{"as_of":"2026-08-07T16:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8ead1449b6b333bcceea5da6f373a88466666a2714fb30aabc026e1f5ab084f3","coverage":[{"denominator":214,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:32:54.306268Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.10446/citation-record","integrity":"/paper/2507.10446/integrity","json":"/paper/2507.10446/citation-record.json","paper":"/paper/2507.10446"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:32:53.980817Z","title":"Structural interplay between germline interactions and adaptive recognition deter- mines the bandwidth of tcr-peptide-mhc cross-reactivity","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:53.980817Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:b2a67b46d62f1b5c7ef80290a64f2a655cdb51073e506584e8ad490ef3094f17","observation_id":"383ae0cd-83ed-4842-a36e-4433b5ac2b9e","resolution":{"observed_at":"2026-08-06T19:32:53.980817Z","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":"2026-08-06T19:32:53.984600Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:53.984600Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:90a681ee3cd85a8989df772331b472e04326f5672485e25c61504f1eca7dd2ee","observation_id":"e7ae2aae-d598-43da-8e7b-96344d34bc50","resolution":{"observed_at":"2026-08-06T19:32:53.984600Z","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":"2026-08-06T19:32:53.988363Z","title":"Efficient 3d deep learning model for medical image semantic segmentation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:53.988363Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:dfde4b590f750bd2b457de4129318ede6ada9d976b70fff8669fc56c51fac13c","observation_id":"483410e3-ae9a-4643-8793-2cab10c96aaf","resolution":{"observed_at":"2026-08-06T19:32:53.988363Z","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":"2026-08-06T19:32:53.991935Z","title":"Flamingo: a visual language model for few-shot learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:53.991935Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:3cec47f88084165c18dedaf198a05ab0a318dfd9d4233464d79f148b4b582edc","observation_id":"13ecbd88-b76b-46aa-ab58-abd572a840ab","resolution":{"observed_at":"2026-08-06T19:32:53.991935Z","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":"2026-08-06T19:32:53.995234Z","title":"Deep speech 2: End-to-end speech recognition in english and mandarin","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:53.995234Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:846e77cdc3fe56b7708a22babc61e38af76edfabe42ca68e29d5e2809896fe26","observation_id":"a22cbe5c-8261-4433-8751-79cbb1387918","resolution":{"observed_at":"2026-08-06T19:32:53.995234Z","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":"2026-08-06T19:32:53.998808Z","title":"Hoffman, David Pfau, Tom Schaul, and Nando de Freitas","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:53.998808Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:5d9a64bd9e73a33081afaf211e09ba471ae054578b921d8a7c0d4fc6d0605309","observation_id":"cd05a772-371e-4f38-b6ec-7d728ebc6e14","resolution":{"observed_at":"2026-08-06T19:32:53.998808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.11967","last_updated":"2020-04-15T16:41:01Z","snapshot_observed_at":"2026-08-03T21:02:56.718899Z","submitted_at":"2020-04-15T16:41:01Z","title":"Defining Benchmarks for Continual Few-Shot Learning","version":1},"cited_work":{"arxiv_id":"2004.11967","doi":null,"metadata_source":"pith","pith_arxiv_id":"2004.11967","snapshot_observed_at":"2026-08-06T19:32:54.978034Z","title":"Defining Benchmarks for Continual Few-Shot Learning","venue":"cs.CV","work_id":"58d2cc14-673d-4e22-b117-f77edd55e1bf","year":2020},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.003582Z"},"links":{"cited_paper":"/paper/2004.11967","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:94e360ce20571dfc0b00312b7f1a39b15115ef54f7c7def4ed3d9cec3abf5877","observation_id":"bb6ab776-4eda-4dd6-b0ea-1d09661d3a68","resolution":{"observed_at":"2026-08-06T19:32:54.981320Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:32:54.007329Z","title":"On the texture bias for few-shot cnn segmentation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.007329Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:d38388ac962116eff0d49269ef01dd807ec384e366b9f4560959abc9ab09abd6","observation_id":"a8a078e3-9e9e-48fb-9704-784118908c41","resolution":{"observed_at":"2026-08-06T19:32:54.007329Z","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":"2026-08-06T19:32:54.011692Z","title":"Hyperfields: Towards zero-shot generation of nerfs from text, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.011692Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:64383b0ee3ea50e049f24401c2f18a5958f76e10a918616a0d5594f9cd9f554e","observation_id":"a4d4b6ab-c42d-4664-8444-b789865ccbfc","resolution":{"observed_at":"2026-08-06T19:32:54.011692Z","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":"2026-08-06T19:32:54.014537Z","title":"Hypernetwork designs for improved classification and robust meta-learning, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.014537Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:a4358f480ae96c3d88bde7f06ffb14fe42997ee383dae7607879eee34e614bc1","observation_id":"12c4c17f-9a34-4ac4-842e-a925d5bb7edc","resolution":{"observed_at":"2026-08-06T19:32:54.014537Z","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":"2026-08-06T19:32:54.018174Z","title":"Online meta-learning via learning with layer-distributed memory","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.018174Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:48ddb4dcb1085083c9a5027a9a2d8604446277b504aa963019856444eb162af5","observation_id":"39fffa8a-ee8e-4ed6-b752-aa369fcc7076","resolution":{"observed_at":"2026-08-06T19:32:54.018174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2008.00247","last_updated":"2020-08-01T11:23:37Z","snapshot_observed_at":"2026-08-05T05:05:26.314543Z","submitted_at":"2020-08-01T11:23:37Z","title":"Meta-DRN: Meta-Learning for 1-Shot Image Segmentation","version":1},"cited_work":{"arxiv_id":"2008.00247","doi":null,"metadata_source":"pith","pith_arxiv_id":"2008.00247","snapshot_observed_at":"2026-08-06T19:32:54.965331Z","title":"Meta-DRN: Meta-Learning