{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:NIAINH5T4HY2NGEMQK6F76NFMZ","short_pith_number":"pith:NIAINH5T","canonical_record":{"source":{"id":"2005.13044","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-05-26T21:15:20Z","cross_cats_sorted":[],"title_canon_sha256":"43b0363170a701135688f9ab54186c3222279b488f5ee08ede15d4782dfebf32","abstract_canon_sha256":"2e54a6929972a19434709d936339b3e461126a6d685b8e82224bccf203f151ec"},"schema_version":"1.0"},"canonical_sha256":"6a00869fb3e1f1a6988c82bc5ff9a5667ab051feef3ad6cb5ff53ef4d394e0d0","source":{"kind":"arxiv","id":"2005.13044","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.13044","created_at":"2026-07-05T01:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2005.13044v1","created_at":"2026-07-05T01:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.13044","created_at":"2026-07-05T01:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"NIAINH5T4HY2","created_at":"2026-07-05T01:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"NIAINH5T4HY2NGEM","created_at":"2026-07-05T01:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"NIAINH5T","created_at":"2026-07-05T01:06:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:NIAINH5T4HY2NGEMQK6F76NFMZ","target":"record","payload":{"canonical_record":{"source":{"id":"2005.13044","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-05-26T21:15:20Z","cross_cats_sorted":[],"title_canon_sha256":"43b0363170a701135688f9ab54186c3222279b488f5ee08ede15d4782dfebf32","abstract_canon_sha256":"2e54a6929972a19434709d936339b3e461126a6d685b8e82224bccf203f151ec"},"schema_version":"1.0"},"canonical_sha256":"6a00869fb3e1f1a6988c82bc5ff9a5667ab051feef3ad6cb5ff53ef4d394e0d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:00.593219Z","signature_b64":"IxkPwVhFKGT+C0rvp8Vkgfl+cyze5hWtoKrrFTVmzexIHHL5hmbWTQV137/aSlAeyyJXGFlVIhO/0Qz7aOEjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a00869fb3e1f1a6988c82bc5ff9a5667ab051feef3ad6cb5ff53ef4d394e0d0","last_reissued_at":"2026-07-05T01:06:00.592805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:00.592805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.13044","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:06:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gdn4/Dy2D28HO4Wzksut/89Lb7d7tZXnDhzxvp7ggNXQBmKblwNw4Cpsj/awuuLjvjeT5eojLLVFNC9GLL6QAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:14:38.338999Z"},"content_sha256":"468b1e804ffc16a85b0d3014e208436eca91fccec978da27c21ac799bdc129cb","schema_version":"1.0","event_id":"sha256:468b1e804ffc16a85b0d3014e208436eca91fccec978da27c21ac799bdc129cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:NIAINH5T4HY2NGEMQK6F76NFMZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alicia Forn\\'es, Lei Kang, Mar\\c{c}al Rusi\\~nol, Mauricio Villegas, Pau Riba","submitted_at":"2020-05-26T21:15:20Z","abstract_excerpt":"The advent of recurrent neural networks for handwriting recognition marked an important milestone reaching impressive recognition accuracies despite the great variability that we observe across different writing styles. Sequential architectures are a perfect fit to model text lines, not only because of the inherent temporal aspect of text, but also to learn probability distributions over sequences of characters and words. However, using such recurrent paradigms comes at a cost at training stage, since their sequential pipelines prevent parallelization. In this work, we introduce a non-recurren"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.13044","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.13044/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:06:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c+G1B8lmL9gNiM+bdTZLfOe1Y2hpV5/EFTD7aT5bW4Bm7I+legiolglrCrXmPWtns5D7XkwtE1cR7wPJWQMqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:14:38.339505Z"},"content_sha256":"c11a2c443157915a7071c46959009cd61e6488631b652b1b9bbf420283160231","schema_version":"1.0","event_id":"sha256:c11a2c443157915a7071c46959009cd61e6488631b652b1b9bbf420283160231"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NIAINH5T4HY2NGEMQK6F76NFMZ/bundle.json","state_url":"https://pith.science/pith/NIAINH5T4