097ea48e352b8ec59fbc556c598530aaaae5","observation_id":"58185850-d8da-4a16-9aaa-edff84709e1c","resolution":{"observed_at":"2026-08-02T13:59:05.498028Z","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":"2026-08-02T13:59:05.620817Z","title":"The ``echo state'' approach to analysing and training recurrent neural networks","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:05.620817Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:a7c9ec12734b76d5d16655f28ee498ae319326218d76482f51081da573601535","observation_id":"cf2484ed-9851-4a92-8866-934095cb117c","resolution":{"observed_at":"2026-08-02T13:59:05.620817Z","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":"2026-08-02T13:59:05.748970Z","title":"Extensions of L ipschitz mappings into a H ilbert space","venue":null,"work_id":null,"year":1984},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:05.748970Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:fab2d69c56dd1b3fe6ac3b80434f32fe3f7d732701798c285a4d579adf328d22","observation_id":"cc858e3c-7bf3-4d21-b032-722a3fe6d11a","resolution":{"observed_at":"2026-08-02T13:59:05.748970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.14498","last_updated":"2021-10-25T03:10:12Z","snapshot_observed_at":"2026-08-19T03:25:15.143800Z","submitted_at":"2020-10-27T17:55:16Z","title":"Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.14498","snapshot_observed_at":"2026-08-02T13:59:05.867960Z","title":"Implicit under-parameterization inhibits data-efficient deep reinforcement learning","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:05.867960Z"},"links":{"cited_paper":"/paper/2010.14498","citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:2f27ab5ee6f0dc5f0501f752a761576499e81d26cbfb20c65d15d54996977fc5","observation_id":"67b27c5e-a6e0-488e-9efd-9d56784b133d","resolution":{"observed_at":"2026-08-02T13:59:05.867960Z","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":"2026-08-02T13:59:05.985951Z","title":"Optimal brain damage","venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:05.985951Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:819c8e1c267cdb3cea5e8d076c32ab7122d075b4c249a88d4d73ce70cbb5c09b","observation_id":"5e93e0ba-8305-4523-98ee-c30ecbb2d383","resolution":{"observed_at":"2026-08-02T13:59:05.985951Z","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":"2026-08-02T13:59:06.112917Z","title":"Measuring the intrinsic dimension of objective landscapes","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:06.112917Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:ed61a3671681a06249ae452564218bd68be70fcfccf53d3df73380783cb95f2c","observation_id":"db9a9120-ea48-46da-8627-a8b6ea690895","resolution":{"observed_at":"2026-08-02T13:59:06.112917Z","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":"2026-08-02T13:59:06.250526Z","title":"Understanding plasticity in neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:06.250526Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:33d5465d73370b13235c5f316a8f40c75401d5705a56d4f001e9d07762dddb23","observation_id":"d48f23b4-6510-4a54-b545-7b339e95cfcf","resolution":{"observed_at":"2026-08-02T13:59:06.250526Z","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":"2026-08-02T13:59:06.418912Z","title":"Sparsity for free: Overcoming the limitations of dense scaling in deep reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:06.418912Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:864d31f5a82f262315397a2ef7588bc0c84053138efd3e1fc0895648e670c4aa","observation_id":"07dc4c47-b6e7-4699-90bd-f7cdfafb005c","resolution":{"observed_at":"2026-08-02T13:59:06.418912Z","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":"2026-08-02T13:59:06.550782Z","title":"Real-time computing without stable states","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:06.550782Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:63421f2431fc9b9474ecea3f496322b4afc26e2aacca9262fe6a25cbcd9f0ec0","observation_id":"94b63104-2126-4241-9be7-2800a494973f","resolution":{"observed_at":"2026-08-02T13:59:06.550782Z","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":"2026-08-02T13:59:06.652193Z","title":"Revisiting the A rcade L earning E nvironment: Evaluation protocols and open problems for general agents","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:06.652193Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:3bdeef13b88f91f512de25168aa14c505d8f65cf4bc7f5f29c8f2726c4df14b0","observation_id":"425f15e3-1671-46fe-88f0-ec252986d16d","resolution":{"observed_at":"2026-08-02T13:59:06.652193Z","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":"2026-08-02T13:59:06.820550Z","title":"Proving the lottery ticket hypothesis: Pruning is all you need","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:06.820550Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:38b2d58056917c0cce2e4da9f571e978168ab20e4326955df206ac874c192d53","observation_id":"e734dbe8-ed00-422f-8218-85f30f0a08b8","resolution":{"observed_at":"2026-08-02T13:59:06.820550Z","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":"2026-08-02T13:59:07.012249Z","title":"Human-level control through deep reinforcement learning","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:07.012249Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:3b4ef25497d1f4ca5057f910be0e27f6ed5c92eb8992f7f16e209611c5a615e9","observation_id":"373c4749-d161-4154-a9c7-82d32c8a9608","resolution":{"observed_at":"2026-08-02T13:59:07.012249Z","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":"2026-08-02T13:59:07.197845Z","title":"No representation, no trust: Connecting representation, collapse, and trust issues in PPO","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:07.197845Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:bad1deec5c73b83de823dd6103e61d58d09779b8a18b8e5d0152f5aaec4d63ca","observation_id":"da3e398f-dffc-48b2-811f-968f9ab2b6a2","resolution":{"observed_at":"2026-08-02T13:59:07.197845Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.06440","last_updated":"2017-06-08T19:53:26Z","snapshot_observed_at":"2026-08-14T21:29:36.502364Z","submitted_at":"2016-11-19T22:48:30Z","title":"Pruning