{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LZSIQDFQOUG37RIHC5RIGV4MIM","short_pith_number":"pith:LZSIQDFQ","canonical_record":{"source":{"id":"2203.14215","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-27T05:54:00Z","cross_cats_sorted":[],"title_canon_sha256":"63cae5377af082ea3a3efb4267f317fbf107db69c75e294f6d10eb0253c3db0e","abstract_canon_sha256":"dba31dbe0d5e74bc3084ad1d64a639bc89cbb96054482ba72cb24545b4e6f484"},"schema_version":"1.0"},"canonical_sha256":"5e64880cb0750dbfc507176283578c433ccbc8cc68ae0fc927d2e0050b09922a","source":{"kind":"arxiv","id":"2203.14215","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.14215","created_at":"2026-07-05T04:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2203.14215v1","created_at":"2026-07-05T04:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14215","created_at":"2026-07-05T04:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"LZSIQDFQOUG3","created_at":"2026-07-05T04:08:48Z"},{"alias_kind":"pith_short_16","alias_value":"LZSIQDFQOUG37RIH","created_at":"2026-07-05T04:08:48Z"},{"alias_kind":"pith_short_8","alias_value":"LZSIQDFQ","created_at":"2026-07-05T04:08:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LZSIQDFQOUG37RIHC5RIGV4MIM","target":"record","payload":{"canonical_record":{"source":{"id":"2203.14215","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-27T05:54:00Z","cross_cats_sorted":[],"title_canon_sha256":"63cae5377af082ea3a3efb4267f317fbf107db69c75e294f6d10eb0253c3db0e","abstract_canon_sha256":"dba31dbe0d5e74bc3084ad1d64a639bc89cbb96054482ba72cb24545b4e6f484"},"schema_version":"1.0"},"canonical_sha256":"5e64880cb0750dbfc507176283578c433ccbc8cc68ae0fc927d2e0050b09922a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:48.913812Z","signature_b64":"6PMVT/LXkiO/FPJVMZFjiZ16ZSb/cbMHj6hNeLTsgi3i4/nMCLoKBClfiNkoiH8VE9erdnndhCkPHJcXWnN9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e64880cb0750dbfc507176283578c433ccbc8cc68ae0fc927d2e0050b09922a","last_reissued_at":"2026-07-05T04:08:48.913393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:48.913393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.14215","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":"2026-07-05T04:08:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O93/NKUrfL7ktLGaOYAxiETYtC7nPsH0oDgW3q3UeGnyYW8fKB8Z3Md0qanmQ9wxy0O7tdrdaftlBXhbJkNCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T09:41:59.492172Z"},"content_sha256":"226774305251d2801c4d81f34a0a2699050af79fca3ce4dbcd17c15964ef2bac","schema_version":"1.0","event_id":"sha256:226774305251d2801c4d81f34a0a2699050af79fca3ce4dbcd17c15964ef2bac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LZSIQDFQOUG37RIHC5RIGV4MIM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Knowledge Mining with Scene Text for Fine-Grained Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Ren, Hao Liu, Hao Wang, Junchao Liao, Tianheng Cheng, Wenyu Liu, Xiang Bai, Zewen Gao","submitted_at":"2022-03-27T05:54:00Z","abstract_excerpt":"Recently, the semantics of scene text has been proven to be essential in fine-grained image classification. However, the existing methods mainly exploit the literal meaning of scene text for fine-grained recognition, which might be irrelevant when it is not significantly related to objects/scenes. We propose an end-to-end trainable network that mines implicit contextual knowledge behind scene text image and enhance the semantics and correlation to fine-tune the image representation. Unlike the existing methods, our model integrates three modalities: visual feature extraction, text semantics ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14215","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/2203.14215/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":"2026-07-05T04:08:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sx6NLX6Tqk0Q797rEDTIdyz05CZLj35fVdIaJG6wq0evvrfKyUl0X7cCGXVc0lGO2OwfSykHWOu5xIdXl8FFDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T09:41:59.492560Z"},"content_sha256":"f83dd51fd9e6b5b0baedf69c45e70f39f84b1014474069252efe198699c68f6c","schema_version":"1.0","event_id":"sha256:f83dd51fd9e6b5b0baedf69c45e70f39f84b1014474069252efe198699c68f6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZSIQDFQOUG37RIHC5RIGV4MIM/bundle.json","state_url":"https://pith.