{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7I3VEE42S33BLHJ6L7GTAKHSX6","short_pith_number":"pith:7I3VEE42","canonical_record":{"source":{"id":"2508.21693","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T15:02:11Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"2b9efc00966f25e38fc4daf27b71834af5ea0e40952c083a27237023fc890b45","abstract_canon_sha256":"61402942f7075fcd29407ae79e3c88dc0060ad1388b145ab677809d58b2c4109"},"schema_version":"1.0"},"canonical_sha256":"fa3752139a96f6159d3e5fcd3028f2bfb9c517e44df8a63fcff629eb86e1da12","source":{"kind":"arxiv","id":"2508.21693","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21693","created_at":"2026-07-05T12:01:48Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21693v1","created_at":"2026-07-05T12:01:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21693","created_at":"2026-07-05T12:01:48Z"},{"alias_kind":"pith_short_12","alias_value":"7I3VEE42S33B","created_at":"2026-07-05T12:01:48Z"},{"alias_kind":"pith_short_16","alias_value":"7I3VEE42S33BLHJ6","created_at":"2026-07-05T12:01:48Z"},{"alias_kind":"pith_short_8","alias_value":"7I3VEE42","created_at":"2026-07-05T12:01:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7I3VEE42S33BLHJ6L7GTAKHSX6","target":"record","payload":{"canonical_record":{"source":{"id":"2508.21693","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T15:02:11Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"2b9efc00966f25e38fc4daf27b71834af5ea0e40952c083a27237023fc890b45","abstract_canon_sha256":"61402942f7075fcd29407ae79e3c88dc0060ad1388b145ab677809d58b2c4109"},"schema_version":"1.0"},"canonical_sha256":"fa3752139a96f6159d3e5fcd3028f2bfb9c517e44df8a63fcff629eb86e1da12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:48.014292Z","signature_b64":"bbPp0l0/dpkVf3K+JVWqmr5RHszll4dnKrYWdc2RrHiZDM03G7MrezVhg5QZdPegyD1WoJ3h8zXxqY2x5VmTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa3752139a96f6159d3e5fcd3028f2bfb9c517e44df8a63fcff629eb86e1da12","last_reissued_at":"2026-07-05T12:01:48.013706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:48.013706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.21693","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":"2026-07-05T12:01:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VHfzzZB3d3/GkLcftb/AxA4XELHwokxm2WLZL71mTD86fqIj3yHErGLHdBGTcZT7ONex3kzoIEYHj9vJUIr/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:04:43.047045Z"},"content_sha256":"bb3a0aa0a23cd087eb4af93297951310d73fe68e7f0e39fbe0d88174e30bbf5e","schema_version":"1.0","event_id":"sha256:bb3a0aa0a23cd087eb4af93297951310d73fe68e7f0e39fbe0d88174e30bbf5e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7I3VEE42S33BLHJ6L7GTAKHSX6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Stop at Words? Unveiling the Bigger Picture through Line-Level OCR","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Arpan Garai, Chetan Arora, Gaurav Talebailkar, Nishit Anand, Shashank Vempati","submitted_at":"2025-08-29T15:02:11Z","abstract_excerpt":"Conventional optical character recognition (OCR) techniques segmented each character and then recognized. This made them prone to error in character segmentation, and devoid of context to exploit language models. Advances in sequence to sequence translation in last decade led to modern techniques first detecting words and then inputting one word at a time to a model to directly output full words as sequence of characters. This allowed better utilization of language models and bypass error-prone character segmentation step. We observe that the above transition in style has moved the bottleneck "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21693","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/2508.21693/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":"2026-07-05T12:01:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WThzL98URS5MDsPqcI8/NkyMvaw7ToL7pbBGWAoUXeXGl+yF4jb8dgsAliYc8HD1ziLvq8c0ImlIq9igMvkXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:04:43.047556Z"},"content_sha256":"44925b463e6e1091ff7b9398e5d7a0c3b1705037dd54f851ca90201a58cc32bc","schema_version":"1.0","event_id":"sha256:44925b463e6e1091ff7b9398e5d7a0c3b1705037dd54f851ca90201a58cc32bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7I3VEE42S33BLHJ6L7GTAKHSX6/bundle.json","state_url":"https