{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TMV4GJT37XSHT33D4UEGESPAI2","short_pith_number":"pith:TMV4GJT3","canonical_record":{"source":{"id":"1805.03384","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-05-09T06:14:51Z","cross_cats_sorted":[],"title_canon_sha256":"d84303113ea7235499d28edbef8f3dea7fefb46f700c852e578cdd18d82539bd","abstract_canon_sha256":"714bec1883096220dfe517b497d12e21fc05e5d98d73db3016ffcbcfb1e070ee"},"schema_version":"1.0"},"canonical_sha256":"9b2bc3267bfde479ef63e5086249e0468347d17560152919ce4e8ede64c867be","source":{"kind":"arxiv","id":"1805.03384","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03384","created_at":"2026-05-18T00:16:20Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03384v1","created_at":"2026-05-18T00:16:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03384","created_at":"2026-05-18T00:16:20Z"},{"alias_kind":"pith_short_12","alias_value":"TMV4GJT37XSH","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"TMV4GJT37XSHT33D","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"TMV4GJT3","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TMV4GJT37XSHT33D4UEGESPAI2","target":"record","payload":{"canonical_record":{"source":{"id":"1805.03384","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-05-09T06:14:51Z","cross_cats_sorted":[],"title_canon_sha256":"d84303113ea7235499d28edbef8f3dea7fefb46f700c852e578cdd18d82539bd","abstract_canon_sha256":"714bec1883096220dfe517b497d12e21fc05e5d98d73db3016ffcbcfb1e070ee"},"schema_version":"1.0"},"canonical_sha256":"9b2bc3267bfde479ef63e5086249e0468347d17560152919ce4e8ede64c867be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:20.359612Z","signature_b64":"Ej+wnnb4m2qCR2A0x/UlvlrjplPD10XHiHap/jDJBPEYglgtRwEOsZ22vwmjgDOXRJ5de3t7TINtZUPFhkV7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b2bc3267bfde479ef63e5086249e0468347d17560152919ce4e8ede64c867be","last_reissued_at":"2026-05-18T00:16:20.359182Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:20.359182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.03384","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":"2026-05-18T00:16:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+xLwloTLjXa6V6J+PnnU3a3i7ath3TIKMdI9o4zHUEbWL5OqxiWeN/AzfZmDZBX6HK1KZEkgYt4TNfUY4pckBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T13:41:40.761261Z"},"content_sha256":"dbc53310e8045c8bdf9e468410fd3dcb51686d7a556ac2988ad458063fd09978","schema_version":"1.0","event_id":"sha256:dbc53310e8045c8bdf9e468410fd3dcb51686d7a556ac2988ad458063fd09978"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TMV4GJT37XSHT33D4UEGESPAI2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Edit Probability for Scene Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Bai, Shiliang Pu, Shuigeng Zhou, Yi Niu, Zhanzhan Cheng","submitted_at":"2018-05-09T06:14:51Z","abstract_excerpt":"We consider the scene text recognition problem under the attention-based encoder-decoder framework, which is the state of the art. The existing methods usually employ a frame-wise maximal likelihood loss to optimize the models. When we train the model, the misalignment between the ground truth strings and the attention's output sequences of probability distribution, which is caused by missing or superfluous characters, will confuse and mislead the training process, and consequently make the training costly and degrade the recognition accuracy. To handle this problem, we propose a novel method "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03384","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":""},"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":"2026-05-18T00:16:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tXJFoiVmTK3B6BTFqarDRzB+RpYqW/SPf2NODAAUiaaam46HffEeg37Zd3lmi748eH3S8HGgirMn2bZA9l35Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T13:41:40.761619Z"},"content_sha256":"c8eb9ad2aa9bf8d32c76762f245ff41870ec12494fc713985cca6a45f0caa647","schema_version":"1.0","event_id":"sha256:c8eb9ad2aa9bf8d32c76762f245ff41870ec12494fc713985cca6a45f0caa647"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TMV4GJT37XSHT33D4UEGESPAI2/bundle.json","state_url":"