{"as_of":"2026-08-19T06:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:294575b2157f06872b9d71bf02a991f4af712ae3211848479bd72d978ccd0f56","coverage":[{"denominator":59,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":59,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T16:44:59.773976Z","state":"measured"},{"denominator":59,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":59,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2501.12898/citation-record","integrity":"/paper/2501.12898/integrity","json":"/paper/2501.12898/citation-record.json","paper":"/paper/2501.12898"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:44:59.554363Z","title":"Improved handwritten digit recognition using convolutional neural networks (cnn)","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.554363Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:b03ffe448220bb3299a80ad11aa2ea13dfae884704e6e2b11950189d85ed911f","observation_id":"bd32c61f-47c9-4799-8099-7b12b7c9176a","resolution":{"observed_at":"2026-08-10T16:44:59.554363Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.475928Z","title":"An improved faster-rcnn model for handwritten character recognition","venue":null,"work_id":"7472c10d-ca76-4cc9-b818-d861f5db6ad3","year":2021},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.558979Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:9e7f7edc88769747e44d4dbeef11c7c42e1488e354863599845323a2bf78f0a9","observation_id":"2cf69210-675e-450f-9d21-a2e78e11e73a","resolution":{"observed_at":"2026-08-10T16:45:00.479483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-10T16:44:59.563193Z","title":"Anderson and Sofia I","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.563193Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:86f3d8959b02b8f79a7bd2ce81a59513e0b45414775d9fb09c13a155716e5ae6","observation_id":"322a1d6e-4399-4e91-af51-4cca0bee211c","resolution":{"observed_at":"2026-08-10T16:44:59.563193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.455201Z","title":"Mt3: Meta test-time training for self- supervised test-time adaption","venue":null,"work_id":"f26fe302-e0c9-4762-a531-f9bd2d1f90ff","year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.567348Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:b03ed83ae6b8a581589217e25d7e0e2f7656db1f9794d792fa2f1e688e56ad48","observation_id":"0c43adf2-89ed-480a-932c-7344ea09f5bd","resolution":{"observed_at":"2026-08-10T16:45:00.460020Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-10T16:44:59.571915Z","title":"Docsynth: a layout guided approach for controllable docu- ment image synthesis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.571915Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:c9356521b8eaa1793081e3ecd40051f6b115f81072149d24e173da569e63eb61","observation_id":"036e7993-49a9-48c4-a7f5-6f6573bf7c45","resolution":{"observed_at":"2026-08-10T16:44:59.571915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.433469Z","title":"Boosting modern and historical handwrit- ten text recognition with deformable convolutions","venue":null,"work_id":"eee913da-5fae-47c7-aa29-43fd88e76d01","year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.576204Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:fddf868d2193833e8265b214b8be6f9f01a95f74560991fe133655162c18e2ed","observation_id":"a4558f07-ba41-417a-8a8b-5cb0781c1da2","resolution":{"observed_at":"2026-08-10T16:45:00.438339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.14879","last_updated":"2022-05-30T06:33:15Z","snapshot_observed_at":"2026-08-16T16:56:45.925301Z","submitted_at":"2022-05-30T06:33:15Z","title":"Easter2.0: Improving convolutional models for handwritten text recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.14879","snapshot_observed_at":"2026-08-10T16:44:59.580166Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.580166Z"},"links":{"cited_paper":"/paper/2205.14879","citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:9d913d52df977358a1cc8477fe388a7cff4edf9df62fd43e110a7597f727120f","observation_id":"67e53881-a411-4e40-95e1-b3cd48643cbf","resolution":{"observed_at":"2026-08-10T16:44:59.580166Z","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":"2026-08-10T16:44:59.584678Z","title":"Contrastive test-time adaptation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.584678Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:bf8fcd9561ec840e09020a4b1f34549ba76706739a690760318a58f490f6181e","observation_id":"c878ef53-8667-4397-847f-84c575bb45a4","resolution":{"observed_at":"2026-08-10T16:44:59.584678Z","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":"2026-08-10T16:44:59.588163Z","title":"Improved test-time adaptation for domain generalization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.588163Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:d58f65ea1a4ffdbae36ad0fa87943ceb790c83e5446cb6efa92812f5929f6e28","observation_id":"d916ef07-130b-425f-8f47-67616f9bb446","resolution":{"observed_at":"2026-08-10T16:44:59.588163Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.406282Z","title":"Metafscil: A meta-learning approach for few-shot class incremental learning","venue":null,"work_id":"03f2f647-d972-47f8-bb18-5b775677501e","year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.591524Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:e510490f3407d9baccfd7442984290e955c6fdc0b0f98a810e678fe5f1296e9e","observation_id":"2a03f9c2-2c85-4a57-bcc3-dcd66b2bbd43","resolution":{"observed_at":"2026-08-10T16:45:00.410491Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.02797","last_updated":"2024-05-05T02:44:04Z","snapshot_observed_at":"2026-08-16T13:55:21.401393Z","submitted_at":"2024-05-05T02:44:04Z","title":"Adapting to Distribution Shift by Visual Domain Prompt Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.02797","snapshot_observed_at":"2026-08-10T16:44:59.595503Z","title":"Adapting to distribution shift by visual domain prompt generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.595503Z"},"links":{"cited_paper":"/paper/2405.02797","citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:522774278614961f7164ee7776924ff6b1bea72f817b854c30e36a1fd7b4dc11","observation_id":"53faa9e7-e428-4590-84ae-114948821528","resolution":{"observed_at":"2026-08-10T16:44:59.595503Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.394078Z","title":"Test- time fast adaptation for dynamic scene deblurring via meta- auxiliary learning","venue":null,"work_id":"c23e5e7d-7218-49ba-b1bc-22ff51ba2b46","year":2021},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.599775Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:1c920a76a905972cd87e684751e98f9b76387527d8a8f934109ccb53cd25f4ef","observation_id":"707c59a1-ec30-4b7b-99c0-4d02723d6dd8","resolution":{"observed_at":"2026-08-10T16:45:00.398467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.381573Z","title":"Span: a simple predict & align network for handwritten para- graph recognition","venue":null,"work_id":"61a441ef-737a-4c0b-afdd-0fc1f4002cb7","year":2021},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.604180Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:70121f74f017e6936e94c28bf542c2d411586d360c85f2d5d0b337eb48f7098e","observation_id":"14d76fc1-42ba-45f8-a49d-c4c67ad1a8ca","resolution":{"observed_at":"2026-08-10T16:45:00.385418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.369786Z","title":"End-to-end handwritten paragraph text recognition using a vertical attention network","venue":null,"work_id":"2ff72d07-ac8a-4f70-bb3d-66e2a610706d","year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.607819Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:67702739b3d9d1f1638351b8a9cd2b2a4cdb509b065e9fd0369ebd693f6b75b7","observation_id":"c3407b0b-d997-4386-9ee9-f4cbfc810952","resolution":{"observed_at":"2026-08-10T16:45:00.373784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.357881Z","title":"Dan: a segmentation-free document attention network for handwritten document recognition","venue":null,"work_id":"224a0eec-6b60-40b4-81e5-843782a6bc57","year":2023},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.611224Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:28d28ab0d684147597c152391491489645c33df5cc14eb3b3dec1184bde09ae8","observation_id":"f37678a6-30af-40d0-8718-505ae0ae82bc","resolution":{"observed_at":"2026-08-10T16:45:00.362147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.344062Z","title":"Faster dan: Multi-target queries with document positional encoding for end-to-end handwritten document recognition","venue":null,"work_id":"780334f7-823f-4bb8-aafd-ab8d840f2817","year":2023},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.614853Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:c9f686a0b89c45864a415bf056cc43e4ef709121d9f088c8c27bbf621a71fef9","observation_id":"ffe84d4f-d27e-4e43-90e9-726d5247a434","resolution":{"observed_at":"2026-08-10T16:45:00.348523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-08-14T18:16:28.847993Z","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":"2026-08-10T16:44:59.618363Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.618363Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:b29f5e31d4f70ad7b84dcb258103a8b21871a77a0abb892888ac6fef0c4730c6","observation_id":"5b6b401b-a7b8-468f-ab21-2cdf934404e9","resolution":{"observed_at":"2026-08-10T16:44:59.618363Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.332475Z","title":"Improving