{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:EXCKYIPYC3FZ4QLKHZBCBRGQGI","short_pith_number":"pith:EXCKYIPY","canonical_record":{"source":{"id":"1704.04613","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-15T09:44:08Z","cross_cats_sorted":[],"title_canon_sha256":"4a2b498c100a1b236c28d57056af53d3e9928381984881205433d598f5c9d66b","abstract_canon_sha256":"a686d130923cd7d17513895e7da088b0ec24a8d559ac7792b0d138daf5fee34a"},"schema_version":"1.0"},"canonical_sha256":"25c4ac21f816cb9e416a3e4220c4d0322d07f7c87859ab01f9faf7d0eed54331","source":{"kind":"arxiv","id":"1704.04613","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.04613","created_at":"2026-05-18T00:43:25Z"},{"alias_kind":"arxiv_version","alias_value":"1704.04613v2","created_at":"2026-05-18T00:43:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04613","created_at":"2026-05-18T00:43:25Z"},{"alias_kind":"pith_short_12","alias_value":"EXCKYIPYC3FZ","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EXCKYIPYC3FZ4QLK","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EXCKYIPY","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:EXCKYIPYC3FZ4QLKHZBCBRGQGI","target":"record","payload":{"canonical_record":{"source":{"id":"1704.04613","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-15T09:44:08Z","cross_cats_sorted":[],"title_canon_sha256":"4a2b498c100a1b236c28d57056af53d3e9928381984881205433d598f5c9d66b","abstract_canon_sha256":"a686d130923cd7d17513895e7da088b0ec24a8d559ac7792b0d138daf5fee34a"},"schema_version":"1.0"},"canonical_sha256":"25c4ac21f816cb9e416a3e4220c4d0322d07f7c87859ab01f9faf7d0eed54331","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:25.628712Z","signature_b64":"BBhFEJ4bursagLz+xly5JVD+NiX1y1q49USO1JkhaMnSWaJSIaPLrMXyW9XROQhKIm/f3s9rJIPqOnX3hPH5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25c4ac21f816cb9e416a3e4220c4d0322d07f7c87859ab01f9faf7d0eed54331","last_reissued_at":"2026-05-18T00:43:25.628072Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:25.628072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.04613","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":"2026-05-18T00:43:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BsBBexFxLFM1nyoEUsQyC5b2n4DiwzCMVLjHIaiv+0oI3mz2KaLIV8b1SWswJ8xyPeYevlo8wBRiNpn45UtxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:13:54.291895Z"},"content_sha256":"a22ea2fc1c4b5dadb12aa4267967cadcc7f5b1c2705db082a66ac6a995211954","schema_version":"1.0","event_id":"sha256:a22ea2fc1c4b5dadb12aa4267967cadcc7f5b1c2705db082a66ac6a995211954"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:EXCKYIPYC3FZ4QLKHZBCBRGQGI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiebo Luo, Mingkun Yang, Pengyuan Lyu, Xiang Bai, Yongchao Xu","submitted_at":"2017-04-15T09:44:08Z","abstract_excerpt":"Text in natural images contains rich semantics that are often highly relevant to objects or scene. In this paper, we focus on the problem of fully exploiting scene text for visual understanding. The main idea is combining word representations and deep visual features into a globally trainable deep convolutional neural network. First, the recognized words are obtained by a scene text reading system. Then, we combine the word embedding of the recognized words and the deep visual features into a single representation, which is optimized by a convolutional neural network for fine-grained image cla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.04613","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":""},"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":"2026-05-18T00:43:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hoIDZby2W6Tyh+WxpNStbduCVEyM6vi3CVx3YIR/us3UXM8yk9tFCKgQWuXcJtU8RgPY4Cgn6XM0S3NgLHKDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:13:54.292570Z"},"content_sha256":"fb1478312a3726ccdcd4bf6360119ab4a0945954e6ebb60518f617c94d71645f","schema_version":"1.0","event_id":"sha256:fb1478312a3726ccdcd4bf6360119ab4a0945954e6ebb60518f617c94d71645f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EXCKYIPYC3FZ4QLKHZBCBRGQGI/bundle.json","state_url":"https://pith.science/pith