{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CQGQSXWWPIUWZSTOC4M5P7E5EI","short_pith_number":"pith:CQGQSXWW","canonical_record":{"source":{"id":"2308.15037","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-29T05:44:00Z","cross_cats_sorted":[],"title_canon_sha256":"c4ff87cea30fcb293a2aa3cc7bd8ab6d5e440eec8587275fefc708c2d6cdcc88","abstract_canon_sha256":"b1d8c0a928af407a749c45df1f9c64152f891f94b880808f3654170b7345b511"},"schema_version":"1.0"},"canonical_sha256":"140d095ed67a296cca6e1719d7fc9d22151736965ade55621c85e2976256dec5","source":{"kind":"arxiv","id":"2308.15037","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.15037","created_at":"2026-07-05T06:45:42Z"},{"alias_kind":"arxiv_version","alias_value":"2308.15037v1","created_at":"2026-07-05T06:45:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15037","created_at":"2026-07-05T06:45:42Z"},{"alias_kind":"pith_short_12","alias_value":"CQGQSXWWPIUW","created_at":"2026-07-05T06:45:42Z"},{"alias_kind":"pith_short_16","alias_value":"CQGQSXWWPIUWZSTO","created_at":"2026-07-05T06:45:42Z"},{"alias_kind":"pith_short_8","alias_value":"CQGQSXWW","created_at":"2026-07-05T06:45:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CQGQSXWWPIUWZSTOC4M5P7E5EI","target":"record","payload":{"canonical_record":{"source":{"id":"2308.15037","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-29T05:44:00Z","cross_cats_sorted":[],"title_canon_sha256":"c4ff87cea30fcb293a2aa3cc7bd8ab6d5e440eec8587275fefc708c2d6cdcc88","abstract_canon_sha256":"b1d8c0a928af407a749c45df1f9c64152f891f94b880808f3654170b7345b511"},"schema_version":"1.0"},"canonical_sha256":"140d095ed67a296cca6e1719d7fc9d22151736965ade55621c85e2976256dec5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:42.532868Z","signature_b64":"anQ1wbuWX077nQVAbrTPXkemW0fTCRXOPdULMhMY8CLV7A6iC5gmGGKcVVsKHx4eX3ApakIGsGkZSerM9H4lDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"140d095ed67a296cca6e1719d7fc9d22151736965ade55621c85e2976256dec5","last_reissued_at":"2026-07-05T06:45:42.532391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:42.532391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.15037","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":"2026-07-05T06:45:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f8dkYbZbdVD18SpcmbbgJqSVzZJO1D3DsWc3qrkP1+U8GV17ZIy2UDsIDUK2VVIIUVlsot0yQQ/6lpeKVxbTBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:54:23.881644Z"},"content_sha256":"90f7a2f232008c68b4b04b15389a497cc146426640732ed7d3e21d371768773f","schema_version":"1.0","event_id":"sha256:90f7a2f232008c68b4b04b15389a497cc146426640732ed7d3e21d371768773f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CQGQSXWWPIUWZSTOC4M5P7E5EI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is it an i or an l: Test-time Adaptation of Text Line Recognition Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Debapriya Tula, Gagan Madan, Gaurav Aggarwal, Peter Garst, Reeve Ingle, Sujoy Paul","submitted_at":"2023-08-29T05:44:00Z","abstract_excerpt":"Recognizing text lines from images is a challenging problem, especially for handwritten documents due to large variations in writing styles. While text line recognition models are generally trained on large corpora of real and synthetic data, such models can still make frequent mistakes if the handwriting is inscrutable or the image acquisition process adds corruptions, such as noise, blur, compression, etc. Writing style is generally quite consistent for an individual, which can be leveraged to correct mistakes made by such models. Motivated by this, we introduce the problem of adapting text "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15037","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/2308.15037/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":"2026-07-05T06:45:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Ao3U9utWgTgLP9YSnvdnoiHazDDY/d46OeKlKRP+3l7NU6+b96Uf/+BaFNXo0YvFT/oo5ujK+8w5bp0b/9XBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:54:23.882225Z"},"content_sha256":"2f4dac2fc6b993305967af4ebd2a92087bc05cea645abb3a39e8ee4ef95d38ed","schema_version":"1.0","event_id":"sha256:2f4dac2fc6b993305967af4ebd2a92087bc05cea645abb3a39e8ee4ef95d38ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQGQSXWWPIUWZSTOC4M5P7E5EI/bundle.json","state_url":"https://pith.science/pith/CQGQSXWWPIUWZSTOC4M5P7E5EI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQGQSXWWPIUWZSTOC4M5P7E5EI/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":"2026-08-04T11:54:23Z","links":{"resolver":"https://pith.science/pith/CQGQSXWWPIUWZSTOC4M5P7E5EI","bundle":"https://pith.science/pith/CQGQSXWWPIUWZSTOC4M5P7E5EI/bundle.json","state":"https://pith.science/pith/CQGQSXWWPIUWZSTOC4M5P7E5EI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQGQSXWWPIUWZSTOC4M5P7E5EI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CQGQSXWWPIUWZSTOC4M5P7E5EI","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":"b1d8c0a928af407a749c45df1f9c64152f891f94b880808f3654170b7345b511","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-29T05:44:00Z","title_canon_sha256":"c4ff87cea30fcb293a2aa3cc7bd8ab6d5e440eec8587275fefc708c2d6cdcc88"},"schema_version":"1.0","source":{"id":"2308.15037","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.15037","created_at":"2026-07-05T06:45:42Z"},{"alias_kind":"arxiv_version","alias_value":"2308.15037v1","created_at":"2026-07-05T06:45:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15037","created_at":"2026-07-05T06:45:42Z"},{"alias_kind":"pith_short_12","alias_value":"CQGQSXWWPIUW","created_at":"2026-07-05T06:45:42Z"},{"alias_kind":"pith_short_16","alias_value":"CQGQSXWWPIUWZSTO","created_at":"2026-07-05T06:45:42Z"},{"alias_kind":"pith_short_8","alias_value":"CQGQSXWW","created_at":"2026-07-05T06:45:42Z"}],"graph_snapshots":[{"event_id":"sha256:2f4dac2fc6b993305967af4ebd2a92087bc05cea645abb3a39e8ee4ef95d38ed","target":"graph","created_at":"2026-07-05T06:45:42Z","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/2308.15037/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recognizing text lines from images is a challenging problem, especially for handwritten documents due to large variations in writing styles. While text line recognition models are generally trained on large corpora of real and synthetic data, such models can still make frequent mistakes if the handwriting is inscrutable or the image acquisition process adds corruptions, such as noise, blur, compression, etc. Writing style is generally quite consistent for an individual, which can be leveraged to correct mistakes made by such models. Motivated by this, we introduce the problem of adapting text ","authors_text":"Debapriya Tula, Gagan Madan, Gaurav Aggarwal, Peter Garst, Reeve Ingle, Sujoy Paul","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-29T05:44:00Z","title":"Is it an i or an l: Test-time Adaptation of Text Line Recognition Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15037","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":"sha256:90f7a2f232008c68b4b04b15389a497cc146426640732ed7d3e21d371768773f","target":"record","created_at":"2026-07-05T06:45:42Z","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":"b1d8c0a928af407a749c45df1f9c64152f891f94b880808f3654170b7345b511","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-29T05:44:00Z","title_canon_sha256":"c4ff87cea30fcb293a2aa3cc7bd8ab6d5e440eec8587275fefc708c2d6cdcc88"},"schema_version":"1.0","source":{"id":"2308.15037","kind":"arxiv","version":1}},"canonical_sha256":"140d095ed67a296cca6e1719d7fc9d22151736965ade55621c85e2976256dec5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"140d095ed67a296cca6e1719d7fc9d22151736965ade55621c85e2976256dec5","first_computed_at":"2026-07-05T06:45:42.532391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:45:42.532391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"anQ1wbuWX077nQVAbrTPXkemW0fTCRXOPdULMhMY8CLV7A6iC5gmGGKcVVsKHx4eX3ApakIGsGkZSerM9H4lDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:45:42.532868Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.15037","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90f7a2f232008c68b4b04b15389a497cc146426640732ed7d3e21d371768773f","sha256:2f4dac2fc6b993305967af4ebd2a92087bc05cea645abb3a39e8ee4ef95d38ed"],"state_sha256":"f04f58135b177c9ea06f264b30a96d78842eedb6646f9b6829f74f9ccab69f76"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9LbBIwWsb8DzrO1WQQu0ZAxYiJBZCWWEafAYV1fyoGKSAHuSOwkquiJLQdy/JPn6fx+bMvk8lzD/pelozx5eAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:54:23.887282Z","bundle_sha256":"5e06aa427ed78c7b374f3db521245f727c1466f7da27443affbf167f20dd69a7"}}