{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:33J73CQPRBKOS7ONU6OVQ6AU26","short_pith_number":"pith:33J73CQP","canonical_record":{"source":{"id":"1811.11239","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T20:23:02Z","cross_cats_sorted":[],"title_canon_sha256":"e2549e8cfb138411c7133f33c7917083f2c304999a26e8bce1ca99349fda2d7a","abstract_canon_sha256":"ef78fe0b8fd3181ecc0eaa8b10e62b8db9a28273c4b88da233b0c735c405183d"},"schema_version":"1.0"},"canonical_sha256":"ded3fd8a0f8854e97dcda79d587814d7806b5f2da809de05acb2431cadf1f4f6","source":{"kind":"arxiv","id":"1811.11239","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.11239","created_at":"2026-05-17T23:59:44Z"},{"alias_kind":"arxiv_version","alias_value":"1811.11239v1","created_at":"2026-05-17T23:59:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11239","created_at":"2026-05-17T23:59:44Z"},{"alias_kind":"pith_short_12","alias_value":"33J73CQPRBKO","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"33J73CQPRBKOS7ON","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"33J73CQP","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:33J73CQPRBKOS7ONU6OVQ6AU26","target":"record","payload":{"canonical_record":{"source":{"id":"1811.11239","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T20:23:02Z","cross_cats_sorted":[],"title_canon_sha256":"e2549e8cfb138411c7133f33c7917083f2c304999a26e8bce1ca99349fda2d7a","abstract_canon_sha256":"ef78fe0b8fd3181ecc0eaa8b10e62b8db9a28273c4b88da233b0c735c405183d"},"schema_version":"1.0"},"canonical_sha256":"ded3fd8a0f8854e97dcda79d587814d7806b5f2da809de05acb2431cadf1f4f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:44.394122Z","signature_b64":"ElYi8cR6kWHXjD78FkwC64n7CmA18FuMjlvrzIB3Ryqg28T9wdLM//uqHqpm3yHmXXB/yIKYULz5CPeRU0OYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ded3fd8a0f8854e97dcda79d587814d7806b5f2da809de05acb2431cadf1f4f6","last_reissued_at":"2026-05-17T23:59:44.393507Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:44.393507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.11239","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":"2026-05-17T23:59:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ReLi1ci+Y+uDTtOI/zw3THp+6/ZKfgE55LsPMNa/puHAO9Uz+6zi8t/x5k1l6h0K6qFiuYrR62f1PMWzWSVCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:43:25.468634Z"},"content_sha256":"038638f0736a3f5a92f66d763d5b98c589eb623b17dcc79750fc0a593b2cbf3a","schema_version":"1.0","event_id":"sha256:038638f0736a3f5a92f66d763d5b98c589eb623b17dcc79750fc0a593b2cbf3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:33J73CQPRBKOS7ONU6OVQ6AU26","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Compositional Textual Model for Recognition of Imperfect Word Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Hua, John Corring, Wei Tang, Ying Wu","submitted_at":"2018-11-27T20:23:02Z","abstract_excerpt":"Printed text recognition is an important problem for industrial OCR systems. Printed text is constructed in a standard procedural fashion in most settings. We develop a mathematical model for this process that can be applied to the backward inference problem of text recognition from an image. Through ablation experiments we show that this model is realistic and that a multi-task objective setting can help to stabilize estimation of its free parameters, enabling use of conventional deep learning methods. Furthermore, by directly modeling the geometric perturbations of text synthesis we show tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11239","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":"2026-05-17T23:59:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xuiYwZCVJ4KFpOC2/tievTPsTPL+/mAmypnqF8reqhZhIL0cKBCdAAuq7bcPpo+xN0J/5WnyTmWSMWMNo/jIDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:43:25.469282Z"},"content_sha256":"37e9e0e6915fe420ce0ce74833cf2f1cb7fb88b822d1b57bf9eacadc89874797","schema_version":"1.0","event_id":"sha256:37e9e0e6915fe420ce0ce74833cf2f1cb7fb88b822d1b57bf9eacadc89874797"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/33J73CQPRBKOS7ONU6OVQ6AU26/bundle.json","state_url":"https://pith.science/pith/33J73CQPRBKOS7ONU6OVQ6AU26/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/33J73CQPRBKOS7ONU6OVQ6AU26/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":"2026-05-27T19:43:25Z","links":{"resolver":"https://pith.science/pith/33J73CQPRBKOS7ONU6OVQ6AU26","bundle":"https://pith.science/pith/33J73CQPRBKOS7ONU6OVQ6AU26/bundle.json","state":"https://pith.science/pith/33J73CQPRBKOS7ONU6OVQ6AU26/state.json","well_known_bundle":"https://pith.science/.well-known/pith/33J73CQPRBKOS7ONU6OVQ6AU26/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:33J73CQPRBKOS7ONU6OVQ6AU26","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":"ef78fe0b8fd3181ecc0eaa8b10e62b8db9a28273c4b88da233b0c735c405183d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T20:23:02Z","title_canon_sha256":"e2549e8cfb138411c7133f33c7917083f2c304999a26e8bce1ca99349fda2d7a"},"schema_version":"1.0","source":{"id":"1811.11239","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.11239","created_at":"2026-05-17T23:59:44Z"},{"alias_kind":"arxiv_version","alias_value":"1811.11239v1","created_at":"2026-05-17T23:59:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11239","created_at":"2026-05-17T23:59:44Z"},{"alias_kind":"pith_short_12","alias_value":"33J73CQPRBKO","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"33J73CQPRBKOS7ON","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"33J73CQP","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:37e9e0e6915fe420ce0ce74833cf2f1cb7fb88b822d1b57bf9eacadc89874797","target":"graph","created_at":"2026-05-17T23:59:44Z","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":"Printed text recognition is an important problem for industrial OCR systems. Printed text is constructed in a standard procedural fashion in most settings. We develop a mathematical model for this process that can be applied to the backward inference problem of text recognition from an image. Through ablation experiments we show that this model is realistic and that a multi-task objective setting can help to stabilize estimation of its free parameters, enabling use of conventional deep learning methods. Furthermore, by directly modeling the geometric perturbations of text synthesis we show tha","authors_text":"Gang Hua, John Corring, Wei Tang, Ying Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T20:23:02Z","title":"A Compositional Textual Model for Recognition of Imperfect Word Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11239","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":"sha256:038638f0736a3f5a92f66d763d5b98c589eb623b17dcc79750fc0a593b2cbf3a","target":"record","created_at":"2026-05-17T23:59:44Z","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":"ef78fe0b8fd3181ecc0eaa8b10e62b8db9a28273c4b88da233b0c735c405183d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T20:23:02Z","title_canon_sha256":"e2549e8cfb138411c7133f33c7917083f2c304999a26e8bce1ca99349fda2d7a"},"schema_version":"1.0","source":{"id":"1811.11239","kind":"arxiv","version":1}},"canonical_sha256":"ded3fd8a0f8854e97dcda79d587814d7806b5f2da809de05acb2431cadf1f4f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ded3fd8a0f8854e97dcda79d587814d7806b5f2da809de05acb2431cadf1f4f6","first_computed_at":"2026-05-17T23:59:44.393507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:44.393507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ElYi8cR6kWHXjD78FkwC64n7CmA18FuMjlvrzIB3Ryqg28T9wdLM//uqHqpm3yHmXXB/yIKYULz5CPeRU0OYCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:44.394122Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.11239","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:038638f0736a3f5a92f66d763d5b98c589eb623b17dcc79750fc0a593b2cbf3a","sha256:37e9e0e6915fe420ce0ce74833cf2f1cb7fb88b822d1b57bf9eacadc89874797"],"state_sha256":"6b881c6e16dc1bf059893c7b20232521a5708e299e71aeca8e1aac0548b29c74"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F94mUvRH86fUuMAfBC9YV9uZ3wL5BSZpwYD5FAsuO3L4PitIWIzUGH3fkLGT4c0at09OzBhq/Llbon4yA2lrCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T19:43:25.472678Z","bundle_sha256":"8d6e5306d5c49b623c3963cb62e4edd5e53c10da4c139f9824871a99858c5853"}}