Convolutional Neural Networks for Resource Efficient Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.06440","snapshot_observed_at":"2026-08-02T13:59:07.412184Z","title":"Pruning convolutional neural networks for resource efficient inference","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:07.412184Z"},"links":{"cited_paper":"/paper/1611.06440","citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:d3467dd2367b83e3743d5a90ed8027303460692e997a11f27ad57f1a4aece00e","observation_id":"950efbcd-a9ef-453c-9f01-1e2d707b3cfa","resolution":{"observed_at":"2026-08-02T13:59:07.412184Z","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":"2026-08-02T13:59:07.625394Z","title":"The primacy bias in deep reinforcement learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:07.625394Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:519c28ebd4b19d1ac049e01279878eb279accce92baffcf2c607333b58d12039","observation_id":"29f2342c-c47e-4a17-b673-275e7fd0aec1","resolution":{"observed_at":"2026-08-02T13:59:07.625394Z","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":"2026-08-02T13:59:07.801430Z","title":"In value-based deep reinforcement learning, a pruned network is a good network","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:07.801430Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:a026f7227079b308b0fdd6bab1a2fbffc4250202a958e5b2f916f05718487599","observation_id":"0176804d-3469-4281-83df-fba9ecca5131","resolution":{"observed_at":"2026-08-02T13:59:07.801430Z","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":"2026-08-02T13:59:07.955983Z","title":"Sample factory: Egocentric 3d control from pixels at 100000 FPS with asynchronous reinforcement learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:07.955983Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:16828992960955e54d3b6764e5df1e733940a6bc8e057b0c5beac3a306fccd99","observation_id":"19071648-18b4-49e5-8eb3-d7441b61c55b","resolution":{"observed_at":"2026-08-02T13:59:07.955983Z","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":"2026-08-02T13:59:08.114491Z","title":"Stable- B aselines3: Reliable reinforcement learning implementations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:08.114491Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:29b0179d04c0b4aa3639450a702292d2bea3287e7040ffc86d00174eadf351f1","observation_id":"959f82ab-dce5-4e6b-8fd3-cc306a9bf982","resolution":{"observed_at":"2026-08-02T13:59:08.114491Z","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":"2026-08-02T13:59:08.287207Z","title":"Random features for large-scale kernel machines","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:08.287207Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:10f41950dd335ec260e752f4436508ca70306f98f5cda49b860d276e226bf5d2","observation_id":"762f5e7f-4e45-403e-87df-66c63223864b","resolution":{"observed_at":"2026-08-02T13:59:08.287207Z","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":"2026-08-02T13:59:08.446510Z","title":"What's hidden in a randomly weighted neural network? In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:08.446510Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:1f7802891ef63eab8b5df99e7e88521053afe15d3445e379e812bec090191e34","observation_id":"2169e80b-eccb-4289-8070-f120139b5db6","resolution":{"observed_at":"2026-08-02T13:59:08.446510Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-08-20T07:04:06.309989Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-02T13:59:08.592302Z","title":"Proximal policy optimization algorithms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:08.592302Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:9454c9e6c5582a6d686178b8e8bb8070ae87a73c8ac9a9d90f655511260508e5","observation_id":"5be55ddf-b303-432a-8856-49fdf9a61504","resolution":{"observed_at":"2026-08-02T13:59:08.592302Z","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":"2026-08-02T13:59:08.738862Z","title":"Dormant neuron phenomenon in deep reinforcement learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:08.738862Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:cb86111a864f0225f28771ec004b5b3157af3ba51f5292c6382768e009126f99","observation_id":"057a986b-221c-4253-995f-b792f57829d3","resolution":{"observed_at":"2026-08-02T13:59:08.738862Z","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":"2026-08-02T13:59:08.891131Z","title":"Regression shrinkage and selection via the lasso","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:08.891131Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:3bbb004cbc579e572098da1ec62bff2fe98af78fbc336b71fc4eddd2df11b6f1","observation_id":"975deeea-f45a-4d5c-9e40-0be6ea10b5c7","resolution":{"observed_at":"2026-08-02T13:59:08.891131Z","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":"2026-08-02T13:59:09.009649Z","title":"Kernel and rich regimes in overparameterized models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:09.009649Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:3e50f0a82e6eec1e50afab757aebf4863538f066181f998751c2e093e924f9c0","observation_id":"f960f840-e1a0-4316-8a82-c52a34ea7e78","resolution":{"observed_at":"2026-08-02T13:59:09.009649Z","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":"2026-08-02T13:59:09.094315Z","title":"Pre-trained visual features for visual RL","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-02T13:59:09.094315Z"},"links":{"citing_paper":"/paper/2607.26059"},"observation_digest":"sha256:82925496f99e2d449eab1c36c2f1211e7e1d6c2dde31204c1c5c9c8360ea5a30","observation_id":"6fd306d4-8139-4aa1-9c93-928667ebd83b","resolution":{"observed_at":"2026-08-02T13:59:09.094315Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.26059","last_updated":"2026-05-15T00:01:05Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-20T18:01:05.782534Z","submitted_at":"2026-05-15T00:01:05Z","title":"Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":46,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":46},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2607.26059."}