{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:NTC5DP7QT3ZTNMRV7G2H2ICHRK","short_pith_number":"pith:NTC5DP7Q","schema_version":"1.0","canonical_sha256":"6cc5d1bff09ef336b235f9b47d20478abaa1e588681c0fac77b8e8ab67751366","source":{"kind":"arxiv","id":"1412.5903","version":5},"attestation_state":"computed","paper":{"title":"Deep Structured Output Learning for Unconstrained Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Karen Simonyan, Max Jaderberg","submitted_at":"2014-12-18T15:49:46Z","abstract_excerpt":"We develop a representation suitable for the unconstrained recognition of words in natural images: the general case of no fixed lexicon and unknown length.\n  To this end we propose a convolutional neural network (CNN) based architecture which incorporates a Conditional Random Field (CRF) graphical model, taking the whole word image as a single input. The unaries of the CRF are provided by a CNN that predicts characters at each position of the output, while higher order terms are provided by another CNN that detects the presence of N-grams. We show that this entire model (CRF, character predict"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1412.5903","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-18T15:49:46Z","cross_cats_sorted":[],"title_canon_sha256":"7fae54224d32bfa3cb1a68553a00516fd5d2744306dd18e8df58d5c034a6de7b","abstract_canon_sha256":"56569c91ce1a42395acd32f2e38b747a9aef541a0604fc63295353f3fbcad11e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:07.986892Z","signature_b64":"Jp21ImN+c6M5lNtrdBe5ljxk1+LaS3JoU7/vdfHbQawfWFZqWPnyJFNgaCO+jTTTxEAFnEjXfGGEqPRWPCirBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cc5d1bff09ef336b235f9b47d20478abaa1e588681c0fac77b8e8ab67751366","last_reissued_at":"2026-05-18T02:19:07.986412Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:07.986412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Structured Output Learning for Unconstrained Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Karen Simonyan, Max Jaderberg","submitted_at":"2014-12-18T15:49:46Z","abstract_excerpt":"We develop a representation suitable for the unconstrained recognition of words in natural images: the general case of no fixed lexicon and unknown length.\n  To this end we propose a convolutional neural network (CNN) based architecture which incorporates a Conditional Random Field (CRF) graphical model, taking the whole word image as a single input. The unaries of the CRF are provided by a CNN that predicts characters at each position of the output, while higher order terms are provided by another CNN that detects the presence of N-grams. We show that this entire model (CRF, character predict"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.5903","kind":"arxiv","version":5},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1412.5903","created_at":"2026-05-18T02:19:07.986482+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.5903v5","created_at":"2026-05-18T02:19:07.986482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.5903","created_at":"2026-05-18T02:19:07.986482+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTC5DP7QT3ZT","created_at":"2026-05-18T12:28:41.024544+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTC5DP7QT3ZTNMRV","created_at":"2026-05-18T12:28:41.024544+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTC5DP7Q","created_at":"2026-05-18T12:28:41.024544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.09705","citing_title":"2D-CTC for Scene Text Recognition","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK","json":"https://pith.science/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK.json","graph_json":"https://pith.science/api/pith-number/NTC5DP7QT3ZTNMRV7G2H2ICHRK/graph.json","events_json":"https://pith.science/api/pith-number/NTC5DP7QT3ZTNMRV7G2H2ICHRK/events.json","paper":"https://pith.science/paper/NTC5DP7Q"},"agent_actions":{"view_html":"https://pith.science/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK","download_json":"https://pith.science/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK.json","view_paper":"https://pith.science/paper/NTC5DP7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.5903&json=true","fetch_graph":"https://pith.science/api/pith-number/NTC5DP7QT3ZTNMRV7G2H2ICHRK/graph.json","fetch_events":"https://pith.science/api/pith-number/NTC5DP7QT3ZTNMRV7G2H2ICHRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK/action/storage_attestation","attest_author":"https://pith.science/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK/action/author_attestation","sign_citation":"https://pith.science/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK/action/citation_signature","submit_replication":"https://pith.science/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK/action/replication_record"}},"created_at":"2026-05-18T02:19:07.986482+00:00","updated_at":"2026-05-18T02:19:07.986482+00:00"}