HY2NGEMQK6F76NFMZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NIAINH5T4HY2NGEMQK6F76NFMZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T10:14:38Z","links":{"resolver":"https://pith.science/pith/NIAINH5T4HY2NGEMQK6F76NFMZ","bundle":"https://pith.science/pith/NIAINH5T4HY2NGEMQK6F76NFMZ/bundle.json","state":"https://pith.science/pith/NIAINH5T4HY2NGEMQK6F76NFMZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NIAINH5T4HY2NGEMQK6F76NFMZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:NIAINH5T4HY2NGEMQK6F76NFMZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2e54a6929972a19434709d936339b3e461126a6d685b8e82224bccf203f151ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-05-26T21:15:20Z","title_canon_sha256":"43b0363170a701135688f9ab54186c3222279b488f5ee08ede15d4782dfebf32"},"schema_version":"1.0","source":{"id":"2005.13044","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.13044","created_at":"2026-07-05T01:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2005.13044v1","created_at":"2026-07-05T01:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.13044","created_at":"2026-07-05T01:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"NIAINH5T4HY2","created_at":"2026-07-05T01:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"NIAINH5T4HY2NGEM","created_at":"2026-07-05T01:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"NIAINH5T","created_at":"2026-07-05T01:06:00Z"}],"graph_snapshots":[{"event_id":"sha256:c11a2c443157915a7071c46959009cd61e6488631b652b1b9bbf420283160231","target":"graph","created_at":"2026-07-05T01:06:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2005.13044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of recurrent neural networks for handwriting recognition marked an important milestone reaching impressive recognition accuracies despite the great variability that we observe across different writing styles. Sequential architectures are a perfect fit to model text lines, not only because of the inherent temporal aspect of text, but also to learn probability distributions over sequences of characters and words. However, using such recurrent paradigms comes at a cost at training stage, since their sequential pipelines prevent parallelization. In this work, we introduce a non-recurren","authors_text":"Alicia Forn\\'es, Lei Kang, Mar\\c{c}al Rusi\\~nol, Mauricio Villegas, Pau Riba","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-05-26T21:15:20Z","title":"Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.13044","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:468b1e804ffc16a85b0d3014e208436eca91fccec978da27c21ac799bdc129cb","target":"record","created_at":"2026-07-05T01:06:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2e54a6929972a19434709d936339b3e461126a6d685b8e82224bccf203f151ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-05-26T21:15:20Z","title_canon_sha256":"43b0363170a701135688f9ab54186c3222279b488f5ee08ede15d4782dfebf32"},"schema_version":"1.0","source":{"id":"2005.13044","kind":"arxiv","version":1}},"canonical_sha256":"6a00869fb3e1f1a6988c82bc5ff9a5667ab051feef3ad6cb5ff53ef4d394e0d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a00869fb3e1f1a6988c82bc5ff9a5667ab051feef3ad6cb5ff53ef4d394e0d0","first_computed_at":"2026-07-05T01:06:00.592805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:06:00.592805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IxkPwVhFKGT+C0rvp8Vkgfl+cyze5hWtoKrrFTVmzexIHHL5hmbWTQV137/aSlAeyyJXGFlVIhO/0Qz7aOEjDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:06:00.593219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.13044","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:468b1e804ffc16a85b0d3014e208436eca91fccec978da27c21ac799bdc129cb","sha256:c11a2c443157915a7071c46959009cd61e6488631b652b1b9bbf420283160231"],"state_sha256":"e25899781914ab811203199f0be4133232caf62736763a2a3280d140231fea80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iiUfItskfQ7A926Tqew6TzR0wmP/YmkPnkRlsozF//OHoerf031CmacWqP2L1fH6eErDqIMwqus9nsi1kF83AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T10:14:38.344351Z","bundle_sha256":"e3881a158360ad746e6c9559e7ecdb9d19b135acc326a42aa0949c4a7f4588a2"}}