for 1-Shot Image Segmentation","venue":"cs.CV","work_id":"9af341ff-df5f-4281-ad30-c6e85d1a8ce1","year":2020},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.021584Z"},"links":{"cited_paper":"/paper/2008.00247","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:5f8902c95a9e6409b787ce7e1e50c65392514a6d6a1fb485f8c1bae3f57acdfa","observation_id":"b93dc50e-3576-4080-b970-b8579df9fc33","resolution":{"observed_at":"2026-08-06T19:32:54.969211Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:32:54.024473Z","title":"Pixelnet: Representation of the pixels, by the pixels, and for the pixels, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.024473Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:4c6babb7d5e57f091e654475b0ea47a4861186fbc6d1864f80fc0fa2833f5c13","observation_id":"0d429219-fc6e-4e4b-8c78-f075852cbfa2","resolution":{"observed_at":"2026-08-06T19:32:54.024473Z","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":"2026-08-06T19:32:54.027862Z","title":"Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.027862Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:34dbe3b31ec8c4ae1ed0311e2e61cd16d77f4efa4ba16dfff9c2eb459e0940c7","observation_id":"bdc13a38-7d6b-44c9-ae3a-ed7ff6e532d0","resolution":{"observed_at":"2026-08-06T19:32:54.027862Z","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":"2026-08-06T19:32:54.030987Z","title":"Mip- nerf 360: Unbounded anti-aliased neural radiance fields","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.030987Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:7fcbd107c2ae29559c61800859e446fe5de1ad3df6abccde0c00af1405b605eb","observation_id":"e4bd1ca5-fe25-454a-8750-e668fb15e268","resolution":{"observed_at":"2026-08-06T19:32:54.030987Z","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":"2026-08-06T19:32:54.033641Z","title":"Rae, Simon Osindero, and Timothy P","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.033641Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:12ed18242425a9ff39f020bf29839957616ce2f7bc37089f5704de8d4c8d71f5","observation_id":"03fb316c-c141-42d9-99ad-bd28dd07ed91","resolution":{"observed_at":"2026-08-06T19:32:54.033641Z","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":"2026-08-06T19:32:54.037143Z","title":"Stanley, Jeff Clune, and Nick Cheney","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.037143Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:308a32c4908487dbfb377c6e706c669edd169c0ea84a4a7326fb07b63d67e4bb","observation_id":"835f6a91-a05f-4eda-bd8f-5f77f8fd6022","resolution":{"observed_at":"2026-08-06T19:32:54.037143Z","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":"2026-08-06T19:32:54.040329Z","title":"On the optimization of a synaptic learning rule","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.040329Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:ad7ef7847f54620db21d0589f67a79b1ac32c45ff8fb999952c35098f0622277","observation_id":"c8701b44-fb18-4153-8c1c-bc704526caed","resolution":{"observed_at":"2026-08-06T19:32:54.040329Z","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":"2026-08-06T19:32:54.043189Z","title":"Practical recommendations for gradient-based training of deep architectures","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.043189Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:b774dcd46ff23a53e7430c03fcbdc5564f45d0973e0037a3fe2d3c99ca377110","observation_id":"6cabd2dd-1df6-464b-8431-bfdfc5fbe8b5","resolution":{"observed_at":"2026-08-06T19:32:54.043189Z","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":"2026-08-06T19:32:54.046123Z","title":"Henriques, Philip H","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.046123Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:603a9dde62b652225a7709a4046d561db7952abd026ab3ec74013e1c5031b5ce","observation_id":"dd8b052e-81b0-4eed-b966-faf9c4502a16","resolution":{"observed_at":"2026-08-06T19:32:54.046123Z","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":"2026-08-06T19:32:54.050337Z","title":"Stylegan knows normal, depth, albedo, and more","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.050337Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:ff3d9eefe6bce4b9a26c50b495f67ec62a9c8bd41f58cea3a0bcc154a5886b03","observation_id":"c3baca04-9b26-41cb-873c-8e1948175949","resolution":{"observed_at":"2026-08-06T19:32:54.050337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.05856","last_updated":"2021-01-20T23:58:29Z","snapshot_observed_at":"2026-08-03T21:52:41.720546Z","submitted_at":"2020-03-12T15:47:16Z","title":"Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.05856","snapshot_observed_at":"2026-08-06T19:32:54.054489Z","title":"Online fast adaptation and knowledge accumulation: a new approach to continual learning","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.054489Z"},"links":{"cited_paper":"/paper/2003.05856","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:96814449ad36cbce072761a0b9f6c0a310edbef11871df599dce1126bc7044f3","observation_id":"686a7392-cb33-4233-9f14-268715174247","resolution":{"observed_at":"2026-08-06T19:32:54.054489Z","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":"2026-08-06T19:32:54.058440Z","title":"Unsupervised learning of visual features by contrasting cluster assignments.Advances in neural information processing systems, 33:9912–9924, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.058440Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:999fe7bbbb8ff9c7a9627c37946b9956f082e9d773adeb6c03ebd8a885879a71","observation_id":"c18dc03f-07be-488d-8e67-7a637be19bd0","resolution":{"observed_at":"2026-08-06T19:32:54.058440Z","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":"2026-08-06T19:32:54.062039Z","title":"Deep local shapes: Learning local sdf priors for detailed 3d reconstruction","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.062039Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:2b495ba52abc771e81455a14ca470bdef128c80fbe595ea6ab52ce92c9bd9d4e","observation_id":"58440240-c4f8-41be-8db0-56bf04f5c961","resolution":{"observed_at":"2026-08-06T19:32:54.062039Z","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":"2026-08-06T19:32:54.064528Z","title":"Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, Jianxiong Xiao, Li Yi, and Fisher