{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GJTMD5TVDRURR67ET2GQFFYIQU","short_pith_number":"pith:GJTMD5TV","schema_version":"1.0","canonical_sha256":"3266c1f6751c6918fbe49e8d0297088501e369aa49203288c3df0958bf2002e8","source":{"kind":"arxiv","id":"2205.03873","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Semi-Supervised Learning for Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aviad Aberdam, Ron Litman, Roy Ganz, Shai Mazor","submitted_at":"2022-05-08T13:55:30Z","abstract_excerpt":"Until recently, the number of public real-world text images was insufficient for training scene text recognizers. Therefore, most modern training methods rely on synthetic data and operate in a fully supervised manner. Nevertheless, the amount of public real-world text images has increased significantly lately, including a great deal of unlabeled data. Leveraging these resources requires semi-supervised approaches; however, the few existing methods do not account for vision-language multimodality structure and therefore suboptimal for state-of-the-art multimodal architectures. To bridge this g"},"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":"2205.03873","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-08T13:55:30Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"402f345fa36fc19585ff38cb45a722649e6d7b703a8b223a1ab554ab0d2309c4","abstract_canon_sha256":"ddeb28a1090c0ba38a42b00743f73fdf5bfca3596e875bda5e8cf955477f3003"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:19.371715Z","signature_b64":"11A83T+3bosIQasw1Fa9RJGRX/XB/OPL9lO3ncOrDqzsWiz4/jZachVNr004tsfZwQekYw3koQxAEovoCcS9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3266c1f6751c6918fbe49e8d0297088501e369aa49203288c3df0958bf2002e8","last_reissued_at":"2026-07-05T04:21:19.371252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:19.371252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Semi-Supervised Learning for Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aviad Aberdam, Ron Litman, Roy Ganz, Shai Mazor","submitted_at":"2022-05-08T13:55:30Z","abstract_excerpt":"Until recently, the number of public real-world text images was insufficient for training scene text recognizers. Therefore, most modern training methods rely on synthetic data and operate in a fully supervised manner. Nevertheless, the amount of public real-world text images has increased significantly lately, including a great deal of unlabeled data. Leveraging these resources requires semi-supervised approaches; however, the few existing methods do not account for vision-language multimodality structure and therefore suboptimal for state-of-the-art multimodal architectures. To bridge this g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03873","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.03873/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2205.03873","created_at":"2026-07-05T04:21:19.371307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.03873v1","created_at":"2026-07-05T04:21:19.371307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03873","created_at":"2026-07-05T04:21:19.371307+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJTMD5TVDRUR","created_at":"2026-07-05T04:21:19.371307+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJTMD5TVDRURR67E","created_at":"2026-07-05T04:21:19.371307+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJTMD5TV","created_at":"2026-07-05T04:21:19.371307+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08746","citing_title":"DocVLM: Make Your VLM an Efficient Reader","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJTMD5TVDRURR67ET2GQFFYIQU","json":"https://pith.science/pith/GJTMD5TVDRURR67ET2GQFFYIQU.json","graph_json":"https://pith.science/api/pith-number/GJTMD5TVDRURR67ET2GQFFYIQU/graph.json","events_json":"https://pith.science/api/pith-number/GJTMD5TVDRURR67ET2GQFFYIQU/events.json","paper":"https://pith.science/paper/GJTMD5TV"},"agent_actions":{"view_html":"https://pith.science/pith/GJTMD5TVDRURR67ET2GQFFYIQU","download_json":"https://pith.science/pith/GJTMD5TVDRURR67ET2GQFFYIQU.json","view_paper":"https://pith.science/paper/GJTMD5TV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.03873&json=true","fetch_graph":"https://pith.science/api/pith-number/GJTMD5TVDRURR67ET2GQFFYIQU/graph.json","fetch_events":"https://pith.science/api/pith-number/GJTMD5TVDRURR67ET2GQFFYIQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJTMD5TVDRURR67ET2GQFFYIQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJTMD5TVDRURR67ET2GQFFYIQU/action/storage_attestation","attest_author":"https://pith.science/pith/GJTMD5TVDRURR67ET2GQFFYIQU/action/author_attestation","sign_citation":"https://pith.science/pith/GJTMD5TVDRURR67ET2GQFFYIQU/action/citation_signature","submit_replication":"https://pith.science/pith/GJTMD5TVDRURR67ET2GQFFYIQU/action/replication_record"}},"created_at":"2026-07-05T04:21:19.371307+00:00","updated_at":"2026-07-05T04:21:19.371307+00:00"}