science/pith/LZSIQDFQOUG37RIHC5RIGV4MIM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZSIQDFQOUG37RIHC5RIGV4MIM/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":"2026-07-21T09:41:59Z","links":{"resolver":"https://pith.science/pith/LZSIQDFQOUG37RIHC5RIGV4MIM","bundle":"https://pith.science/pith/LZSIQDFQOUG37RIHC5RIGV4MIM/bundle.json","state":"https://pith.science/pith/LZSIQDFQOUG37RIHC5RIGV4MIM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZSIQDFQOUG37RIHC5RIGV4MIM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LZSIQDFQOUG37RIHC5RIGV4MIM","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":"dba31dbe0d5e74bc3084ad1d64a639bc89cbb96054482ba72cb24545b4e6f484","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-27T05:54:00Z","title_canon_sha256":"63cae5377af082ea3a3efb4267f317fbf107db69c75e294f6d10eb0253c3db0e"},"schema_version":"1.0","source":{"id":"2203.14215","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.14215","created_at":"2026-07-05T04:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2203.14215v1","created_at":"2026-07-05T04:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14215","created_at":"2026-07-05T04:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"LZSIQDFQOUG3","created_at":"2026-07-05T04:08:48Z"},{"alias_kind":"pith_short_16","alias_value":"LZSIQDFQOUG37RIH","created_at":"2026-07-05T04:08:48Z"},{"alias_kind":"pith_short_8","alias_value":"LZSIQDFQ","created_at":"2026-07-05T04:08:48Z"}],"graph_snapshots":[{"event_id":"sha256:f83dd51fd9e6b5b0baedf69c45e70f39f84b1014474069252efe198699c68f6c","target":"graph","created_at":"2026-07-05T04:08:48Z","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/2203.14215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, the semantics of scene text has been proven to be essential in fine-grained image classification. However, the existing methods mainly exploit the literal meaning of scene text for fine-grained recognition, which might be irrelevant when it is not significantly related to objects/scenes. We propose an end-to-end trainable network that mines implicit contextual knowledge behind scene text image and enhance the semantics and correlation to fine-tune the image representation. Unlike the existing methods, our model integrates three modalities: visual feature extraction, text semantics ex","authors_text":"Bo Ren, Hao Liu, Hao Wang, Junchao Liao, Tianheng Cheng, Wenyu Liu, Xiang Bai, Zewen Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-27T05:54:00Z","title":"Knowledge Mining with Scene Text for Fine-Grained Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14215","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":"sha256:226774305251d2801c4d81f34a0a2699050af79fca3ce4dbcd17c15964ef2bac","target":"record","created_at":"2026-07-05T04:08:48Z","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":"dba31dbe0d5e74bc3084ad1d64a639bc89cbb96054482ba72cb24545b4e6f484","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-27T05:54:00Z","title_canon_sha256":"63cae5377af082ea3a3efb4267f317fbf107db69c75e294f6d10eb0253c3db0e"},"schema_version":"1.0","source":{"id":"2203.14215","kind":"arxiv","version":1}},"canonical_sha256":"5e64880cb0750dbfc507176283578c433ccbc8cc68ae0fc927d2e0050b09922a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e64880cb0750dbfc507176283578c433ccbc8cc68ae0fc927d2e0050b09922a","first_computed_at":"2026-07-05T04:08:48.913393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:48.913393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6PMVT/LXkiO/FPJVMZFjiZ16ZSb/cbMHj6hNeLTsgi3i4/nMCLoKBClfiNkoiH8VE9erdnndhCkPHJcXWnN9BA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:48.913812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.14215","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:226774305251d2801c4d81f34a0a2699050af79fca3ce4dbcd17c15964ef2bac","sha256:f83dd51fd9e6b5b0baedf69c45e70f39f84b1014474069252efe198699c68f6c"],"state_sha256":"68608da7288f7400fbd46ef0f9c4db5e965dd60c234e9ea9d688ab8bb5509e77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f0DJ4WMgUhlTvnrMlpSKGmhMbtH6iIqg4dQnG8EmfjnIf/LSoo9NpPuIY58JhuWiwRxlMjbqKqYAkAm6oY9KCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T09:41:59.494658Z","bundle_sha256":"08048f994b2a99f51a3300b35c4f58f851d7aed135b1d4bd8fb44f879d3dd666"}}