://pith.science/pith/7I3VEE42S33BLHJ6L7GTAKHSX6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7I3VEE42S33BLHJ6L7GTAKHSX6/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":"2026-08-17T06:04:43Z","links":{"resolver":"https://pith.science/pith/7I3VEE42S33BLHJ6L7GTAKHSX6","bundle":"https://pith.science/pith/7I3VEE42S33BLHJ6L7GTAKHSX6/bundle.json","state":"https://pith.science/pith/7I3VEE42S33BLHJ6L7GTAKHSX6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7I3VEE42S33BLHJ6L7GTAKHSX6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7I3VEE42S33BLHJ6L7GTAKHSX6","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":"61402942f7075fcd29407ae79e3c88dc0060ad1388b145ab677809d58b2c4109","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T15:02:11Z","title_canon_sha256":"2b9efc00966f25e38fc4daf27b71834af5ea0e40952c083a27237023fc890b45"},"schema_version":"1.0","source":{"id":"2508.21693","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21693","created_at":"2026-07-05T12:01:48Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21693v1","created_at":"2026-07-05T12:01:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21693","created_at":"2026-07-05T12:01:48Z"},{"alias_kind":"pith_short_12","alias_value":"7I3VEE42S33B","created_at":"2026-07-05T12:01:48Z"},{"alias_kind":"pith_short_16","alias_value":"7I3VEE42S33BLHJ6","created_at":"2026-07-05T12:01:48Z"},{"alias_kind":"pith_short_8","alias_value":"7I3VEE42","created_at":"2026-07-05T12:01:48Z"}],"graph_snapshots":[{"event_id":"sha256:44925b463e6e1091ff7b9398e5d7a0c3b1705037dd54f851ca90201a58cc32bc","target":"graph","created_at":"2026-07-05T12:01:48Z","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/2508.21693/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional optical character recognition (OCR) techniques segmented each character and then recognized. This made them prone to error in character segmentation, and devoid of context to exploit language models. Advances in sequence to sequence translation in last decade led to modern techniques first detecting words and then inputting one word at a time to a model to directly output full words as sequence of characters. This allowed better utilization of language models and bypass error-prone character segmentation step. We observe that the above transition in style has moved the bottleneck ","authors_text":"Arpan Garai, Chetan Arora, Gaurav Talebailkar, Nishit Anand, Shashank Vempati","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T15:02:11Z","title":"Why Stop at Words? Unveiling the Bigger Picture through Line-Level OCR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21693","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:bb3a0aa0a23cd087eb4af93297951310d73fe68e7f0e39fbe0d88174e30bbf5e","target":"record","created_at":"2026-07-05T12:01:48Z","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":"61402942f7075fcd29407ae79e3c88dc0060ad1388b145ab677809d58b2c4109","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T15:02:11Z","title_canon_sha256":"2b9efc00966f25e38fc4daf27b71834af5ea0e40952c083a27237023fc890b45"},"schema_version":"1.0","source":{"id":"2508.21693","kind":"arxiv","version":1}},"canonical_sha256":"fa3752139a96f6159d3e5fcd3028f2bfb9c517e44df8a63fcff629eb86e1da12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa3752139a96f6159d3e5fcd3028f2bfb9c517e44df8a63fcff629eb86e1da12","first_computed_at":"2026-07-05T12:01:48.013706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:48.013706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bbPp0l0/dpkVf3K+JVWqmr5RHszll4dnKrYWdc2RrHiZDM03G7MrezVhg5QZdPegyD1WoJ3h8zXxqY2x5VmTAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:48.014292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21693","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb3a0aa0a23cd087eb4af93297951310d73fe68e7f0e39fbe0d88174e30bbf5e","sha256:44925b463e6e1091ff7b9398e5d7a0c3b1705037dd54f851ca90201a58cc32bc"],"state_sha256":"56784dfd45da43cd5d7fa224bf7368e62f8cb27fa267570a761209bf694175ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SwoCAnFtD18uSPj73u7XM4zGTwBr5tm5lLNKN9woOuUBXFoy1WSwjmMj0frrgCf4JGRZueGdns99swZbKmfNCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T06:04:43.051972Z","bundle_sha256":"c0f75f3c54d646ba87442646f6d83bb6c3a3efee963f672d637c30e67c42e2a4"}}