Yu","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.064528Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:d84b24e96d44f0ae6f01c3c34860eaee02763b2f9d732db5e4616f715867433b","observation_id":"2215bba3-f148-49f5-ae2c-4b768c78fa10","resolution":{"observed_at":"2026-08-06T19:32:54.064528Z","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":"2026-08-06T19:32:54.067926Z","title":"Principled weight initialization for hyper- networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.067926Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:651bc116bb0a3a130983b694ecc7e1c9f1b6380e66f607903d6188095f44e7e6","observation_id":"977f851e-e55b-4285-895a-9ccacd2e6206","resolution":{"observed_at":"2026-08-06T19:32:54.067926Z","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":"2026-08-06T19:32:54.074860Z","title":"Tensorf: Tensorial radiance fields, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.074860Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:9c6169dcd17e84ab970253d7fe42bfcbdd1c6b4af0c9d428a06f3fe900b118ad","observation_id":"40effbd2-2bd5-4e5e-9713-a7087eb19be4","resolution":{"observed_at":"2026-08-06T19:32:54.074860Z","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":"2026-08-06T19:32:54.078165Z","title":"Fantasia3d: Disentangling geometry and appearance for high-quality text-to-3d content creation, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.078165Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:6663ec4493acf88542781dfceb33d1f0b46544514f3f7cc8ee9e24bc36844ced","observation_id":"0b643acb-0a72-421f-9c4c-2eed3ab9d361","resolution":{"observed_at":"2026-08-06T19:32:54.078165Z","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":"2026-08-06T19:32:54.081285Z","title":"A simple frame- work for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.081285Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:6ff83e8237e8f742cf0c87b3265b73642c1b0d2b1dbafd9c83143e7b8f5a8a70","observation_id":"c9833fa3-2cd0-4cde-98b7-29fb98440153","resolution":{"observed_at":"2026-08-06T19:32:54.081285Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.04232","last_updated":"2020-01-12T16:25:06Z","snapshot_observed_at":"2026-08-07T01:22:24.475726Z","submitted_at":"2019-04-08T17:59:07Z","title":"A Closer Look at Few-shot Classification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.04232","snapshot_observed_at":"2026-08-06T19:32:54.083733Z","title":"A closer look at few-shot classification","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.083733Z"},"links":{"cited_paper":"/paper/1904.04232","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:1a471aa944369744cde7729438e9b9188256f70549c7be1b94d3dcddb19a6959","observation_id":"164c5c02-c726-41b0-af46-7926f6b64ba0","resolution":{"observed_at":"2026-08-06T19:32:54.083733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.04297","last_updated":"2020-03-09T17:56:49Z","snapshot_observed_at":"2026-07-06T09:03:25.467987Z","submitted_at":"2020-03-09T17:56:49Z","title":"Improved Baselines with Momentum Contrastive Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.04297","snapshot_observed_at":"2026-08-06T19:32:54.087361Z","title":"Improved baselines with momen- tum contrastive learning","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.087361Z"},"links":{"cited_paper":"/paper/2003.04297","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:55d65680ca9ba22511f69d80e2ef5cb9050cd738b3d14fce08600b6a4b9136e3","observation_id":"0e6e1210-da33-4b80-b362-19abeaacd943","resolution":{"observed_at":"2026-08-06T19:32:54.087361Z","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":"2026-08-06T19:32:54.090911Z","title":"Dynamic convolution: Attention over convolution kernels","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.090911Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:56caa1fbb4eaac7417279595978adc2ebba8c3f9c283093383b8834756da5da7","observation_id":"6037936d-406a-419c-b3cd-b43272c30288","resolution":{"observed_at":"2026-08-06T19:32:54.090911Z","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":"2026-08-06T19:32:54.093733Z","title":"Stylizing 3d scene via implicit representation and hypernetwork, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.093733Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:f94049247520f31b0ff40b6f4e3469f9a687faf944278aed5921adf69f56b84e","observation_id":"685a6cf3-4df1-4f01-bb14-ff1c93f360ff","resolution":{"observed_at":"2026-08-06T19:32:54.093733Z","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":"2026-08-06T19:32:54.096886Z","title":"Chemberta: Large-scale self-supervised pretraining for molecular property prediction, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.096886Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:c6422296a1cf7fa60a831099f018ed77c1e4b55b935f4cccd3a50023c213ad5d","observation_id":"b498d108-3a93-487a-b5be-ba26c04cacb2","resolution":{"observed_at":"2026-08-06T19:32:54.096886Z","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":"2026-08-06T19:32:54.099294Z","title":"3d u-net: learning dense volumetric segmentation from sparse annotation","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.099294Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:76f4d0f5146a8a7c1f4d3bdd3107bc28381057e9a294247e191922bbd070341c","observation_id":"00d62418-c2cb-4e94-8aae-791ca3f126a7","resolution":{"observed_at":"2026-08-06T19:32:54.099294Z","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":"2026-08-06T19:32:54.101674Z","title":"T-cell antigen receptor genes and t-cell recognition","venue":null,"work_id":null,"year":1988},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.101674Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:499387f22e15be9b11575c1b93a2db25bebf25d386185b5efa4112abb14d9e9a","observation_id":"8fa18a7b-e945-401e-8ad8-627c17c1c914","resolution":{"observed_at":"2026-08-06T19:32:54.101674Z","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":"2026-08-06T19:32:54.103926Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.103926Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:5d86b6556405578c9ad48d92d992a734cda4ef2d66d75a2ddf0d88af32ce107f","observation_id":"d8c75c46-d71a-4c18-93cf-e3471eec5669","resolution":{"observed_at":"2026-08-06T19:32:54.103926Z","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":"2026-08-06T19:32:54.106325Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.106325Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:4858b95d646d44850ae58b2b68798b9fd1110d52e6cd50ab20e0cd9bfb852a4d","observation_id":"c2cd2bda-88d7-42a8-909e-92fe849e8d0e","resolution":{"observed_at":"2026-08-06T19:32:54.106325Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-07-30T09:12:38.100527Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-06T19:32:54.108889Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding.arXiv