/EXCKYIPYC3FZ4QLKHZBCBRGQGI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EXCKYIPYC3FZ4QLKHZBCBRGQGI/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":"2026-05-25T19:13:54Z","links":{"resolver":"https://pith.science/pith/EXCKYIPYC3FZ4QLKHZBCBRGQGI","bundle":"https://pith.science/pith/EXCKYIPYC3FZ4QLKHZBCBRGQGI/bundle.json","state":"https://pith.science/pith/EXCKYIPYC3FZ4QLKHZBCBRGQGI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EXCKYIPYC3FZ4QLKHZBCBRGQGI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EXCKYIPYC3FZ4QLKHZBCBRGQGI","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":"a686d130923cd7d17513895e7da088b0ec24a8d559ac7792b0d138daf5fee34a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-15T09:44:08Z","title_canon_sha256":"4a2b498c100a1b236c28d57056af53d3e9928381984881205433d598f5c9d66b"},"schema_version":"1.0","source":{"id":"1704.04613","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.04613","created_at":"2026-05-18T00:43:25Z"},{"alias_kind":"arxiv_version","alias_value":"1704.04613v2","created_at":"2026-05-18T00:43:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04613","created_at":"2026-05-18T00:43:25Z"},{"alias_kind":"pith_short_12","alias_value":"EXCKYIPYC3FZ","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EXCKYIPYC3FZ4QLK","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EXCKYIPY","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:fb1478312a3726ccdcd4bf6360119ab4a0945954e6ebb60518f617c94d71645f","target":"graph","created_at":"2026-05-18T00:43:25Z","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"},"paper":{"abstract_excerpt":"Text in natural images contains rich semantics that are often highly relevant to objects or scene. In this paper, we focus on the problem of fully exploiting scene text for visual understanding. The main idea is combining word representations and deep visual features into a globally trainable deep convolutional neural network. First, the recognized words are obtained by a scene text reading system. Then, we combine the word embedding of the recognized words and the deep visual features into a single representation, which is optimized by a convolutional neural network for fine-grained image cla","authors_text":"Jiebo Luo, Mingkun Yang, Pengyuan Lyu, Xiang Bai, Yongchao Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-15T09:44:08Z","title":"Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.04613","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:a22ea2fc1c4b5dadb12aa4267967cadcc7f5b1c2705db082a66ac6a995211954","target":"record","created_at":"2026-05-18T00:43:25Z","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":"a686d130923cd7d17513895e7da088b0ec24a8d559ac7792b0d138daf5fee34a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-15T09:44:08Z","title_canon_sha256":"4a2b498c100a1b236c28d57056af53d3e9928381984881205433d598f5c9d66b"},"schema_version":"1.0","source":{"id":"1704.04613","kind":"arxiv","version":2}},"canonical_sha256":"25c4ac21f816cb9e416a3e4220c4d0322d07f7c87859ab01f9faf7d0eed54331","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25c4ac21f816cb9e416a3e4220c4d0322d07f7c87859ab01f9faf7d0eed54331","first_computed_at":"2026-05-18T00:43:25.628072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:25.628072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BBhFEJ4bursagLz+xly5JVD+NiX1y1q49USO1JkhaMnSWaJSIaPLrMXyW9XROQhKIm/f3s9rJIPqOnX3hPH5AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:25.628712Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.04613","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a22ea2fc1c4b5dadb12aa4267967cadcc7f5b1c2705db082a66ac6a995211954","sha256:fb1478312a3726ccdcd4bf6360119ab4a0945954e6ebb60518f617c94d71645f"],"state_sha256":"0d1295351ea1b88088bb78d09aa5edf3d20dd0e53f20d26fca3661db87183e31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sG6nSP4VPn+X6I+Rjjf07mNrLAwFt5bQyMRPpFSeztdBlILQy8nfq5qgpW6dvXNt3uDlx6dpnZ4QoTUfqsRNAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:13:54.296137Z","bundle_sha256":"aa705859da559a92a9db9415bb003e91a111e10f09223c2f4d3b7310b7b41f67"}}