cnn-rnn hybrid networks for handwrit- ing recognition","venue":null,"work_id":"63633b1f-64ee-43d6-9880-e7831540775c","year":2018},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.622321Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:629a247d7a965128b3ad9899ed94e9c835de27d6cf9f9a296dc357ca3a3afe57","observation_id":"c78a2a13-8ef9-438b-8c2b-f23e74f009eb","resolution":{"observed_at":"2026-08-10T16:45:00.336594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.321204Z","title":"The pascal visual object classes (voc) challenge","venue":null,"work_id":"8f91de2d-1cc5-42ff-b091-66f9b84e67bd","year":2010},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.626400Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:6389328856b91b1d2901212739cad50270cf8e0da60622014eba2db50639744e","observation_id":"cb48cc5d-43e5-4f70-8129-57ba61539bbe","resolution":{"observed_at":"2026-08-10T16:45:00.325333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.310182Z","title":"Model- agnostic meta-learning for fast adaptation of deep networks","venue":null,"work_id":"377678c5-32d8-4ccf-985d-1b36269d256d","year":2017},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.630154Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:5427567a03b4b579372620894510915d78af1bfd12a761c662a3b1531bc170ea","observation_id":"f6b75cb4-586f-47ef-b1f7-80eb725b1e88","resolution":{"observed_at":"2026-08-10T16:45:00.314048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.298415Z","title":"Convolutional neural network based intelligent handwritten document recognition","venue":null,"work_id":"a1dbfaf8-a75f-409b-acf2-3a558d854cda","year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.633922Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:5458e7b453631bf8110ca91d088c504279e3789cd1c4f1d8f7c87d6a5f9237e8","observation_id":"8ec811a0-40c6-4290-9499-36ba699c990f","resolution":{"observed_at":"2026-08-10T16:45:00.302630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.287035Z","title":"Handwritten gujarati numer- als classification based on deep convolution neural networks using transfer learning scenarios","venue":null,"work_id":"03bd2f56-cc64-4e2a-a6e5-71db13fa3dd4","year":2023},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.636999Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:cdb285f97397333ef9cb03703aa1d6232fdc891514c5689a67efcce09d83ce6f","observation_id":"d484e04f-24a5-46ce-b407-d6a5df737a3d","resolution":{"observed_at":"2026-08-10T16:45:00.290648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.274342Z","title":"Icdar 2011-french handwriting recognition competition","venue":null,"work_id":"9491258d-cd6e-4e30-8187-bc0901f314b0","year":2011},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.640389Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:8c454113034ad3c4a2bd19cd11287e2f47659e4e480802dc9dd520cabf2dcfe4","observation_id":"3db69fd4-b75b-488f-abc5-ef518c836a06","resolution":{"observed_at":"2026-08-10T16:45:00.278191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.00174","last_updated":"2022-10-01T03:03:20Z","snapshot_observed_at":"2026-08-16T16:27:40.902135Z","submitted_at":"2022-10-01T03:03:20Z","title":"Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.00174","snapshot_observed_at":"2026-08-10T16:44:59.644099Z","title":"Improving protonet for few-shot video object recog- nition: Winner of orbit challenge 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.644099Z"},"links":{"cited_paper":"/paper/2210.00174","citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:c7f346f1e3b24f6a72fb41fd3ef39ce6520023e3b3c4ab93bd1b49b7fe0a5bc4","observation_id":"b444b35e-12ee-4780-afad-bc8742073eca","resolution":{"observed_at":"2026-08-10T16:44:59.644099Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.262301Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":"2ec63388-82d4-4e29-9648-baffad739d1a","year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.648193Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:812e06960db6430d15e4eacea46b8922a56224eee4c395f29ca5c362dcbee35d","observation_id":"4223121f-08d5-4bd1-8acd-b7234d52b6d8","resolution":{"observed_at":"2026-08-10T16:45:00.266196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.249258Z","title":"General