preprint arXiv:1810.04805, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.108889Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:eb480da7284e8ac9f51f52ae400df5a2e99fe0ac9dc2d398ce9a507100490e46","observation_id":"81caf0a5-f4c8-4dea-8ebd-8ad84555219f","resolution":{"observed_at":"2026-08-06T19:32:54.108889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.04552","last_updated":"2017-11-29T14:51:40Z","snapshot_observed_at":"2026-07-06T05:55:22.966528Z","submitted_at":"2017-08-15T15:21:53Z","title":"Improved Regularization of Convolutional Neural Networks with Cutout","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.04552","snapshot_observed_at":"2026-08-06T19:32:54.112455Z","title":"Improved regularization of convolutional neural networks with cutout","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.112455Z"},"links":{"cited_paper":"/paper/1708.04552","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:544671dad2e8a0280f487f3e799aef005d3249da659f15cefa9a92ccb81574d3","observation_id":"eaecd39c-280a-4e7b-91ef-cea63b2eb9f7","resolution":{"observed_at":"2026-08-06T19:32:54.112455Z","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":"2026-08-06T19:32:54.116146Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.116146Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:37039ba3099c16f5dcf1045b5b43ee8d06880f7d91284925cb469312672aa727","observation_id":"7e6aa4fe-a18c-4afd-bb20-9dafeeee3ad9","resolution":{"observed_at":"2026-08-06T19:32:54.116146Z","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":"2026-08-06T19:32:54.119319Z","title":"Unsupervised visual representation learning by context prediction","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.119319Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:4abeeca59e240f30904ca772a40f6b8b01966bb708330ffc2388a8d27acb4289","observation_id":"971311d1-fa17-48f2-8423-e7b9aa1c0cde","resolution":{"observed_at":"2026-08-06T19:32:54.119319Z","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":"2026-08-06T19:32:54.122322Z","title":"Machine learning methods for small data challenges in molecular science","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.122322Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:d20a0fea74f72556e3a2ecdc838ed51799c3b08237cd8d203b69c266972d4a22","observation_id":"0d48261f-54b6-4411-bf8d-671f33225963","resolution":{"observed_at":"2026-08-06T19:32:54.122322Z","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":"2026-08-06T19:32:54.125388Z","title":"Hyperdiffu- sion: Generating implicit neural fields with weight-space diffusion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.125388Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:0fce1a74ab5cd42cc21166a56bc38bf27bcad02200f4caed2eae0180daf9594b","observation_id":"5695ead0-d0b7-4054-97b5-c67c08b48822","resolution":{"observed_at":"2026-08-06T19:32:54.125388Z","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":"2026-08-06T19:32:54.129137Z","title":"Kiloneus: A versatile neural implicit surface representation for real-time rendering, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.129137Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:0d6070f456bb4f39956e80fb9da5b17efee6144495a2ffb8c901f6a2def8aaf9","observation_id":"2605aa44-6830-43c2-b407-a9fc59af0714","resolution":{"observed_at":"2026-08-06T19:32:54.129137Z","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":"2026-08-06T19:32:54.132150Z","title":"Model-agnostic meta-learning for fast adaptation of deep networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.132150Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:c7f918e0c76da014aab0480d5e172e0a6e390dd61adca0fa331383b5f94a5974","observation_id":"31901585-b223-4d70-8c62-0219a2da2a86","resolution":{"observed_at":"2026-08-06T19:32:54.132150Z","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":"2026-08-06T19:32:54.135968Z","title":"Kakade, and Sergey Levine","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.135968Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:625ab96d2107c809e66bdae261f0753ae4165ab5fe6e907ee1ffd5f8ba38939a","observation_id":"6b6e89cb-5773-4220-9d42-cd030aace000","resolution":{"observed_at":"2026-08-06T19:32:54.135968Z","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":"2026-08-06T19:32:54.139737Z","title":"Nerf: Neural radiance field in 3d vision, a comprehensive review, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.139737Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:00de25f3d89b00dcf76d1f8d8012bccbab63a04d5812e1836b029635aa77440f","observation_id":"c122f53e-bf4a-4aca-88ef-cafab756fe45","resolution":{"observed_at":"2026-08-06T19:32:54.139737Z","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":"2026-08-06T19:32:54.143072Z","title":"Fast r-cnn","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.143072Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:4678ac1387f94809abca16aa0d3259192f837583e2f7d6b8accae5529a3f0c49","observation_id":"a6232755-2b3d-4e20-be23-24161ae80453","resolution":{"observed_at":"2026-08-06T19:32:54.143072Z","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":"2026-08-06T19:32:54.147413Z","title":"Evolving modular fast-weight networks for control","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.147413Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:e34f981883a946511766553f2eff6b38660b644bd373b2ddd9f744571d8942dc","observation_id":"37450394-7e1f-4a26-b11f-a51b3c507a5d","resolution":{"observed_at":"2026-08-06T19:32:54.147413Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1410.5401","last_updated":"2014-12-10T16:01:39Z","snapshot_observed_at":"2026-08-01T22:22:04.725773Z","submitted_at":"2014-10-20T19:28:26Z","title":"Neural