{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:M7CNY5CLB6PAE53PA7H6UYLDBO","short_pith_number":"pith:M7CNY5CL","canonical_record":{"source":{"id":"2301.07464","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-18T12:16:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d67379e2d442cc0cd93a27eb1baac31220119decfb8227458b69f5d3063faeb6","abstract_canon_sha256":"a98e243e3f335a0fb68bbef8b90292fb28be4e893ed1072268a1aa84d1733e79"},"schema_version":"1.0"},"canonical_sha256":"67c4dc744b0f9e02776f07cfea61630b9f148c60da881dc50bfa06e9bfaf6232","source":{"kind":"arxiv","id":"2301.07464","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.07464","created_at":"2026-07-05T06:33:42Z"},{"alias_kind":"arxiv_version","alias_value":"2301.07464v2","created_at":"2026-07-05T06:33:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07464","created_at":"2026-07-05T06:33:42Z"},{"alias_kind":"pith_short_12","alias_value":"M7CNY5CLB6PA","created_at":"2026-07-05T06:33:42Z"},{"alias_kind":"pith_short_16","alias_value":"M7CNY5CLB6PAE53P","created_at":"2026-07-05T06:33:42Z"},{"alias_kind":"pith_short_8","alias_value":"M7CNY5CL","created_at":"2026-07-05T06:33:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:M7CNY5CLB6PAE53PA7H6UYLDBO","target":"record","payload":{"canonical_record":{"source":{"id":"2301.07464","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-18T12:16:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d67379e2d442cc0cd93a27eb1baac31220119decfb8227458b69f5d3063faeb6","abstract_canon_sha256":"a98e243e3f335a0fb68bbef8b90292fb28be4e893ed1072268a1aa84d1733e79"},"schema_version":"1.0"},"canonical_sha256":"67c4dc744b0f9e02776f07cfea61630b9f148c60da881dc50bfa06e9bfaf6232","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:42.739397Z","signature_b64":"XNjEF48vHQCNapwEexKcvq6YpdeWgdtKbg8MTbag0yPi6XEkPKTXgdAyBsVPFzC1l/6LeBO5dx2ptfpE0oHJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67c4dc744b0f9e02776f07cfea61630b9f148c60da881dc50bfa06e9bfaf6232","last_reissued_at":"2026-07-05T06:33:42.738901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:42.738901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.07464","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:33:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8tTn0yoh4LWKPNOvZ6jwsZk9vevM44CpduKpcuxN09dCtxdDDPiFsXa+Chbe2zp+pPj+LjX+ZIW0X5NjemHiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:50:16.515240Z"},"content_sha256":"96ac5f6a4feddc7f8a04eff8cd0b52b9251b9711c44e82822382c8d540420ff3","schema_version":"1.0","event_id":"sha256:96ac5f6a4feddc7f8a04eff8cd0b52b9251b9711c44e82822382c8d540420ff3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:M7CNY5CLB6PAE53PA7H6UYLDBO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIPTER: Looking at the Bigger Picture in Scene Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alona Golts, Aviad Aberdam, David Bensa\\\"id, Oren Nuriel, Ron Litman, Royee Tichauer, Roy Ganz, Shai Mazor","submitted_at":"2023-01-18T12:16:19Z","abstract_excerpt":"Reading text in real-world scenarios often requires understanding the context surrounding it, especially when dealing with poor-quality text. However, current scene text recognizers are unaware of the bigger picture as they operate on cropped text images. In this study, we harness the representative capabilities of modern vision-language models, such as CLIP, to provide scene-level information to the crop-based recognizer. We achieve this by fusing a rich representation of the entire image, obtained from the vision-language model, with the recognizer word-level features via a gated cross-atten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07464","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/2301.07464/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":"2026-07-05T06:33:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VrUjiNHfS1oZBcs2Gg1r1PNe93ZrzANDm7syjcNPhzNyBoSDhpbFnNCVB5Dc9ukar5b45t/+k0JPXY4WGd0NCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:50:16.516341Z"},"content_sha256":"19bf2e8d8563dac3f537d8b1ce765160625bfbb759a96d136982af661706139f","schema_version":"1.0","event_id":"sha256:19bf2e8d8563dac3f537d8b1ce765160625bfbb759a96d136982af661706139f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M7CNY5CLB6PAE53PA7H6UYLDBO/bundle.json","state_url":"https://pith.science/pith/M7CNY5CLB6PAE53