models for handwritten text recognition: Feasibility and state-of-the art","venue":null,"work_id":"16f5e2f4-33c0-4ffd-a476-049488ea6906","year":2021},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.652301Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:60adeff4b43fefa6314d0590809e4df3b069a830bcd7cc1b05b87e5a41adfa8d","observation_id":"bcaa112b-0efe-4db4-a99d-6c67549e85fe","resolution":{"observed_at":"2026-08-10T16:45:00.252990Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.236451Z","title":"Johnson and Emily D","venue":null,"work_id":"0ef0fd10-48f1-4d94-a27f-91faf0c3f4c9","year":2021},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.656002Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:cbfb8598528cb77ff49dc156f742616e2b6876d8a6abfe99f54c7a70de8a65f9","observation_id":"1ae76c83-d0c8-46f8-bd6f-af63ad44d5e1","resolution":{"observed_at":"2026-08-10T16:45:00.240940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.13044","last_updated":"2020-05-26T21:15:20Z","snapshot_observed_at":"2026-07-06T09:23:37.201640Z","submitted_at":"2020-05-26T21:15:20Z","title":"Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognition","version":1},"cited_work":{"arxiv_id":"2005.13044","doi":null,"metadata_source":"pith","pith_arxiv_id":"2005.13044","snapshot_observed_at":"2026-08-10T16:44:59.843401Z","title":"Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognition","venue":"cs.CV","work_id":"5d10d27d-fe0c-4b08-9d5f-a83b7ed52399","year":2020},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.659867Z"},"links":{"cited_paper":"/paper/2005.13044","citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:ec61e0191a2703cc7c16294f5a593d1d24567970c9323f04215f10db4380226a","observation_id":"c095eceb-8784-4dde-b273-222a4aa8367a","resolution":{"observed_at":"2026-08-10T16:44:59.849752Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.223538Z","title":"Meta- sgd: Learning to learn quickly for few-shot learning","venue":null,"work_id":"b76470b0-3db2-4bea-a6c7-6722ec094dd0","year":2017},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.664160Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:c2c80076bfc2002587bcf3b16b4ed3812d48a712986bfb6e0d35698e49ac8d20","observation_id":"33cb8c74-45c5-4de4-96f0-1846b692221d","resolution":{"observed_at":"2026-08-10T16:45:00.228138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.210685Z","title":"Self-supervised spa- tiotemporal representation learning by exploiting video con- tinuity","venue":null,"work_id":"cf8c3918-06f7-4304-9225-7d4533a9f2f9","year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.667839Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:be61c69c540654b37b62e3af97721106b41e8933bddcf552787e95ab478d4884","observation_id":"3bcf6699-ee24-404e-9519-f77b4378a705","resolution":{"observed_at":"2026-08-10T16:45:00.215449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-10T16:44:59.671463Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.671463Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:06db70a8c43e66614930016c3c30ece7ed772af8b5b0485fe7a33bb4e4ad7392","observation_id":"cb655c92-5c89-40a8-8f34-34ac6e34f4f3","resolution":{"observed_at":"2026-08-10T16:44:59.671463Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.188945Z","title":"Meta-auxiliary learning for future depth pre- diction in videos","venue":null,"work_id":"00f68ae4-927a-4aeb-af6f-14557db1eeb9","year":2023},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.675336Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:d01e4b2406b6d9530e6ef55fe605ca5cb0ebe7ba876fb6430c9e298478c2e178","observation_id":"09e05649-022e-40d1-82e6-0461c72ffdd5","resolution":{"observed_at":"2026-08-10T16:45:00.193724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-10T16:44:59.679650Z","title":"Few-shot class-incremental learning via entropy-regularized data-free replay","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.679650Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:e7b7868e3623316b2477fbc5d6a4ee4b005030eaba60dd756943a6fa9bcb5979","observation_id":"d8689b38-fa77-44d0-b98d-77fc0a14a85b","resolution":{"observed_at":"2026-08-10T16:44:59.679650Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.00311","last_updated":"2023-10-10T03:06:45Z","snapshot_observed_at":"2026-08-16T16:56:05.556941Z","submitted_at":"2022-06-01T08:27:19Z","title":"MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.00311","snapshot_observed_at":"2026-08-10T16:44:59.683714Z","title":"Maskocr: Text recognition with masked encoder-decoder