Turing Machines","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1410.5401","snapshot_observed_at":"2026-08-06T19:32:54.150746Z","title":"Neural turing machines","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.150746Z"},"links":{"cited_paper":"/paper/1410.5401","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:9ed253838a24dcf0aad391348af18aae547f6b4ea23562c66a00b6dd80179af7","observation_id":"23e523ff-9250-4fd0-9fe6-428781bdfdb3","resolution":{"observed_at":"2026-08-06T19:32:54.150746Z","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":"2026-08-06T19:32:54.153929Z","title":"Development or dreamfield delusions: Assessing casino gambling’s costs and benefits","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.153929Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:104cc12e69390388b04ff7f98f8d9c61217c55086219b2c4d77af06ffa2dcce6","observation_id":"00aeaea4-ff2b-447b-bd02-3e7081203cd3","resolution":{"observed_at":"2026-08-06T19:32:54.153929Z","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":"2026-08-06T19:32:54.157360Z","title":"Snapnet-r: Consistent 3d multi-view semantic labeling for robotics","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.157360Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:b8cb2aea51d47d5747c6b21014676040652bd6510871578bffce00ccb9ab6b48","observation_id":"ee3ab87f-eb6d-4959-ab69-4927fa2738bd","resolution":{"observed_at":"2026-08-06T19:32:54.157360Z","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":"2026-08-06T19:32:54.160807Z","title":"An investigation of model-free planning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.160807Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:f2f6a7fee4dd1b295c83396bf2709ec42428954a0583e3f9e4a4fa93d7bfe16d","observation_id":"44ef741d-55c8-4c5d-98c0-1b0e6a2dc0c9","resolution":{"observed_at":"2026-08-06T19:32:54.160807Z","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":"2026-08-06T19:32:54.164099Z","title":"Spottune: transfer learning through adaptive fine-tuning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.164099Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:4182268c49e17e1dfa9dcc097655b347c9676e6fec73b49913ab00884730c07d","observation_id":"55e6e52c-9a3c-4f20-804d-1fc382a41644","resolution":{"observed_at":"2026-08-06T19:32:54.164099Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.09106","last_updated":"2016-12-01T10:08:15Z","snapshot_observed_at":"2026-07-06T05:12:38.024970Z","submitted_at":"2016-09-27T05:57:00Z","title":"HyperNetworks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.09106","snapshot_observed_at":"2026-08-06T19:32:54.167973Z","title":"Hypernetworks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.167973Z"},"links":{"cited_paper":"/paper/1609.09106","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:ad97a8bc730f816ce94ad351f35177f5b27de3c14cbcac8c08c0435b49281561","observation_id":"10f55d32-955c-47fc-9b8b-769205a85628","resolution":{"observed_at":"2026-08-06T19:32:54.167973Z","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":"2026-08-06T19:32:54.171082Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.171082Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:c49c02f0b32fd3cdde993cf1bbf1121cd6b5d417331d3796a59e3d9117b53e64","observation_id":"5f537f7a-a69c-4393-91d9-e05d971ed05a","resolution":{"observed_at":"2026-08-06T19:32:54.171082Z","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":"2026-08-06T19:32:54.173487Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.173487Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:6fcadbfd04d63f64be3652d6fa282496312ebdc606e0f35cc5bb1d72ee951545","observation_id":"c02c2113-875d-45d5-a8d8-b4a709247859","resolution":{"observed_at":"2026-08-06T19:32:54.173487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.05722","last_updated":"2020-03-23T18:36:55Z","snapshot_observed_at":"2026-07-06T08:36:48.869880Z","submitted_at":"2019-11-13T18:53:26Z","title":"Momentum Contrast for Unsupervised Visual Representation Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.05722","snapshot_observed_at":"2026-08-06T19:32:54.176374Z","title":"Girshick","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.176374Z"},"links":{"cited_paper":"/paper/1911.05722","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:a8471447db564e81cb8bd0580ca5fe9f2810cf609ac095bbca2506deb06a83b8","observation_id":"4e3adccc-06d4-4c40-bf48-a71f01388adc","resolution":{"observed_at":"2026-08-06T19:32:54.176374Z","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":"2026-08-06T19:32:54.179796Z","title":"Mask r-cnn","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.179796Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:54691be0df737f1cc81a8b957f4cd569f6632e4747d5374ed278e6b822f7b08f","observation_id":"6b3b12ce-9249-4e5d-b0c2-6266a1b6fb99","resolution":{"observed_at":"2026-08-06T19:32:54.179796Z","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":"2026-08-06T19:32:54.182537Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.182537Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:a5af9c0028dd665f347738fc2f11f16e773e748ac19b64cd52862aaf35c0b899","observation_id":"b5eae914-d85b-4954-80d8-466d98b75990","resolution":{"observed_at":"2026-08-06T19:32:54.182537Z","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":"2026-08-06T19:32:54.184887Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.184887Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:2931ae5de2e8a9821c5fc378f0de2c2847ea1459f9a8663fc2657d5166d6a19f","observation_id":"56fa57f6-ff03-4c98-b863-1af1746663e8","resolution":{"observed_at":"2026-08-06T19:32:54.184887Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03164","last_updated":"2021-06-06T16:10:12Z","snapshot_observed_at":"2026-07-06T11:16:26.441741Z","submitted_at":"2021-06-06T16:10:12Z","title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.03164","snapshot_observed_at":"2026-08-06T19:32:54.188288Z","title":"On the effectiveness of adapter-based tuning for pretrained language model