{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:S2IBCWPIAXJGAM2PRZ3E7TLY57","short_pith_number":"pith:S2IBCWPI","canonical_record":{"source":{"id":"2302.14338","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-28T06:06:12Z","cross_cats_sorted":[],"title_canon_sha256":"cecde34eeb7a68a8ccc4ce2fe7842f3938a82407548da615b0310be769c69ca1","abstract_canon_sha256":"13503fb9f2d2d81ec769d857db4781e8da033bad311225a5286065b904d61acc"},"schema_version":"1.0"},"canonical_sha256":"96901159e805d260334f8e764fcd78efcbb4a5638e231ec0b04f13766f6bf617","source":{"kind":"arxiv","id":"2302.14338","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.14338","created_at":"2026-07-05T05:54:36Z"},{"alias_kind":"arxiv_version","alias_value":"2302.14338v3","created_at":"2026-07-05T05:54:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14338","created_at":"2026-07-05T05:54:36Z"},{"alias_kind":"pith_short_12","alias_value":"S2IBCWPIAXJG","created_at":"2026-07-05T05:54:36Z"},{"alias_kind":"pith_short_16","alias_value":"S2IBCWPIAXJGAM2P","created_at":"2026-07-05T05:54:36Z"},{"alias_kind":"pith_short_8","alias_value":"S2IBCWPI","created_at":"2026-07-05T05:54:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:S2IBCWPIAXJGAM2PRZ3E7TLY57","target":"record","payload":{"canonical_record":{"source":{"id":"2302.14338","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-28T06:06:12Z","cross_cats_sorted":[],"title_canon_sha256":"cecde34eeb7a68a8ccc4ce2fe7842f3938a82407548da615b0310be769c69ca1","abstract_canon_sha256":"13503fb9f2d2d81ec769d857db4781e8da033bad311225a5286065b904d61acc"},"schema_version":"1.0"},"canonical_sha256":"96901159e805d260334f8e764fcd78efcbb4a5638e231ec0b04f13766f6bf617","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:36.010612Z","signature_b64":"NXZEWsBBEbUqSPqueN1kqpelu49njLVT/lDc7lX2pNUm4vO6a50jDh+mkRvTxZPOoUcYYd6vSi/5Gm4ov4whAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96901159e805d260334f8e764fcd78efcbb4a5638e231ec0b04f13766f6bf617","last_reissued_at":"2026-07-05T05:54:36.010122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:36.010122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.14338","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:54:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UGS4OCuGcVBbeQ6yf5B4fx06AJNR6WyRenQcKOg3yABN21ORQDyef2afXAMWqR3/hsI0c7iGOxA7Q63Sx2k1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:50:04.047501Z"},"content_sha256":"a705c50d2b077b6b7a381c5f647296f1b656138b594f09ffd986751d5de9bee8","schema_version":"1.0","event_id":"sha256:a705c50d2b077b6b7a381c5f647296f1b656138b594f09ffd986751d5de9bee8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:S2IBCWPIAXJGAM2PRZ3E7TLY57","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Turning a CLIP Model into a Scene Text Detector","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Ren, Deqiang Jiang, Wei Hua, Wenwen Yu, Xiang Bai, Yuliang Liu","submitted_at":"2023-02-28T06:06:12Z","abstract_excerpt":"The recent large-scale Contrastive Language-Image Pretraining (CLIP) model has shown great potential in various downstream tasks via leveraging the pretrained vision and language knowledge. Scene text, which contains rich textual and visual information, has an inherent connection with a model like CLIP. Recently, pretraining approaches based on vision language models have made effective progresses in the field of text detection. In contrast to these works, this paper proposes a new method, termed TCM, focusing on Turning the CLIP Model directly for text detection without pretraining process. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14338","kind":"arxiv","version":3},"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/2302.14338/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":"2026-07-05T05:54:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J4srEunDdZJjG4bWid4bXXt6059IhcVwA1h7U9/NslUWpoNKznhDicJv+jo8GPAi94um9SRl4+0F1OW4ybwNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:50:04.048428Z"},"content_sha256":"f5c663af2b086b7fc381ecc210da528cceb9148833347ab35dd19ed9a23d3015","schema_version":"1.0","event_id":"sha256:f5c663af2b086b7fc381ecc210da528cceb9148833347ab35dd19ed9a23d3015"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S2IBCWPIAXJGAM2PRZ3E7TLY57/bundle.json","state_url":"https://pith.science