pretraining","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.683714Z"},"links":{"cited_paper":"/paper/2206.00311","citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:ce8d8cd0f321d1d14032f67a6b76ffe9f8b909868434503c2509a0673e591606","observation_id":"2e2a8860-de77-467b-8e61-5ebc039d2c9d","resolution":{"observed_at":"2026-08-10T16:44:59.683714Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.168351Z","title":"Crowd counting us- ing meta-test-time adaptation","venue":null,"work_id":"080ab6a5-9114-4bfb-ba8f-80e41543834e","year":2024},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.687914Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:765727dde1ec64cdc65331babaa9727cd4231753575f8d634ac717093ecd4654","observation_id":"c23f2de1-3aae-4b35-932d-9daad32460d5","resolution":{"observed_at":"2026-08-10T16:45:00.172547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.154524Z","title":"The iam-database: an english sentence database for offline handwriting recognition","venue":null,"work_id":"793aa9bb-acbb-4208-b82b-5aeadd41764d","year":2002},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.691496Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:cbfb00e2dc3b3358f72f8289d485459628ec57d441fecb208dc697010784db94","observation_id":"9d009277-64c0-4145-b992-a6bbdc7000ad","resolution":{"observed_at":"2026-08-10T16:45:00.159321Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.02999","last_updated":"2018-10-22T16:11:14Z","snapshot_observed_at":"2026-08-14T19:38:16.450214Z","submitted_at":"2018-03-08T08:29:38Z","title":"On First-Order Meta-Learning Algorithms","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.02999","snapshot_observed_at":"2026-08-10T16:44:59.695425Z","title":"On first-order meta-learning algorithms","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.695425Z"},"links":{"cited_paper":"/paper/1803.02999","citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:9dca3e648e65033e890f8ec546ea6c1e94370914a101cea041b20be381be4ec9","observation_id":"a4b8eb51-d412-456c-a58c-3960ad8515fe","resolution":{"observed_at":"2026-08-10T16:44:59.695425Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.141055Z","title":"Handwritten kazakh and russian (hkr) database for text recognition","venue":null,"work_id":"a712dd48-0152-4c0f-85ea-af14137bd8cd","year":2021},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.698924Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:3b4f3adf61db90f6b6461e4233d41d9af68de8d3e0e6b6c43124698a4a021180","observation_id":"059db339-91c9-4a6e-bd75-d789457957f0","resolution":{"observed_at":"2026-08-10T16:45:00.145389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.127158Z","title":"Meta-learning of pooling layers for character recognition","venue":null,"work_id":"c681583b-d316-4bad-8571-764e6eb80386","year":2021},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.702015Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:f37211e5a07f916b528fba8ce77a1832360423da355076812d84978f27fc1162","observation_id":"4e049c93-e6d0-43d5-a88d-9315bb4492a4","resolution":{"observed_at":"2026-08-10T16:45:00.132391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.112536Z","title":null,"venue":null,"work_id":"7d8121dc-9e1a-4156-966c-46d8da9704e8","year":2017},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.705081Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:f45b60970fa606fc4326b27cfff16981b645e474f43656fa7905e9fd2ea5cc2d","observation_id":"46e278a8-ed22-42d1-9596-d3599189806f","resolution":{"observed_at":"2026-08-10T16:45:00.118520Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.098580Z","title":"Meta self- learning for multi-source domain adaptation: a benchmark","venue":null,"work_id":"435a2d83-a779-460d-9ab9-c908d37952e5","year":2021},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.708752Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:4cd9650641bab093f3454132b7780b44bc701c341f382aebe7ba5fe9436df1f5","observation_id":"55aff686-28f8-4ae3-9e44-3c0f852ce873","resolution":{"observed_at":"2026-08-10T16:45:00.102832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.083852Z","title":"Pat- tern recognition-recognition of handwritten document using convolutional neural networks","venue":null,"work_id":"28dddd2c-06b8-4d19-b50b-f49392a9e624","year":2019},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.712234Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:798007e6b262826d986448ed69a3f9289b327fc996b94e9cdcd34feb9e8597de","observation_id":"30f1eda5-f5be-48d7-97bf-52d93c459956","resolution":{"observed_at":"2026-08-10T16:45:00.088549Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-10T16:44:59.715874Z","title":"Transformer-based