adaptation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.188288Z"},"links":{"cited_paper":"/paper/2106.03164","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:7e8542acd221f4b430225de0a189b34f93a156fccc24a964f26d8d08b3e7abab","observation_id":"fcfb74f5-afa6-427c-b08b-fdb06a1fec1c","resolution":{"observed_at":"2026-08-06T19:32:54.188288Z","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":"2026-08-06T19:32:54.191529Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.191529Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:a1a658d8a12c85da8b8aa0cd0088eb6e0cbf3e905130a8d5305d0bfb21b92765","observation_id":"0a95f90f-aa28-47ce-a1b4-d9e903434f63","resolution":{"observed_at":"2026-08-06T19:32:54.191529Z","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":"2026-08-06T19:32:54.194338Z","title":"Long short-term memory","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.194338Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:4b4a4635bc0f78ed43e5c7f7f9538a5f7d0f18165fedc13b4d83f8f37aadc1b4","observation_id":"3815d854-e7e8-468e-bd69-5f8330a9d49b","resolution":{"observed_at":"2026-08-06T19:32:54.194338Z","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":"2026-08-06T19:32:54.197107Z","title":"Learning to learn using gradient descent","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.197107Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:280d7c097e2cc91fc9c42e0462dbba048e3b7123ff4773237df141d393ff58fa","observation_id":"8e23f21b-19de-4900-8643-7a8674c753ac","resolution":{"observed_at":"2026-08-06T19:32:54.197107Z","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":"2026-08-06T19:32:54.201329Z","title":"Avatarclip: Zero-shot text-driven generation and animation of 3d avatars","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.201329Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:672970acb6851ac4f8a3e5d4078a5ce96c085eac7a59c918518d2c0d05c4e202","observation_id":"8868e35f-edee-4477-a088-b5e6a0526cd8","resolution":{"observed_at":"2026-08-06T19:32:54.201329Z","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":"2026-08-06T19:32:54.205036Z","title":"Equivariant diffusion for molecule generation in 3d, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.205036Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:a5639a1b39d641d42b3f95f9318e1fa0a978b75e9b9b39ef36394d917564eada","observation_id":"af796a3b-8c71-414c-b493-f2dffa307f6b","resolution":{"observed_at":"2026-08-06T19:32:54.205036Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.05439","last_updated":"2020-11-07T20:22:57Z","snapshot_observed_at":"2026-08-05T23:42:31.035532Z","submitted_at":"2020-04-11T16:34:24Z","title":"Meta-Learning in Neural Networks: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.05439","snapshot_observed_at":"2026-08-06T19:32:54.208459Z","title":"Meta-learning in neural networks: A survey","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.208459Z"},"links":{"cited_paper":"/paper/2004.05439","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:dd69db521579c210cfddbb8649725ac1905c146bed9ead94b22bf98dc26bd034","observation_id":"4da49965-3032-4721-adf3-258a5eacc9ff","resolution":{"observed_at":"2026-08-06T19:32:54.208459Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1801.06146","last_updated":"2018-05-23T09:23:47Z","snapshot_observed_at":"2026-08-06T18:01:48.915710Z","submitted_at":"2018-01-18T17:54:52Z","title":"Universal Language Model Fine-tuning for Text Classification","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.06146","snapshot_observed_at":"2026-08-06T19:32:54.211808Z","title":"Universal language model fine-tuning for text classifi- cation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.211808Z"},"links":{"cited_paper":"/paper/1801.06146","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:3547118edb57551642b5ecc5ed1f928b47134244be701febae80f9c5477f8a6d","observation_id":"9f29867c-a415-4e45-b3a7-1bc8e85ed404","resolution":{"observed_at":"2026-08-06T19:32:54.211808Z","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":"2026-08-06T19:32:54.214889Z","title":"Attention-based multi-context guiding for few-shot semantic segmentation","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.214889Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:c529c3b52e08971b90de1b667967265e4d369eecc4e2b9ba03b3a1853a81896b","observation_id":"43d4f527-a493-46c0-98d9-aa1d89cf50bf","resolution":{"observed_at":"2026-08-06T19:32:54.214889Z","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":"2026-08-06T19:32:54.217371Z","title":"Supervoxel convolution for online 3d semantic segmentation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.217371Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:4987b1105701c9ea26c137e68782f52cb2bb75021b2c13d74a38f085e5d3d4af","observation_id":"355fe682-5a28-4b73-9d68-35710d6b2efe","resolution":{"observed_at":"2026-08-06T19:32:54.217371Z","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":"2026-08-06T19:32:54.221234Z","title":"Self-challenging improves cross-domain generalization","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.221234Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:9a5b51e51b725cc570834721c8b7e348cb6f126fb63b76023f0752c44b1b4748","observation_id":"c305831b-cb47-4ce0-9375-135a7bf7a30f","resolution":{"observed_at":"2026-08-06T19:32:54.221234Z","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":"2026-08-06T19:32:54.223661Z","title":"Can we predict t cell specificity with digital biology and machine learning? Nature Reviews Immunology, pages 1–11, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.223661Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:c37abdc15df4097ce72d448661ae8df512fe5bfbcce3a8ad343c232d4390ee3f","observation_id":"abf486d0-5987-40dd-9bb5-62e5fbf5de8a","resolution":{"observed_at":"2026-08-06T19:32:54.223661Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05407","last_updated":"2019-02-25T14:18:11Z","snapshot_observed_at":"2026-07-31T19:09:21.589864Z","submitted_at":"2018-03-14T17:09:27Z","title":"Averaging Weights Leads to Wider Optima and Better Generalization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05407","snapshot_observed_at":"2026-08-06T19:32:54.226699Z","title":"Averaging weights leads to wider optima and better generalization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.226699Z"},"links":{"cited_paper":"/paper/1803.05407","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:f02542b54adcc6cbdbbf8e52f86522eb7a68560e867217d57212118227bff9ec","observation_id":"3316143d-b7b7-4256-8216-c7c51b8467f3","resolution":{"observed_at":"2026-08-06T19:32:54.226699Z","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":"2026-08-06T19:32:54.230453Z","title":"Barron, Pieter