{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NEXYKBPWA46HYUPC54PSJQ4RNO","short_pith_number":"pith:NEXYKBPW","schema_version":"1.0","canonical_sha256":"692f8505f6073c7c51e2ef1f24c3916ba2b2e7d09bd134cf83076abe2c20a8c6","source":{"kind":"arxiv","id":"2503.15639","version":2},"attestation_state":"computed","paper":{"title":"A Lightweight Context-Driven Training-Free Network for Scene Text Segmentation and Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cheng-Lin Liu, Ritabrata Chakraborty, Shivakumara Palaiahnakote, Umapada Pal","submitted_at":"2025-03-19T18:51:01Z","abstract_excerpt":"Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios. In such cases, the deployment of heavy models becomes impractical due to constraints on memory, computational resources, and latency. To address these challenges, we propose a novel, training-free plug-and-play framework that leverages the strengths of pre-trained text recognizers while minimizing redundant computations. Our approach uses context-based understanding and introduces an attention-based segmentation stage, whi"},"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":"2503.15639","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T18:51:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a0d48d0b92d7c080d21c49163a779163af8a7affbd87972cbce7c1e138a945cd","abstract_canon_sha256":"fb7b908affbec3400a237d65022fb583d636a9167530d2aa2208bfbbe3c3e7be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:05:03.414689Z","signature_b64":"4Rw+kbjAiOmVn1X7rqZEG1MGVl+5d9A842gUk/DayK0OEqIlLU2n3cQEp8eHJCZCgHHi3FiqaC92bdlas1QDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"692f8505f6073c7c51e2ef1f24c3916ba2b2e7d09bd134cf83076abe2c20a8c6","last_reissued_at":"2026-06-02T03:05:03.414264Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:05:03.414264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Lightweight Context-Driven Training-Free Network for Scene Text Segmentation and Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cheng-Lin Liu, Ritabrata Chakraborty, Shivakumara Palaiahnakote, Umapada Pal","submitted_at":"2025-03-19T18:51:01Z","abstract_excerpt":"Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios. In such cases, the deployment of heavy models becomes impractical due to constraints on memory, computational resources, and latency. To address these challenges, we propose a novel, training-free plug-and-play framework that leverages the strengths of pre-trained text recognizers while minimizing redundant computations. Our approach uses context-based understanding and introduces an attention-based segmentation stage, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15639","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.15639/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":"2503.15639","created_at":"2026-06-02T03:05:03.414340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15639v2","created_at":"2026-06-02T03:05:03.414340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15639","created_at":"2026-06-02T03:05:03.414340+00:00"},{"alias_kind":"pith_short_12","alias_value":"NEXYKBPWA46H","created_at":"2026-06-02T03:05:03.414340+00:00"},{"alias_kind":"pith_short_16","alias_value":"NEXYKBPWA46HYUPC","created_at":"2026-06-02T03:05:03.414340+00:00"},{"alias_kind":"pith_short_8","alias_value":"NEXYKBPW","created_at":"2026-06-02T03:05:03.414340+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/NEXYKBPWA46HYUPC54PSJQ4RNO","json":"https://pith.science/pith/NEXYKBPWA46HYUPC54PSJQ4RNO.json","graph_json":"https://pith.science/api/pith-number/NEXYKBPWA46HYUPC54PSJQ4RNO/graph.json","events_json":"https://pith.science/api/pith-number/NEXYKBPWA46HYUPC54PSJQ4RNO/events.json","paper":"https://pith.science/paper/NEXYKBPW"},"agent_actions":{"view_html":"https://pith.science/pith/NEXYKBPWA46HYUPC54PSJQ4RNO","download_json":"https://pith.science/pith/NEXYKBPWA46HYUPC54PSJQ4RNO.json","view_paper":"https://pith.science/paper/NEXYKBPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15639&json=true","fetch_graph":"https://pith.science/api/pith-number/NEXYKBPWA46HYUPC54PSJQ4RNO/graph.json","fetch_events":"https://pith.science/api/pith-number/NEXYKBPWA46HYUPC54PSJQ4RNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NEXYKBPWA46HYUPC54PSJQ4RNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NEXYKBPWA46HYUPC54PSJQ4RNO/action/storage_attestation","attest_author":"https://pith.science/pith/NEXYKBPWA46HYUPC54PSJQ4RNO/action/author_attestation","sign_citation":"https://pith.science/pith/NEXYKBPWA46HYUPC54PSJQ4RNO/action/citation_signature","submit_replication":"https://pith.science/pith/NEXYKBPWA46HYUPC54PSJQ4RNO/action/replication_record"}},"created_at":"2026-06-02T03:05:03.414340+00:00","updated_at":"2026-06-02T03:05:03.414340+00:00"}