{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EBC2K224RPDPZ2ICZ3CGNWF4RU","short_pith_number":"pith:EBC2K224","schema_version":"1.0","canonical_sha256":"2045a56b5c8bc6fce902cec466d8bc8d06a6ccc5bdfc2f0a194b7c75f2a8aee0","source":{"kind":"arxiv","id":"2508.01153","version":1},"attestation_state":"computed","paper":{"title":"TEACH: Text Encoding as Curriculum Hints for Scene Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hui Zheng, Xiahan Yang","submitted_at":"2025-08-02T02:28:09Z","abstract_excerpt":"Scene Text Recognition (STR) remains a challenging task due to complex visual appearances and limited semantic priors. We propose TEACH, a novel training paradigm that injects ground-truth text into the model as auxiliary input and progressively reduces its influence during training. By encoding target labels into the embedding space and applying loss-aware masking, TEACH simulates a curriculum learning process that guides the model from label-dependent learning to fully visual recognition. Unlike language model-based approaches, TEACH requires no external pretraining and introduces no inferen"},"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":"2508.01153","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-02T02:28:09Z","cross_cats_sorted":[],"title_canon_sha256":"fdf1118e583552152d6b163af8ad2f044924663766a51296a5987d4e59e7896f","abstract_canon_sha256":"1a00c48b0c76ef67b6fd9c287e381b4e11f6207c6deaca1e0bba048236c5298c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:33.986854Z","signature_b64":"Wl+71oqEJPq6IT87iH3CHzFcv2K8c9tnxzqRsSo/krRTD2l7go4wGrg/6hSZCunl9S3bgChE8w5SGIggyNgYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2045a56b5c8bc6fce902cec466d8bc8d06a6ccc5bdfc2f0a194b7c75f2a8aee0","last_reissued_at":"2026-07-05T11:47:33.986403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:33.986403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TEACH: Text Encoding as Curriculum Hints for Scene Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hui Zheng, Xiahan Yang","submitted_at":"2025-08-02T02:28:09Z","abstract_excerpt":"Scene Text Recognition (STR) remains a challenging task due to complex visual appearances and limited semantic priors. We propose TEACH, a novel training paradigm that injects ground-truth text into the model as auxiliary input and progressively reduces its influence during training. By encoding target labels into the embedding space and applying loss-aware masking, TEACH simulates a curriculum learning process that guides the model from label-dependent learning to fully visual recognition. Unlike language model-based approaches, TEACH requires no external pretraining and introduces no inferen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01153","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/2508.01153/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":"2508.01153","created_at":"2026-07-05T11:47:33.986466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01153v1","created_at":"2026-07-05T11:47:33.986466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01153","created_at":"2026-07-05T11:47:33.986466+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBC2K224RPDP","created_at":"2026-07-05T11:47:33.986466+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBC2K224RPDPZ2IC","created_at":"2026-07-05T11:47:33.986466+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBC2K224","created_at":"2026-07-05T11:47:33.986466+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01153","citing_title":"TEACH: Text Encoding as Curriculum Hints for Scene Text Recognition","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EBC2K224RPDPZ2ICZ3CGNWF4RU","json":"https://pith.science/pith/EBC2K224RPDPZ2ICZ3CGNWF4RU.json","graph_json":"https://pith.science/api/pith-number/EBC2K224RPDPZ2ICZ3CGNWF4RU/graph.json","events_json":"https://pith.science/api/pith-number/EBC2K224RPDPZ2ICZ3CGNWF4RU/events.json","paper":"https://pith.science/paper/EBC2K224"},"agent_actions":{"view_html":"https://pith.science/pith/EBC2K224RPDPZ2ICZ3CGNWF4RU","download_json":"https://pith.science/pith/EBC2K224RPDPZ2ICZ3CGNWF4RU.json","view_paper":"https://pith.science/paper/EBC2K224","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01153&json=true","fetch_graph":"https://pith.science/api/pith-number/EBC2K224RPDPZ2ICZ3CGNWF4RU/graph.json","fetch_events":"https://pith.science/api/pith-number/EBC2K224RPDPZ2ICZ3CGNWF4RU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBC2K224RPDPZ2ICZ3CGNWF4RU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBC2K224RPDPZ2ICZ3CGNWF4RU/action/storage_attestation","attest_author":"https://pith.science/pith/EBC2K224RPDPZ2ICZ3CGNWF4RU/action/author_attestation","sign_citation":"https://pith.science/pith/EBC2K224RPDPZ2ICZ3CGNWF4RU/action/citation_signature","submit_replication":"https://pith.science/pith/EBC2K224RPDPZ2ICZ3CGNWF4RU/action/replication_record"}},"created_at":"2026-07-05T11:47:33.986466+00:00","updated_at":"2026-07-05T11:47:33.986466+00:00"}