approach for joint handwriting and named entity recognition in historical doc- ument","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.715874Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:7b3be2b58c11b04bce19873ee4c100851b5b321ae265a6c09fdeeba3f1f17169","observation_id":"696cdc02-fb16-4673-b100-57114f673406","resolution":{"observed_at":"2026-08-10T16:44:59.715874Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.063849Z","title":"Icfhr2016 competition on hand- written text recognition on the read dataset","venue":null,"work_id":"7b44a93f-d75a-48f3-86e9-6393895edf9f","year":2016},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.719412Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:c851bdc1b4d95756d22db0811fe51d2c2f58cb4d9d7230539f73009884cc9596","observation_id":"adcac9b2-274e-4b1b-a4f9-c8d82598e686","resolution":{"observed_at":"2026-08-10T16:45:00.067910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.049395Z","title":"Image quality assessment through fsim, ssim, mse and psnr—a comparative study","venue":null,"work_id":"2f1967c3-0a10-4f8e-9af2-55045748218d","year":2019},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.723329Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:de93e0eb6a1f01954491fba2ab4a28c543c8f807f28ba1c7d02f421ec3ce4d28","observation_id":"818e5067-19ad-4c7f-87e8-d8cbda29799b","resolution":{"observed_at":"2026-08-10T16:45:00.055404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.037154Z","title":"Psnr vs ssim: impercepti- bility quality assessment for image steganography","venue":null,"work_id":"66ae19fe-5a81-49b4-b574-940798c8e372","year":2021},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.726848Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:505ce11decedc0cd751bacd8f9fd45ceebfd8ef1a014e2fec5dbb1bf18c0ede7","observation_id":"04246d05-e979-4c12-95bf-126ca15bd6e0","resolution":{"observed_at":"2026-08-10T16:45:00.041197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:45:00.017051Z","title":"Full page handwriting recognition via image to sequence extraction","venue":null,"work_id":"2c99244a-cf62-4847-8e86-962f823540ea","year":2021},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.730441Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:3d2e751a555838b265b4ba3efad76ce55e2076432a2827bd6ef1a8e9078ffab8","observation_id":"d46815ff-28fd-47f8-838f-c707b65a1e2e","resolution":{"observed_at":"2026-08-10T16:45:00.028284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-10T16:44:59.733936Z","title":"Test-time training with self- supervision for generalization under distribution shifts","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.733936Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:8d1189c500d94e641720728beca6f0372db7e33020522e8ace3f1b3d1becacf8","observation_id":"a7a3d541-94c0-49c6-93f1-37e40bb68baf","resolution":{"observed_at":"2026-08-10T16:44:59.733936Z","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":"2026-08-10T16:44:59.737874Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.737874Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:e24c3a7e1c850fac0cc5847dd9ce274c21b01b0c8bfb482063c12dac71f8851b","observation_id":"70134296-543e-46b4-b483-c4420188712d","resolution":{"observed_at":"2026-08-10T16:44:59.737874Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10726","last_updated":"2021-03-18T17:58:01Z","snapshot_observed_at":"2026-08-16T06:30:33.794820Z","submitted_at":"2020-06-18T17:55:28Z","title":"Tent: Fully Test-time Adaptation by Entropy Minimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10726","snapshot_observed_at":"2026-08-10T16:44:59.741517Z","title":"Tent: Fully test-time adaptation by entropy minimization","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.741517Z"},"links":{"cited_paper":"/paper/2006.10726","citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:67274521d31319fac7444f1753ce33f185d74156c5812ae3017df9286c9bf929","observation_id":"1185fe66-e1af-477e-a7a7-365aa8f0e4c7","resolution":{"observed_at":"2026-08-10T16:44:59.741517Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:44:59.984291Z","title":"Combinatorial learning of graph edit distance via dynamic embedding","venue":null,"work_id":"797db004-0dcf-406e-aa9c-3bde0161932d","year":2021},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.745546Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:99ee1b1a118d243391898a3246fe0ae9f04981bf141e8460b9ed501997dfb33e","observation_id":"fd5af7ed-0f14-4bd6-8543-55ab8611d05c","resolution":{"observed_at":"2026-08-10T16:44:59.988650Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:44:59.971975Z","title":"Decoupled