PA7H6UYLDBO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M7CNY5CLB6PAE53PA7H6UYLDBO/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":"2026-08-09T04:50:16Z","links":{"resolver":"https://pith.science/pith/M7CNY5CLB6PAE53PA7H6UYLDBO","bundle":"https://pith.science/pith/M7CNY5CLB6PAE53PA7H6UYLDBO/bundle.json","state":"https://pith.science/pith/M7CNY5CLB6PAE53PA7H6UYLDBO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M7CNY5CLB6PAE53PA7H6UYLDBO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:M7CNY5CLB6PAE53PA7H6UYLDBO","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":"a98e243e3f335a0fb68bbef8b90292fb28be4e893ed1072268a1aa84d1733e79","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-18T12:16:19Z","title_canon_sha256":"d67379e2d442cc0cd93a27eb1baac31220119decfb8227458b69f5d3063faeb6"},"schema_version":"1.0","source":{"id":"2301.07464","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.07464","created_at":"2026-07-05T06:33:42Z"},{"alias_kind":"arxiv_version","alias_value":"2301.07464v2","created_at":"2026-07-05T06:33:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07464","created_at":"2026-07-05T06:33:42Z"},{"alias_kind":"pith_short_12","alias_value":"M7CNY5CLB6PA","created_at":"2026-07-05T06:33:42Z"},{"alias_kind":"pith_short_16","alias_value":"M7CNY5CLB6PAE53P","created_at":"2026-07-05T06:33:42Z"},{"alias_kind":"pith_short_8","alias_value":"M7CNY5CL","created_at":"2026-07-05T06:33:42Z"}],"graph_snapshots":[{"event_id":"sha256:19bf2e8d8563dac3f537d8b1ce765160625bfbb759a96d136982af661706139f","target":"graph","created_at":"2026-07-05T06:33:42Z","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/2301.07464/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reading text in real-world scenarios often requires understanding the context surrounding it, especially when dealing with poor-quality text. However, current scene text recognizers are unaware of the bigger picture as they operate on cropped text images. In this study, we harness the representative capabilities of modern vision-language models, such as CLIP, to provide scene-level information to the crop-based recognizer. We achieve this by fusing a rich representation of the entire image, obtained from the vision-language model, with the recognizer word-level features via a gated cross-atten","authors_text":"Alona Golts, Aviad Aberdam, David Bensa\\\"id, Oren Nuriel, Ron Litman, Royee Tichauer, Roy Ganz, Shai Mazor","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-18T12:16:19Z","title":"CLIPTER: Looking at the Bigger Picture in Scene Text Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07464","kind":"arxiv","version":2},"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":"sha256:96ac5f6a4feddc7f8a04eff8cd0b52b9251b9711c44e82822382c8d540420ff3","target":"record","created_at":"2026-07-05T06:33:42Z","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":"a98e243e3f335a0fb68bbef8b90292fb28be4e893ed1072268a1aa84d1733e79","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-18T12:16:19Z","title_canon_sha256":"d67379e2d442cc0cd93a27eb1baac31220119decfb8227458b69f5d3063faeb6"},"schema_version":"1.0","source":{"id":"2301.07464","kind":"arxiv","version":2}},"canonical_sha256":"67c4dc744b0f9e02776f07cfea61630b9f148c60da881dc50bfa06e9bfaf6232","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67c4dc744b0f9e02776f07cfea61630b9f148c60da881dc50bfa06e9bfaf6232","first_computed_at":"2026-07-05T06:33:42.738901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:42.738901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XNjEF48vHQCNapwEexKcvq6YpdeWgdtKbg8MTbag0yPi6XEkPKTXgdAyBsVPFzC1l/6LeBO5dx2ptfpE0oHJBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:42.739397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.07464","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96ac5f6a4feddc7f8a04eff8cd0b52b9251b9711c44e82822382c8d540420ff3","sha256:19bf2e8d8563dac3f537d8b1ce765160625bfbb759a96d136982af661706139f"],"state_sha256":"d18e10ca083b7bc984579ed5f6e45b38bdf00a0d6702e22e1539d9e0e80d9d2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7w4WeCOdeaoi499v5Cvg7uOwFcttfcdHc5aMpONoU8KAShiMSiw0aXoWKMByuPb0w4vUomiw8Jw9waP7aH8rCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:50:16.521518Z","bundle_sha256":"e2ead37f2ec8b9c416349f51fe9d7f8cd71a4a4a9ffd4095d44059a8143af0e6"}}