{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:MAQ4BVRK4FK5TZPBAQJA43CTBQ","short_pith_number":"pith:MAQ4BVRK","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"},"canonical_sha256":"6021c0d62ae155d9e5e104120e6c530c38bd5c8b7b6712e23084668e6d13be54","source":{"kind":"arxiv","id":"1708.04671","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.04671","created_at":"2026-05-18T00:37:50Z"},{"alias_kind":"arxiv_version","alias_value":"1708.04671v2","created_at":"2026-05-18T00:37:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04671","created_at":"2026-05-18T00:37:50Z"},{"alias_kind":"pith_short_12","alias_value":"MAQ4BVRK4FK5","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MAQ4BVRK4FK5TZPB","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MAQ4BVRK","created_at":"2026-05-18T12:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:MAQ4BVRK4FK5TZPBAQJA43CTBQ","target":"record","payload":{"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"},"canonical_sha256":"6021c0d62ae155d9e5e104120e6c530c38bd5c8b7b6712e23084668e6d13be54","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"},"source_kind":"arxiv","source_id":"1708.04671","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:37:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bk2a3R1yapgA0fODI0zN5IWHXz8GqTx+gdUlLsaH2HsWxZnZul0V0Ib43eJL/n90+hca7yG0z4YoUpl3wfDXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:19:36.950778Z"},"content_sha256":"091cae2df0c7eb948ef7f168dd5a8a85da5c3d2b006770dd83bdde9beb0b6d15","schema_version":"1.0","event_id":"sha256:091cae2df0c7eb948ef7f168dd5a8a85da5c3d2b006770dd83bdde9beb0b6d15"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:MAQ4BVRK4FK5TZPBAQJA43CTBQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:37:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UKge55EvQINtbwcTeP8oVV+NCN3WpZ36TygIBvlYCgo1dq7ebRjgk9kMf+YjF7fcgex+wlGWeRk2WpQHw7p/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:19:36.951450Z"},"content_sha256":"bb4a995def8bdfac6528e3307521ed359bd43af8d9b73580cfca1a98a08dcd3c","schema_version":"1.0","event_id":"sha256:bb4a995def8bdfac6528e3307521ed359bd43af8d9b73580cfca1a98a08dcd3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ/bundle.json","state_url":"https://pith.science/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ/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":"2026-05-26T02:19:36Z","links":{"resolver":"https://pith.science/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ","bundle":"https://pith.science/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ/bundle.json","state":"https://pith.science/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MAQ4BVRK4FK5TZPBAQJA43CTBQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:MAQ4BVRK4FK5TZPBAQJA43CTBQ","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":"392a34011687b41779f0e3bc5cb9a8cf6ccfb4cd4582c233fcdfa1b4a675a46c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-15T20:14:51Z","title_canon_sha256":"7af2a15cdc742f840b57901563bf0cf1286ee18321aed2c303ab4df8a32ff495"},"schema_version":"1.0","source":{"id":"1708.04671","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.04671","created_at":"2026-05-18T00:37:50Z"},{"alias_kind":"arxiv_version","alias_value":"1708.04671v2","created_at":"2026-05-18T00:37:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04671","created_at":"2026-05-18T00:37:50Z"},{"alias_kind":"pith_short_12","alias_value":"MAQ4BVRK4FK5","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MAQ4BVRK4FK5TZPB","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MAQ4BVRK","created_at":"2026-05-18T12:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:bb4a995def8bdfac6528e3307521ed359bd43af8d9b73580cfca1a98a08dcd3c","target":"graph","created_at":"2026-05-18T00:37:50Z","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 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,","authors_text":"Ash Hurst, Ashok C. Popat, Jonathan Baccash, Karel Driesen, Yasuhisa Fujii","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-15T20:14:51Z","title":"Sequence-to-Label Script Identification for Multilingual OCR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.04671","kind":"arxiv","version":2},"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":"sha256:091cae2df0c7eb948ef7f168dd5a8a85da5c3d2b006770dd83bdde9beb0b6d15","target":"record","created_at":"2026-05-18T00:37:50Z","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":"392a34011687b41779f0e3bc5cb9a8cf6ccfb4cd4582c233fcdfa1b4a675a46c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-15T20:14:51Z","title_canon_sha256":"7af2a15cdc742f840b57901563bf0cf1286ee18321aed2c303ab4df8a32ff495"},"schema_version":"1.0","source":{"id":"1708.04671","kind":"arxiv","version":2}},"canonical_sha256":"6021c0d62ae155d9e5e104120e6c530c38bd5c8b7b6712e23084668e6d13be54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6021c0d62ae155d9e5e104120e6c530c38bd5c8b7b6712e23084668e6d13be54","first_computed_at":"2026-05-18T00:37:50.262382Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:37:50.262382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U3pHR67pzOUs21S8Xnk06yZFd71dazAAL5LdaOmuoFKDaXJ4z1L5lhat8Fyfl4KLo6ev1lHKBTQeeiULt5FFCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:37:50.262971Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.04671","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:091cae2df0c7eb948ef7f168dd5a8a85da5c3d2b006770dd83bdde9beb0b6d15","sha256:bb4a995def8bdfac6528e3307521ed359bd43af8d9b73580cfca1a98a08dcd3c"],"state_sha256":"642757e69495ead085f1a88718c2bcaf125e059d3614a5cc70d3a6b12c92fef2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"odz4Hx15oGMpeBY3DNs9GNgZEl/Hu1yKypd/RN6KmVP7Sl21qgfTumUUHYJJvJYn6ZvV5XE5nsCGnyvU6BhdAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T02:19:36.954428Z","bundle_sha256":"cbe675093dde89c54f106afb706fc34b0942427126dd32c175499828c506084e"}}