Abbeel, and Ben Poole","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.230453Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:44ce8bb750835636b7907656b3cf8c4e8f4cec2c6793ea71a972111405a73062","observation_id":"8bb58740-6ad5-44b4-9c18-6df102815379","resolution":{"observed_at":"2026-08-06T19:32:54.230453Z","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":"2026-08-06T19:32:54.233347Z","title":"Putting nerf on a diet: Semantically consistent few-shot view synthesis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.233347Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:a5db179afc04e5bb6eab85acdaf23c9d4033bdc0f1ee97730aab2894bf8e54d8","observation_id":"c110fe16-4662-4a9c-b598-830876b5f60e","resolution":{"observed_at":"2026-08-06T19:32:54.233347Z","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":"2026-08-06T19:32:54.236364Z","title":"Meta-learning representations for continual learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.236364Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:0091b1d551c27abd7cec967da66afe53c48c0698d110ca50097d9c82a3d46bfc","observation_id":"cd26108d-7f30-4652-8d51-f8d322cdd2b8","resolution":{"observed_at":"2026-08-06T19:32:54.236364Z","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":"2026-08-06T19:32:54.240308Z","title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.240308Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:a783c1ceedb2a2294a26fb9b919731b9e256f8c1dbffc3bb4f546201d48c3d9a","observation_id":"e4433f34-62f9-49f3-9c1d-0430880e7d9b","resolution":{"observed_at":"2026-08-06T19:32:54.240308Z","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":"2026-08-06T19:32:54.243487Z","title":"Human learning and memory","venue":null,"work_id":null,"year":1987},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.243487Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:8ebbc03da6f6769447d5725f5b3312e5b419218773b4ed412c16aa41494d6286","observation_id":"984f4ace-2185-4bf8-a018-260c3b238663","resolution":{"observed_at":"2026-08-06T19:32:54.243487Z","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":"2026-08-06T19:32:54.247257Z","title":"Shap-e: Generating conditional 3d implicit functions, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.247257Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:fd28536d3a3e6d4ad76feba1a89315371564016a91866e0097504196b3a003bb","observation_id":"f18b2814-4e33-42e7-a433-46cc50fd17b6","resolution":{"observed_at":"2026-08-06T19:32:54.247257Z","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":"2026-08-06T19:32:54.250135Z","title":"Lerf: Language embedded radiance fields","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.250135Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:cce6fbab909c90f835d935ebe94366e53c1c4d3c935204568884a7a9fcbc5ddf","observation_id":"3d2492d6-ecd2-444b-aa4c-5891b62250bb","resolution":{"observed_at":"2026-08-06T19:32:54.250135Z","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":"2026-08-06T19:32:54.252993Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.252993Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:5978132fdab866c021c3f9247e987e7b824b914ec8f14c0445e403d327ffef4d","observation_id":"218747ff-0a69-4014-b2f1-1231d20dc927","resolution":{"observed_at":"2026-08-06T19:32:54.252993Z","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":"2026-08-06T19:32:54.256056Z","title":"Overcoming catastrophic forgetting in neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.256056Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:0982df3b183d7bfca44a2cb13c939dfb5a0909793c7a80c460e07a3a0b05c9f6","observation_id":"21afddff-a95b-489c-8b04-0dfcddb9c584","resolution":{"observed_at":"2026-08-06T19:32:54.256056Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.14905","last_updated":"2022-03-13T11:41:05Z","snapshot_observed_at":"2026-08-02T07:20:04.881917Z","submitted_at":"2020-12-29T18:56:10Z","title":"Meta Learning Backpropagation And Improving It","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.14905","snapshot_observed_at":"2026-08-06T19:32:54.259374Z","title":"Meta learning backpropagation and improving it","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.259374Z"},"links":{"cited_paper":"/paper/2012.14905","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:9324fd57038c609fdea0e1814ce1b1e050d9b5692bd92c0fd0388c657026b024","observation_id":"ef54feef-ef75-4208-bffe-0ccc07a83b3a","resolution":{"observed_at":"2026-08-06T19:32:54.259374Z","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":"2026-08-06T19:32:54.262780Z","title":"Decomposing nerf for editing via feature field distillation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.262780Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:4ca730d7cadeeeec223ce45e8293994652cf393fc68c265a85d75d4e274a0f77","observation_id":"688c9580-4a69-410f-bd9c-8a3181337ccf","resolution":{"observed_at":"2026-08-06T19:32:54.262780Z","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":"2026-08-06T19:32:54.265819Z","title":"Learning multiple layers of features from tiny images, 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.265819Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:134df2c7f10029d52048df50a7d09a0d55ec8421a170e48950c7e19a8201e2d0","observation_id":"af0c06cf-5ef6-4c63-aa0a-a366e86baa33","resolution":{"observed_at":"2026-08-06T19:32:54.265819Z","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":"2026-08-06T19:32:54.269154Z","title":"Imagenet classification with deep convolutional neural networks","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.269154Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:5a56bfc85a20284ddd760132abd651a219e0f9cda5415a241f069fb6505c0e1d","observation_id":"2d4f7ea3-ce3b-40fc-8c9c-3e5ac977e205","resolution":{"observed_at":"2026-08-06T19:32:54.269154Z","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":"2026-08-06T19:32:54.271587Z","title":"Role of cognitive factors in the acquisition of cognitive