{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ESYHCMZSYZEIQ43PWJN2EPTRIT","short_pith_number":"pith:ESYHCMZS","canonical_record":{"source":{"id":"2205.12105","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-24T14:32:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"87effe95b59e3d594476ef1ae2b74528378e06358003739fcac3491ff64b22d1","abstract_canon_sha256":"9dafc0c5726fbc4c7a66326ce3beb4dc369df9d80395a754b4652df00e59ab5e"},"schema_version":"1.0"},"canonical_sha256":"24b0713332c64888736fb25ba23e7144e65bdea7169d1d27f78b2c8402c00007","source":{"kind":"arxiv","id":"2205.12105","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12105","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12105v2","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12105","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"pith_short_12","alias_value":"ESYHCMZSYZEI","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"pith_short_16","alias_value":"ESYHCMZSYZEIQ43P","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"pith_short_8","alias_value":"ESYHCMZS","created_at":"2026-07-05T04:27:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ESYHCMZSYZEIQ43PWJN2EPTRIT","target":"record","payload":{"canonical_record":{"source":{"id":"2205.12105","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-24T14:32:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"87effe95b59e3d594476ef1ae2b74528378e06358003739fcac3491ff64b22d1","abstract_canon_sha256":"9dafc0c5726fbc4c7a66326ce3beb4dc369df9d80395a754b4652df00e59ab5e"},"schema_version":"1.0"},"canonical_sha256":"24b0713332c64888736fb25ba23e7144e65bdea7169d1d27f78b2c8402c00007","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:31.410520Z","signature_b64":"sXFCdfLFbmmZVNXpcxBSZQZ0OeW5E0knMEu01ovw3bEHaGoVVrpVYfP2Wgd2+EYfHHyu67IFD/ZwYSTo2Sh+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24b0713332c64888736fb25ba23e7144e65bdea7169d1d27f78b2c8402c00007","last_reissued_at":"2026-07-05T04:27:31.410031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:31.410031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.12105","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":"2026-07-05T04:27:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/BZAp6ZwUPYthZMA+BPDept8ywb+NzNUX95zRgKCc9lDiuey0XBjh9zQcudWznmynglpmyEnzxYoKMW82WopBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T21:21:55.282426Z"},"content_sha256":"6537aaf7c15b2213abe1106717c35eb2193893875c72b12b45b4a9fa434cdb03","schema_version":"1.0","event_id":"sha256:6537aaf7c15b2213abe1106717c35eb2193893875c72b12b45b4a9fa434cdb03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ESYHCMZSYZEIQ43PWJN2EPTRIT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HiVLP: Hierarchical Vision-Language Pre-Training for Fast Image-Text Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Duzhen Zhang, Feilong Chen, Jianlong Chang, Jiaxin Shi, Qi Tian, Xiuyi Chen","submitted_at":"2022-05-24T14:32:57Z","abstract_excerpt":"In the past few years, the emergence of vision-language pre-training (VLP) has brought cross-modal retrieval to a new era. However, due to the latency and computation demand, it is commonly challenging to apply VLP in a real-time online retrieval system. To alleviate the defect, this paper proposes a \\textbf{Hi}erarchical \\textbf{V}ision-\\textbf{}Language \\textbf{P}re-Training (\\textbf{HiVLP}) for fast Image-Text Retrieval (ITR). Specifically, we design a novel hierarchical retrieval objective, which uses the representation of different dimensions for coarse-to-fine ITR, i.e., using low-dimens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12105","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/2205.12105/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":"2026-07-05T04:27:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cX4JaqKtScXsvath5myclJb8Iil2OPsn9x1qjvvYdxdq/wiOCFD1NTj7u/8ASX4Hi+RnHaf7SVBRS763u2FSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T21:21:55.282815Z"},"content_sha256":"6cafab0a31a90d3de1ee5d8891004c035ca42c2b81bcec6f486de76c1be29de7","schema_version":"1.0","event_id":"sha256:6cafab0a31a90d3de1ee5d8891004c035ca42c2b81bcec6f486de76c1be29de7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT/bundle.json","state_url":