/pith/S2IBCWPIAXJGAM2PRZ3E7TLY57/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S2IBCWPIAXJGAM2PRZ3E7TLY57/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":"2026-08-17T08:50:04Z","links":{"resolver":"https://pith.science/pith/S2IBCWPIAXJGAM2PRZ3E7TLY57","bundle":"https://pith.science/pith/S2IBCWPIAXJGAM2PRZ3E7TLY57/bundle.json","state":"https://pith.science/pith/S2IBCWPIAXJGAM2PRZ3E7TLY57/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S2IBCWPIAXJGAM2PRZ3E7TLY57/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:S2IBCWPIAXJGAM2PRZ3E7TLY57","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":"13503fb9f2d2d81ec769d857db4781e8da033bad311225a5286065b904d61acc","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-28T06:06:12Z","title_canon_sha256":"cecde34eeb7a68a8ccc4ce2fe7842f3938a82407548da615b0310be769c69ca1"},"schema_version":"1.0","source":{"id":"2302.14338","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.14338","created_at":"2026-07-05T05:54:36Z"},{"alias_kind":"arxiv_version","alias_value":"2302.14338v3","created_at":"2026-07-05T05:54:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14338","created_at":"2026-07-05T05:54:36Z"},{"alias_kind":"pith_short_12","alias_value":"S2IBCWPIAXJG","created_at":"2026-07-05T05:54:36Z"},{"alias_kind":"pith_short_16","alias_value":"S2IBCWPIAXJGAM2P","created_at":"2026-07-05T05:54:36Z"},{"alias_kind":"pith_short_8","alias_value":"S2IBCWPI","created_at":"2026-07-05T05:54:36Z"}],"graph_snapshots":[{"event_id":"sha256:f5c663af2b086b7fc381ecc210da528cceb9148833347ab35dd19ed9a23d3015","target":"graph","created_at":"2026-07-05T05:54:36Z","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/2302.14338/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent large-scale Contrastive Language-Image Pretraining (CLIP) model has shown great potential in various downstream tasks via leveraging the pretrained vision and language knowledge. Scene text, which contains rich textual and visual information, has an inherent connection with a model like CLIP. Recently, pretraining approaches based on vision language models have made effective progresses in the field of text detection. In contrast to these works, this paper proposes a new method, termed TCM, focusing on Turning the CLIP Model directly for text detection without pretraining process. W","authors_text":"Bo Ren, Deqiang Jiang, Wei Hua, Wenwen Yu, Xiang Bai, Yuliang Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-28T06:06:12Z","title":"Turning a CLIP Model into a Scene Text Detector"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14338","kind":"arxiv","version":3},"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:a705c50d2b077b6b7a381c5f647296f1b656138b594f09ffd986751d5de9bee8","target":"record","created_at":"2026-07-05T05:54:36Z","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":"13503fb9f2d2d81ec769d857db4781e8da033bad311225a5286065b904d61acc","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-28T06:06:12Z","title_canon_sha256":"cecde34eeb7a68a8ccc4ce2fe7842f3938a82407548da615b0310be769c69ca1"},"schema_version":"1.0","source":{"id":"2302.14338","kind":"arxiv","version":3}},"canonical_sha256":"96901159e805d260334f8e764fcd78efcbb4a5638e231ec0b04f13766f6bf617","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96901159e805d260334f8e764fcd78efcbb4a5638e231ec0b04f13766f6bf617","first_computed_at":"2026-07-05T05:54:36.010122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:36.010122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NXZEWsBBEbUqSPqueN1kqpelu49njLVT/lDc7lX2pNUm4vO6a50jDh+mkRvTxZPOoUcYYd6vSi/5Gm4ov4whAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:36.010612Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.14338","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a705c50d2b077b6b7a381c5f647296f1b656138b594f09ffd986751d5de9bee8","sha256:f5c663af2b086b7fc381ecc210da528cceb9148833347ab35dd19ed9a23d3015"],"state_sha256":"46ead1ed0c6e4b554bbc21a1a6c917d55a9a05ebc024c92e342ae08a3a3c115e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ip4bNfFX5ZQ9BMhuu+uqkLL0rwbxcGxFzZHR7Dd7nQGzNCEW0cMlh495j0oG1X4GuOzyzFQNk0BdOhxerTS9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T08:50:04.069131Z","bundle_sha256":"f77b7e6bfa4fdf7ac0c6acf4ff1abc51b1f5b279a9c36f6a69d4a4e5f0e83bd9"}}