{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HTKIPACDRORQAYY7UJNMLQS2EM","short_pith_number":"pith:HTKIPACD","canonical_record":{"source":{"id":"2308.10408","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T01:25:48Z","cross_cats_sorted":[],"title_canon_sha256":"178415172cbc5bce4918b3a105c091aacf908ec0d8c2e3dc76a31ef256eef2bb","abstract_canon_sha256":"f1a8b5dfa0b7d9aa4cbf35ee86aeec21977b183943bfb83b2774f590e20e2f67"},"schema_version":"1.0"},"canonical_sha256":"3cd48780438ba300631fa25ac5c25a233e4b78e7e599626a6418b6c349a74e72","source":{"kind":"arxiv","id":"2308.10408","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10408","created_at":"2026-07-05T06:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10408v1","created_at":"2026-07-05T06:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10408","created_at":"2026-07-05T06:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"HTKIPACDRORQ","created_at":"2026-07-05T06:43:08Z"},{"alias_kind":"pith_short_16","alias_value":"HTKIPACDRORQAYY7","created_at":"2026-07-05T06:43:08Z"},{"alias_kind":"pith_short_8","alias_value":"HTKIPACD","created_at":"2026-07-05T06:43:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HTKIPACDRORQAYY7UJNMLQS2EM","target":"record","payload":{"canonical_record":{"source":{"id":"2308.10408","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T01:25:48Z","cross_cats_sorted":[],"title_canon_sha256":"178415172cbc5bce4918b3a105c091aacf908ec0d8c2e3dc76a31ef256eef2bb","abstract_canon_sha256":"f1a8b5dfa0b7d9aa4cbf35ee86aeec21977b183943bfb83b2774f590e20e2f67"},"schema_version":"1.0"},"canonical_sha256":"3cd48780438ba300631fa25ac5c25a233e4b78e7e599626a6418b6c349a74e72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:08.771239Z","signature_b64":"Ua++267Mg28u8IGY61VecogRvtaD3SMl1Jf1Ce5BmhTv4huq9H7UDFQsYO6+MFVOIr/Bc9jX1IIRHb70MB8sAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cd48780438ba300631fa25ac5c25a233e4b78e7e599626a6418b6c349a74e72","last_reissued_at":"2026-07-05T06:43:08.770893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:08.770893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.10408","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":"2026-07-05T06:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PDB6WOXT4jhrIKQZd3Bs1+a/RqEpB8G2LOYUzVTjkWqi5BVmOQGyDGHEoz0I88l2AGCknJV9yIGIpGthwXMqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:19:26.202363Z"},"content_sha256":"1f7789211d09aefae3a532db8f2a27a5ae954c63eece14828c6950dc336a1125","schema_version":"1.0","event_id":"sha256:1f7789211d09aefae3a532db8f2a27a5ae954c63eece14828c6950dc336a1125"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HTKIPACDRORQAYY7UJNMLQS2EM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Turning a CLIP Model into a Scene Text Spotter","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Cao, Wenwen Yu, Xiang Bai, Xingkui Zhu, Xing Sun, Yuliang Liu","submitted_at":"2023-08-21T01:25:48Z","abstract_excerpt":"We exploit the potential of the large-scale Contrastive Language-Image Pretraining (CLIP) model to enhance scene text detection and spotting tasks, transforming it into a robust backbone, FastTCM-CR50. This backbone utilizes visual prompt learning and cross-attention in CLIP to extract image and text-based prior knowledge. Using predefined and learnable prompts, FastTCM-CR50 introduces an instance-language matching process to enhance the synergy between image and text embeddings, thereby refining text regions. Our Bimodal Similarity Matching (BSM) module facilitates dynamic language prompt gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10408","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/2308.10408/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u5hhY4eOKvygKIzBG7FVt7hrOn5v8P8u5yG1p+z2aPFRAMgSoWTeQiuSr98wvYr37p1xBOF+zi4mzViTWoMGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:19:26.203115Z"},"content_sha256":"2737f27461bd708f57001d638d5f4ff9b75629731b9e0b8f114838473033a3ba","schema_version":"1.0","event_id":"sha256:2737f27461bd708f57001d638d5f4ff9b75629731b9e0b8f114838473033a3ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HTKIPACDRORQAYY7UJNMLQS2EM/bundle.json","state_url":"https://pith.science/pith/HTKIPACDRORQAYY7UJNMLQS2EM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HTKIPACDRORQAYY7UJNMLQS2EM/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":"2026-08-06T16:19:26Z","links":{"resolver":"https://pith.science/pith/HTKIPACDRORQAYY7UJNMLQS2EM","bundle":"https://pith.science/pith/HTKIPACDRORQAYY7UJNMLQS2EM/bundle.json","state":"https://pith.science/pith/HTKIPACDRORQAYY7UJNMLQS2EM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HTKIPACDRORQAYY7UJNMLQS2EM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HTKIPACDRORQAYY7UJNMLQS2EM","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":"f1a8b5dfa0b7d9aa4cbf35ee86aeec21977b183943bfb83b2774f590e20e2f67","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T01:25:48Z","title_canon_sha256":"178415172cbc5bce4918b3a105c091aacf908ec0d8c2e3dc76a31ef256eef2bb"},"schema_version":"1.0","source":{"id":"2308.10408","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10408","created_at":"2026-07-05T06:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10408v1","created_at":"2026-07-05T06:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10408","created_at":"2026-07-05T06:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"HTKIPACDRORQ","created_at":"2026-07-05T06:43:08Z"},{"alias_kind":"pith_short_16","alias_value":"HTKIPACDRORQAYY7","created_at":"2026-07-05T06:43:08Z"},{"alias_kind":"pith_short_8","alias_value":"HTKIPACD","created_at":"2026-07-05T06:43:08Z"}],"graph_snapshots":[{"event_id":"sha256:2737f27461bd708f57001d638d5f4ff9b75629731b9e0b8f114838473033a3ba","target":"graph","created_at":"2026-07-05T06:43:08Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.10408/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We exploit the potential of the large-scale Contrastive Language-Image Pretraining (CLIP) model to enhance scene text detection and spotting tasks, transforming it into a robust backbone, FastTCM-CR50. This backbone utilizes visual prompt learning and cross-attention in CLIP to extract image and text-based prior knowledge. Using predefined and learnable prompts, FastTCM-CR50 introduces an instance-language matching process to enhance the synergy between image and text embeddings, thereby refining text regions. Our Bimodal Similarity Matching (BSM) module facilitates dynamic language prompt gen","authors_text":"Haoyu Cao, Wenwen Yu, Xiang Bai, Xingkui Zhu, Xing Sun, Yuliang Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T01:25:48Z","title":"Turning a CLIP Model into a Scene Text Spotter"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10408","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":"sha256:1f7789211d09aefae3a532db8f2a27a5ae954c63eece14828c6950dc336a1125","target":"record","created_at":"2026-07-05T06:43:08Z","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":"f1a8b5dfa0b7d9aa4cbf35ee86aeec21977b183943bfb83b2774f590e20e2f67","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T01:25:48Z","title_canon_sha256":"178415172cbc5bce4918b3a105c091aacf908ec0d8c2e3dc76a31ef256eef2bb"},"schema_version":"1.0","source":{"id":"2308.10408","kind":"arxiv","version":1}},"canonical_sha256":"3cd48780438ba300631fa25ac5c25a233e4b78e7e599626a6418b6c349a74e72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cd48780438ba300631fa25ac5c25a233e4b78e7e599626a6418b6c349a74e72","first_computed_at":"2026-07-05T06:43:08.770893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:08.770893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ua++267Mg28u8IGY61VecogRvtaD3SMl1Jf1Ce5BmhTv4huq9H7UDFQsYO6+MFVOIr/Bc9jX1IIRHb70MB8sAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:08.771239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.10408","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f7789211d09aefae3a532db8f2a27a5ae954c63eece14828c6950dc336a1125","sha256:2737f27461bd708f57001d638d5f4ff9b75629731b9e0b8f114838473033a3ba"],"state_sha256":"7d1394678292201b277a3bd16fc18ab6f5d4387f3a7afd732ed0399ee7499f2d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sRc2lrMopQKI91MODq1xodkMVDyubc6HtHmlMdKPvpWD9Nl8EXtkfVillRx+qNPfQElDN9gEKswXcmECBp+RCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:19:26.209965Z","bundle_sha256":"fb4a1dc605b9c79c1f73b84006b1f6f3eb40993352495bbcc8e384ec4edd0124"}}