{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:MAQ4BVRK4FK5TZPBAQJA43CTBQ","short_pith_number":"pith:MAQ4BVRK","schema_version":"1.0","canonical_sha256":"6021c0d62ae155d9e5e104120e6c530c38bd5c8b7b6712e23084668e6d13be54","source":{"kind":"arxiv","id":"1708.04671","version":2},"attestation_state":"computed","paper":{"title":"Sequence-to-Label Script Identification for Multilingual OCR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ash Hurst, Ashok C. Popat, Jonathan Baccash, Karel Driesen, Yasuhisa Fujii","submitted_at":"2017-08-15T20:14:51Z","abstract_excerpt":"We describe a novel line-level script identification method. Previous work repurposed an OCR model generating per-character script codes, counted to obtain line-level script identification. This has two shortcomings. First, as a sequence-to-sequence model it is more complex than necessary for the sequence-to-label problem of line script identification. This makes it harder to train and inefficient to run. Second, the counting heuristic may be suboptimal compared to a learned model. Therefore we reframe line script identification as a sequence-to-label problem and solve it using two components,"},"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":"1708.04671","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-15T20:14:51Z","cross_cats_sorted":[],"title_canon_sha256":"7af2a15cdc742f840b57901563bf0cf1286ee18321aed2c303ab4df8a32ff495","abstract_canon_sha256":"392a34011687b41779f0e3bc5cb9a8cf6ccfb4cd4582c233fcdfa1b4a675a46c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:50.262971Z","signature_b64":"U3pHR67pzOUs21S8Xnk06yZFd71dazAAL5LdaOmuoFKDaXJ4z1L5lhat8Fyfl4KLo6ev1lHKBTQeeiULt5FFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6021c0d62ae155d9e5e104120e6c530c38bd5c8b7b6712e23084668e6d13be54","last_reissued_at":"2026-05-18T00:37:50.262382Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:50.262382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequence-to-Label Script Identification for Multilingual OCR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ash Hurst, Ashok C. Popat, Jonathan Baccash, Karel Driesen, Yasuhisa Fujii","submitted_at":"2017-08-15T20:14:51Z","abstract_excerpt":"We describe a novel line-level script identification method. Previous work repurposed an OCR model generating per-character script codes, counted to obtain line-level script identification. This has two shortcomings. First, as a sequence-to-sequence model it is more complex than necessary for the sequence-to-label problem of line script identification. This makes it harder to train and inefficient to run. Second, the counting heuristic may be suboptimal compared to a learned model. Therefore we reframe line script identification as a sequence-to-label problem and solve it using two components,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.04671","kind":"arxiv","version":2},"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":"1708.04671","created_at":"2026-05-18T00:37:50.262480+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.04671v2","created_at":"2026-05-18T00:37:50.262480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04671","created_at":"2026-05-18T00:37:50.262480+00:00"},{"alias_kind":"pith_short_12","alias_value":"MAQ4BVRK4FK5","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"MAQ4BVRK4FK5TZPB","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"MAQ4BVRK","created_at":"2026-05-18T12:31:31.346846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ","json":"https://pith.science/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ.json","graph_json":"https://pith.science/api/pith-number/MAQ4BVRK4FK5TZPBAQJA43CTBQ/graph.json","events_json":"https://pith.science/api/pith-number/MAQ4BVRK4FK5TZPBAQJA43CTBQ/events.json","paper":"https://pith.science/paper/MAQ4BVRK"},"agent_actions":{"view_html":"https://pith.science/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ","download_json":"https://pith.science/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ.json","view_paper":"https://pith.science/paper/MAQ4BVRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.04671&json=true","fetch_graph":"https://pith.science/api/pith-number/MAQ4BVRK4FK5TZPBAQJA43CTBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/MAQ4BVRK4FK5TZPBAQJA43CTBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ/action/storage_attestation","attest_author":"https://pith.science/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ/action/author_attestation","sign_citation":"https://pith.science/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ/action/citation_signature","submit_replication":"https://pith.science/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ/action/replication_record"}},"created_at":"2026-05-18T00:37:50.262480+00:00","updated_at":"2026-05-18T00:37:50.262480+00:00"}