{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TXS2UJNTQC5DTANWRS2KMYU645","short_pith_number":"pith:TXS2UJNT","canonical_record":{"source":{"id":"2404.11249","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T10:56:06Z","cross_cats_sorted":[],"title_canon_sha256":"12ad9c3399c0c3b09f43418a22b8abb1e6d15a3ccdf3b13212291a5068458285","abstract_canon_sha256":"6aa33e6e114454abbc95bfd7c8f88d08a0aac16696bc10bd232711e8895e1fa5"},"schema_version":"1.0"},"canonical_sha256":"9de5aa25b380ba3981b68cb4a6629ee74b8ca4899efdcbd7a2034fec4ee52506","source":{"kind":"arxiv","id":"2404.11249","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11249","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11249v1","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11249","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"TXS2UJNTQC5D","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"TXS2UJNTQC5DTANW","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"TXS2UJNT","created_at":"2026-07-05T08:09:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TXS2UJNTQC5DTANWRS2KMYU645","target":"record","payload":{"canonical_record":{"source":{"id":"2404.11249","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T10:56:06Z","cross_cats_sorted":[],"title_canon_sha256":"12ad9c3399c0c3b09f43418a22b8abb1e6d15a3ccdf3b13212291a5068458285","abstract_canon_sha256":"6aa33e6e114454abbc95bfd7c8f88d08a0aac16696bc10bd232711e8895e1fa5"},"schema_version":"1.0"},"canonical_sha256":"9de5aa25b380ba3981b68cb4a6629ee74b8ca4899efdcbd7a2034fec4ee52506","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:06.324767Z","signature_b64":"tEs3OISaXUdSdw7+lhO4zCOpC8yTnRkrVdwKmDpauE6WZL+ZPzy0BAjVQOGKh7rzhYL358Qh09A6lt+rhKTbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9de5aa25b380ba3981b68cb4a6629ee74b8ca4899efdcbd7a2034fec4ee52506","last_reissued_at":"2026-07-05T08:09:06.324330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:06.324330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.11249","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":"2026-07-05T08:09:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NxcctvmB62KG7oz0DST7eMk4Uvm0X52oEojsa1pfVxY4SE2dnOtUtxcp3+VuRNWTmepd+9nH6iD7Y3KoWrlrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:19:39.263742Z"},"content_sha256":"2bbfc179b1c3c465169866766073194765256cc3f799c065056572aede962fb9","schema_version":"1.0","event_id":"sha256:2bbfc179b1c3c465169866766073194765256cc3f799c065056572aede962fb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TXS2UJNTQC5DTANWRS2KMYU645","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Progressive Framework of Vision-language Knowledge Distillation and Alignment for Multilingual Scene","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binqiang Huang, Jianfeng Lin, Jinlu Zhang, Wenbo Zhang, Wenhao Yu, Yifan Zhang","submitted_at":"2024-04-17T10:56:06Z","abstract_excerpt":"Pre-trained vision-language (V-L) models such as CLIP have shown excellent performance in many downstream cross-modal tasks. However, most of them are only applicable to the English context. Subsequent research has focused on this problem and proposed improved models, such as CN-CLIP and AltCLIP, to facilitate their applicability to Chinese and even other languages. Nevertheless, these models suffer from high latency and a large memory footprint in inference, which limits their further deployment on resource-constrained edge devices. In this work, we propose a conceptually simple yet effective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11249","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/2404.11249/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":"2026-07-05T08:09:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CRPxdAeyC7bNhw9joD3xz8GqNCCN6W3iPZT3fQsfjfFcs5s9K2enfURa435gCR11Y6oNmpDGwGoZUm+U3p3nDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:19:39.265255Z"},"content_sha256":"89af7903d5539fd875149c3f416f07576979fd2fef40530897a8409eaa90e45f","schema_version":"1.0","event_id":"sha256:89af7903d5539fd875149c3f416f07576979fd2fef40530897a8409eaa90e45f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TXS2UJNTQC5DTANWRS2KMYU645/bundle.json","state_url":"https://pith.science/pith