attention network for text recognition","venue":null,"work_id":"ade1828a-6d98-40bc-b4fd-4f5edf5bccfd","year":2020},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.748951Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:0b2fb7398d475e4f984dd23eabbc92f99a67f5dd307780ea5ce85d2ccf2ba458","observation_id":"e88a87ee-4756-476f-9d25-3ab60c5bb9d6","resolution":{"observed_at":"2026-08-10T16:44:59.976151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:44:59.959054Z","title":"Distribution align- ment for fully test-time adaptation with dynamic online data streams","venue":null,"work_id":"d5bfbfc0-4448-401c-8112-214dfc406c7f","year":2025},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.752526Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:0d53c1da7ad2984d42e14092d954417fb13288040328ebe6c270570bd8da4c10","observation_id":"ec662089-faf4-4a8d-ad65-a6cf1b0e61c4","resolution":{"observed_at":"2026-08-10T16:44:59.963643Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-10T16:44:59.755859Z","title":"Start, follow, read: End-to-end full-page handwriting recognition","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.755859Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:4dc2df210c16922db4f59ad290af43a4b65d019af9e0af98b6f75cd844d89676","observation_id":"aaaaa53c-5920-4af7-96b1-e3edc4a117ae","resolution":{"observed_at":"2026-08-10T16:44:59.755859Z","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":"2026-08-10T16:44:59.759026Z","title":"Williams and Neha S","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.759026Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:0143e82d8d4cbcc6773c33db858560aac2fc6bb99ee30cd6fc5f2415196fcb59","observation_id":"2cddc07f-a6e0-415b-a2a3-746ca1d1fdde","resolution":{"observed_at":"2026-08-10T16:44:59.759026Z","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":"2026-08-10T16:44:59.762609Z","title":"Metagcd: Learning to continually learn in generalized cat- egory discovery","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.762609Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:608da830bed7812d2fc1379659920c5a3a3d94d45412d0b510b7fa9f57f71130","observation_id":"c57254b3-cc89-4fd2-a723-0a2929adc831","resolution":{"observed_at":"2026-08-10T16:44:59.762609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:44:59.927209Z","title":"Test-time domain adaptation by learning domain-aware batch normalization","venue":null,"work_id":"3d5ebd79-4a9b-4302-9b50-e5727ead75bb","year":2024},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.766371Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:ba419dc54021afe04e13bca339b5b9bb3ef65a819b10aeadb73284501cc402de","observation_id":"166df035-09b5-423f-be5b-c413faa2465a","resolution":{"observed_at":"2026-08-10T16:44:59.931036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:44:59.915442Z","title":"A-vit: Adaptive to- kens for efficient vision transformer","venue":null,"work_id":"1e21dba5-ccb4-4b35-beab-6c7e91a6b6d2","year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.770011Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:20809807e7aadc284227f51b0a9c479484e4f5fe87beecaf1dc61a1808849077","observation_id":"b364de14-e844-4ab1-8583-dcb26f95ed75","resolution":{"observed_at":"2026-08-10T16:44:59.919646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:44:59.903331Z","title":"Meta-dmoe: Adapting to domain shift by meta- distillation from mixture-of-experts","venue":null,"work_id":"a9d16754-34ad-40d9-bf91-85b94f86a36b","year":2022},"citing_paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-10T16:44:59.773976Z"},"links":{"citing_paper":"/paper/2501.12898"},"observation_digest":"sha256:fb9fed181d37163377911cfeb41c083c6c6babfbc78151f8edabe3a7dabcf249","observation_id":"63c46aae-a24c-4c7c-88f3-fd246214edd0","resolution":{"observed_at":"2026-08-10T16:44:59.907092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.12898","last_updated":"2025-01-22T14:18:47Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T06:28:19.758469Z","submitted_at":"2025-01-22T14:18:47Z","title":"DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning"},"reference_resolution":{"displayed":59,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":1,"verified_fuzzy":37},"total_outbound_references":59},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 0 inbound Pith citation observations for arXiv:2501.12898."}