https://pith.science/pith/TMV4GJT37XSHT33D4UEGESPAI2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TMV4GJT37XSHT33D4UEGESPAI2/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":"2026-06-01T13:41:40Z","links":{"resolver":"https://pith.science/pith/TMV4GJT37XSHT33D4UEGESPAI2","bundle":"https://pith.science/pith/TMV4GJT37XSHT33D4UEGESPAI2/bundle.json","state":"https://pith.science/pith/TMV4GJT37XSHT33D4UEGESPAI2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TMV4GJT37XSHT33D4UEGESPAI2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TMV4GJT37XSHT33D4UEGESPAI2","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":"714bec1883096220dfe517b497d12e21fc05e5d98d73db3016ffcbcfb1e070ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-05-09T06:14:51Z","title_canon_sha256":"d84303113ea7235499d28edbef8f3dea7fefb46f700c852e578cdd18d82539bd"},"schema_version":"1.0","source":{"id":"1805.03384","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03384","created_at":"2026-05-18T00:16:20Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03384v1","created_at":"2026-05-18T00:16:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03384","created_at":"2026-05-18T00:16:20Z"},{"alias_kind":"pith_short_12","alias_value":"TMV4GJT37XSH","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"TMV4GJT37XSHT33D","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"TMV4GJT3","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:c8eb9ad2aa9bf8d32c76762f245ff41870ec12494fc713985cca6a45f0caa647","target":"graph","created_at":"2026-05-18T00:16:20Z","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"},"paper":{"abstract_excerpt":"We consider the scene text recognition problem under the attention-based encoder-decoder framework, which is the state of the art. The existing methods usually employ a frame-wise maximal likelihood loss to optimize the models. When we train the model, the misalignment between the ground truth strings and the attention's output sequences of probability distribution, which is caused by missing or superfluous characters, will confuse and mislead the training process, and consequently make the training costly and degrade the recognition accuracy. To handle this problem, we propose a novel method ","authors_text":"Fan Bai, Shiliang Pu, Shuigeng Zhou, Yi Niu, Zhanzhan Cheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-05-09T06:14:51Z","title":"Edit Probability for Scene Text Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03384","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:dbc53310e8045c8bdf9e468410fd3dcb51686d7a556ac2988ad458063fd09978","target":"record","created_at":"2026-05-18T00:16:20Z","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":"714bec1883096220dfe517b497d12e21fc05e5d98d73db3016ffcbcfb1e070ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-05-09T06:14:51Z","title_canon_sha256":"d84303113ea7235499d28edbef8f3dea7fefb46f700c852e578cdd18d82539bd"},"schema_version":"1.0","source":{"id":"1805.03384","kind":"arxiv","version":1}},"canonical_sha256":"9b2bc3267bfde479ef63e5086249e0468347d17560152919ce4e8ede64c867be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b2bc3267bfde479ef63e5086249e0468347d17560152919ce4e8ede64c867be","first_computed_at":"2026-05-18T00:16:20.359182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:20.359182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ej+wnnb4m2qCR2A0x/UlvlrjplPD10XHiHap/jDJBPEYglgtRwEOsZ22vwmjgDOXRJ5de3t7TINtZUPFhkV7Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:20.359612Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.03384","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbc53310e8045c8bdf9e468410fd3dcb51686d7a556ac2988ad458063fd09978","sha256:c8eb9ad2aa9bf8d32c76762f245ff41870ec12494fc713985cca6a45f0caa647"],"state_sha256":"7827c650aeee93d4ef5d6ef53db0b9e63813609ab93fcd64f83a3faf1bce8977"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dw4TbF3SybuPDDRlRRJfyl9L/iJ1G7CgyqUKw+ikIa/KY3fOgnhdyqw6sqksYmtCYGQ6PitISS83c3jx32EVAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T13:41:40.763562Z","bundle_sha256":"28c514ec4735d45cc4cc76b9e110a27ce5a225f2b871e9d263b459bc2dc79f6b"}}