/TXS2UJNTQC5DTANWRS2KMYU645/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TXS2UJNTQC5DTANWRS2KMYU645/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":"2026-08-17T15:19:39Z","links":{"resolver":"https://pith.science/pith/TXS2UJNTQC5DTANWRS2KMYU645","bundle":"https://pith.science/pith/TXS2UJNTQC5DTANWRS2KMYU645/bundle.json","state":"https://pith.science/pith/TXS2UJNTQC5DTANWRS2KMYU645/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TXS2UJNTQC5DTANWRS2KMYU645/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TXS2UJNTQC5DTANWRS2KMYU645","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":"6aa33e6e114454abbc95bfd7c8f88d08a0aac16696bc10bd232711e8895e1fa5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T10:56:06Z","title_canon_sha256":"12ad9c3399c0c3b09f43418a22b8abb1e6d15a3ccdf3b13212291a5068458285"},"schema_version":"1.0","source":{"id":"2404.11249","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11249","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11249v1","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11249","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"TXS2UJNTQC5D","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"TXS2UJNTQC5DTANW","created_at":"2026-07-05T08:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"TXS2UJNT","created_at":"2026-07-05T08:09:06Z"}],"graph_snapshots":[{"event_id":"sha256:89af7903d5539fd875149c3f416f07576979fd2fef40530897a8409eaa90e45f","target":"graph","created_at":"2026-07-05T08:09:06Z","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/2404.11249/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained vision-language (V-L) models such as CLIP have shown excellent performance in many downstream cross-modal tasks. However, most of them are only applicable to the English context. Subsequent research has focused on this problem and proposed improved models, such as CN-CLIP and AltCLIP, to facilitate their applicability to Chinese and even other languages. Nevertheless, these models suffer from high latency and a large memory footprint in inference, which limits their further deployment on resource-constrained edge devices. In this work, we propose a conceptually simple yet effective","authors_text":"Binqiang Huang, Jianfeng Lin, Jinlu Zhang, Wenbo Zhang, Wenhao Yu, Yifan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T10:56:06Z","title":"A Progressive Framework of Vision-language Knowledge Distillation and Alignment for Multilingual Scene"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11249","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":"sha256:2bbfc179b1c3c465169866766073194765256cc3f799c065056572aede962fb9","target":"record","created_at":"2026-07-05T08:09:06Z","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":"6aa33e6e114454abbc95bfd7c8f88d08a0aac16696bc10bd232711e8895e1fa5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T10:56:06Z","title_canon_sha256":"12ad9c3399c0c3b09f43418a22b8abb1e6d15a3ccdf3b13212291a5068458285"},"schema_version":"1.0","source":{"id":"2404.11249","kind":"arxiv","version":1}},"canonical_sha256":"9de5aa25b380ba3981b68cb4a6629ee74b8ca4899efdcbd7a2034fec4ee52506","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9de5aa25b380ba3981b68cb4a6629ee74b8ca4899efdcbd7a2034fec4ee52506","first_computed_at":"2026-07-05T08:09:06.324330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:06.324330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tEs3OISaXUdSdw7+lhO4zCOpC8yTnRkrVdwKmDpauE6WZL+ZPzy0BAjVQOGKh7rzhYL358Qh09A6lt+rhKTbBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:06.324767Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.11249","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bbfc179b1c3c465169866766073194765256cc3f799c065056572aede962fb9","sha256:89af7903d5539fd875149c3f416f07576979fd2fef40530897a8409eaa90e45f"],"state_sha256":"6798fbc22fd8862f83d86370b88f4b707083b5788b77209e5ed855d2d1faf043"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"42fOqg4QvLcOa2EjzSbtkU+4oHttpGeDWku9Xa4AqaLpDl3Fi0V4kzdj7aNqrUXitZX4jP+x0XtnBoTSNIyXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T15:19:39.281492Z","bundle_sha256":"cb8935ff64b08d778c1599936e39bcd2595dfda7c3a4ba03e0adfe6bb8e716f2"}}