"https://pith.science/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT/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":"2026-07-15T21:21:55Z","links":{"resolver":"https://pith.science/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT","bundle":"https://pith.science/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT/bundle.json","state":"https://pith.science/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ESYHCMZSYZEIQ43PWJN2EPTRIT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ESYHCMZSYZEIQ43PWJN2EPTRIT","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":"9dafc0c5726fbc4c7a66326ce3beb4dc369df9d80395a754b4652df00e59ab5e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-24T14:32:57Z","title_canon_sha256":"87effe95b59e3d594476ef1ae2b74528378e06358003739fcac3491ff64b22d1"},"schema_version":"1.0","source":{"id":"2205.12105","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12105","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12105v2","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12105","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"pith_short_12","alias_value":"ESYHCMZSYZEI","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"pith_short_16","alias_value":"ESYHCMZSYZEIQ43P","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"pith_short_8","alias_value":"ESYHCMZS","created_at":"2026-07-05T04:27:31Z"}],"graph_snapshots":[{"event_id":"sha256:6cafab0a31a90d3de1ee5d8891004c035ca42c2b81bcec6f486de76c1be29de7","target":"graph","created_at":"2026-07-05T04:27:31Z","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/2205.12105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the past few years, the emergence of vision-language pre-training (VLP) has brought cross-modal retrieval to a new era. However, due to the latency and computation demand, it is commonly challenging to apply VLP in a real-time online retrieval system. To alleviate the defect, this paper proposes a \\textbf{Hi}erarchical \\textbf{V}ision-\\textbf{}Language \\textbf{P}re-Training (\\textbf{HiVLP}) for fast Image-Text Retrieval (ITR). Specifically, we design a novel hierarchical retrieval objective, which uses the representation of different dimensions for coarse-to-fine ITR, i.e., using low-dimens","authors_text":"Duzhen Zhang, Feilong Chen, Jianlong Chang, Jiaxin Shi, Qi Tian, Xiuyi Chen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-24T14:32:57Z","title":"HiVLP: Hierarchical Vision-Language Pre-Training for Fast Image-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12105","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":"sha256:6537aaf7c15b2213abe1106717c35eb2193893875c72b12b45b4a9fa434cdb03","target":"record","created_at":"2026-07-05T04:27:31Z","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":"9dafc0c5726fbc4c7a66326ce3beb4dc369df9d80395a754b4652df00e59ab5e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-24T14:32:57Z","title_canon_sha256":"87effe95b59e3d594476ef1ae2b74528378e06358003739fcac3491ff64b22d1"},"schema_version":"1.0","source":{"id":"2205.12105","kind":"arxiv","version":2}},"canonical_sha256":"24b0713332c64888736fb25ba23e7144e65bdea7169d1d27f78b2c8402c00007","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24b0713332c64888736fb25ba23e7144e65bdea7169d1d27f78b2c8402c00007","first_computed_at":"2026-07-05T04:27:31.410031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:31.410031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sXFCdfLFbmmZVNXpcxBSZQZ0OeW5E0knMEu01ovw3bEHaGoVVrpVYfP2Wgd2+EYfHHyu67IFD/ZwYSTo2Sh+DA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:31.410520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.12105","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6537aaf7c15b2213abe1106717c35eb2193893875c72b12b45b4a9fa434cdb03","sha256:6cafab0a31a90d3de1ee5d8891004c035ca42c2b81bcec6f486de76c1be29de7"],"state_sha256":"f1b6e2262e55d86ed19a2aaec7a00b330eb06820044fdcfddd8eaffdd6f8a88a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d4EyYtaPbTV0I4yiGXHjt/tNTGPwGyw4O1XqGRrzdqO5TuFlOQ3eRE9Tpp8ccEzRXI5dNv2lZq9vzfEBcLrbAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-15T21:21:55.285145Z","bundle_sha256":"71b72c6b0bc8312aa2336640c1649b853e31fb9463face07f3cf8b795ce6b982"}}