skill","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.271587Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:19640791391ad6f5783f8caa72a13059f036356857d016ae77c6063207608b88","observation_id":"7163ac85-3641-4d81-b982-f18b728461ad","resolution":{"observed_at":"2026-08-06T19:32:54.271587Z","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":"2026-08-06T19:32:54.274006Z","title":"Omniglot git repo, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.274006Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:8434ecc3f8f3849d034fb59bf2901313d3cbb591d76f0a169b7037851b595d6c","observation_id":"728ed3cd-e9e5-4d92-b615-0d11a0749160","resolution":{"observed_at":"2026-08-06T19:32:54.274006Z","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":"2026-08-06T19:32:54.277516Z","title":"Human-level concept learning through probabilistic program induction","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.277516Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:f4ab16f515477902afa745134d6acd4bfb98ad7b06aeddf4dad718445bbd3452","observation_id":"998bb67d-7b26-4fba-83e7-2902b2692ee6","resolution":{"observed_at":"2026-08-06T19:32:54.277516Z","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":"2026-08-06T19:32:54.280031Z","title":"Colorization as a proxy task for visual understanding","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.280031Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:18737edb4e4d9854d95fe50c6c7f316da47c4d82f46d5ff563dab242fae2226a","observation_id":"76d47ec9-39dc-40cd-8614-afb7b273807a","resolution":{"observed_at":"2026-08-06T19:32:54.280031Z","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":"2026-08-06T19:32:54.282290Z","title":"Deeper, broader and artier domain generalization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.282290Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:e9e79ed1baa786dd5ecd217f8ca9620b47d8f8693eac628cc0ac67d3117ca52e","observation_id":"41fcc85a-18ab-4897-9510-e116c02f25a4","resolution":{"observed_at":"2026-08-06T19:32:54.282290Z","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":"2026-08-06T19:32:54.285462Z","title":"Learning to generalize: Meta-learning for domain generalization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.285462Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:562574056a4a280b4a2edb86bccfb08f412d150ab6a8898d230de8c9e1f60632","observation_id":"21910a93-84de-4411-957b-4c167d11ab6b","resolution":{"observed_at":"2026-08-06T19:32:54.285462Z","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":"2026-08-06T19:32:54.288973Z","title":"Referring image segmentation via recurrent refinement networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.288973Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:2d9402ed33d679b5afd5d3cf154ccd84c38b17c018699d46e8275b23657f3516","observation_id":"321c9587-ebb5-4c36-8206-9a56a1376bd4","resolution":{"observed_at":"2026-08-06T19:32:54.288973Z","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":"2026-08-06T19:32:54.292212Z","title":"Fss-1000: A 1000-class dataset for few-shot segmentation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.292212Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:f9f14ed2fdaf30a8294a7a1d1f47c329783d059c4266804778e0753480ff1f6c","observation_id":"c984569c-27e3-4600-92d5-48c4fd865127","resolution":{"observed_at":"2026-08-06T19:32:54.292212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.09835","last_updated":"2017-09-28T15:59:41Z","snapshot_observed_at":"2026-07-06T05:53:24.061473Z","submitted_at":"2017-07-31T13:08:11Z","title":"Meta-SGD: Learning to Learn Quickly for Few-Shot Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.09835","snapshot_observed_at":"2026-08-06T19:32:54.294985Z","title":"Meta-sgd: Learning to learn quickly for few-shot learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.294985Z"},"links":{"cited_paper":"/paper/1707.09835","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:524cf2b2a273e6a5d7c20e8df9d370520a6426f2c2d95e7facbfabf7d90235a1","observation_id":"1f9d5112-b011-4abc-9af4-185bae7352fc","resolution":{"observed_at":"2026-08-06T19:32:54.294985Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.10440","last_updated":"2023-03-25T17:32:25Z","snapshot_observed_at":"2026-07-06T14:20:26.566667Z","submitted_at":"2022-11-18T18:59:59Z","title":"Magic3D: High-Resolution Text-to-3D Content Creation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.10440","snapshot_observed_at":"2026-08-06T19:32:54.298796Z","title":"Magic3d: High-resolution text-to-3d content creation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.298796Z"},"links":{"cited_paper":"/paper/2211.10440","citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:62539ab49ed88cdaa24e868328b8b10210648cf44d9fae9d510946b61e1a85f1","observation_id":"17d79b07-9858-4366-b831-e452282ddebf","resolution":{"observed_at":"2026-08-06T19:32:54.298796Z","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":"2026-08-06T19:32:54.302737Z","title":"Lee, and Michael I","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.302737Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:0ac6e3c76046feef371bb54840df194b53869224237c1d8d8f541b31de863fc0","observation_id":"774da49e-0364-4e2a-ab42-3d27b9e1f9bd","resolution":{"observed_at":"2026-08-06T19:32:54.302737Z","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":"2026-08-06T19:32:54.306268Z","title":"Audio self-supervised learning: A survey","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures","version":2},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:54.306268Z"},"links":{"citing_paper":"/paper/2507.10446"},"observation_digest":"sha256:9648c50aa575ea078c8a2b556eedafb4da2d9e153a1b06e53fcd3c7f38008930","observation_id":"532c0dc8-8603-4ab7-a6ea-bdb4aae84ed1","resolution":{"observed_at":"2026-08-06T19:32:54.306268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.10446","last_updated":"2025-07-15T02:06:07Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-06T19:24:51.226619Z","submitted_at":"2025-07-07T18:48:09Z","title":"Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":98,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":214},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 100 of 214 outbound references and 0 inbound Pith citation observations for arXiv:2507.10446."}