{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KJ3VHAI33FAQER3ZACFEXLJ5SP","short_pith_number":"pith:KJ3VHAI3","canonical_record":{"source":{"id":"2303.02995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-06T09:44:01Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"075d4955127c73c9948b8fd88390ae8f6b1b12e4d83df265e4a3bbae856ddabb","abstract_canon_sha256":"ad250daebb343855e94fb42ab5db55409b46b73ab33bf8ed10a2876b4858929c"},"schema_version":"1.0"},"canonical_sha256":"527753811bd941024779008a4bad3d93fe8e1062aab81f0117fe54061e267b2f","source":{"kind":"arxiv","id":"2303.02995","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02995","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02995v1","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02995","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"pith_short_12","alias_value":"KJ3VHAI33FAQ","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"pith_short_16","alias_value":"KJ3VHAI33FAQER3Z","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"pith_short_8","alias_value":"KJ3VHAI3","created_at":"2026-07-05T05:48:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KJ3VHAI33FAQER3ZACFEXLJ5SP","target":"record","payload":{"canonical_record":{"source":{"id":"2303.02995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-06T09:44:01Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"075d4955127c73c9948b8fd88390ae8f6b1b12e4d83df265e4a3bbae856ddabb","abstract_canon_sha256":"ad250daebb343855e94fb42ab5db55409b46b73ab33bf8ed10a2876b4858929c"},"schema_version":"1.0"},"canonical_sha256":"527753811bd941024779008a4bad3d93fe8e1062aab81f0117fe54061e267b2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:18.056625Z","signature_b64":"snhz0lF1JNu5mVvHfAtI8j/6UpSDOSje2XD9YLL9GLT4Ym7Li829FRdfslkCAHUPhnhMbS5exC4HZ8ZNECgoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"527753811bd941024779008a4bad3d93fe8e1062aab81f0117fe54061e267b2f","last_reissued_at":"2026-07-05T05:48:18.056182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:18.056182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.02995","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":"2026-07-05T05:48:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bKRu7gQ+YeYhPzQwixO2Xsnh7aVUgwFnfAybSbHdcgphslliHiS5LFXA7xfIy5ASTTf0/X2Nb/bxZ9virGWWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T13:15:53.131020Z"},"content_sha256":"80f0179ea836bf3be254d2c6780b5caf35132f833eba1a8d848519926770e689","schema_version":"1.0","event_id":"sha256:80f0179ea836bf3be254d2c6780b5caf35132f833eba1a8d848519926770e689"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KJ3VHAI33FAQER3ZACFEXLJ5SP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jianbo Yuan, Shijie Geng, Yongfeng Zhang, Yu Tian, Yuxiao Chen","submitted_at":"2023-03-06T09:44:01Z","abstract_excerpt":"The success of large-scale contrastive vision-language pretraining (CLIP) has benefited both visual recognition and multimodal content understanding. The concise design brings CLIP the advantage in inference efficiency against other vision-language models with heavier cross-attention fusion layers, making it a popular choice for a wide spectrum of downstream tasks. However, CLIP does not explicitly capture the hierarchical nature of high-level and fine-grained semantics conveyed in images and texts, which is arguably critical to vision-language understanding and reasoning. To this end, we equi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02995","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/2303.02995/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":"2026-07-05T05:48:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yv7vyjoHX9UNqyKjyVyD3e413fqxTH90fAfkQQWAEiF51uSJdCoZzi+dhGmwu4Zin6NOjnqiQlxSGDbddcOLBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T13:15:53.131435Z"},"content_sha256":"8fefba4476aca71b7d35929766c9b53b1f292e9a9ae9e983ee43b150448fb910","schema_version":"1.0","event_id":"sha256:8fefba4476aca71b7d35929766c9b53b1f292e9a9ae9e983ee43b150448fb910"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJ3VHAI33FAQER3ZACFEXLJ5SP/bundle.json","state_url":"https://pith.science/pith/KJ3VHAI33FAQER3ZACFEXLJ5SP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJ3VHAI33FAQER3ZACFEXLJ5SP/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":"2026-07-15T13:15:53Z","links":{"resolver":"https://pith.science/pith/KJ3VHAI33FAQER3ZACFEXLJ5SP","bundle":"https://pith.science/pith/KJ3VHAI33FAQER3ZACFEXLJ5SP/bundle.json","state":"https://pith.science/pith/KJ3VHAI33FAQER3ZACFEXLJ5SP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJ3VHAI33FAQER3ZACFEXLJ5SP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KJ3VHAI33FAQER3ZACFEXLJ5SP","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":"ad250daebb343855e94fb42ab5db55409b46b73ab33bf8ed10a2876b4858929c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-06T09:44:01Z","title_canon_sha256":"075d4955127c73c9948b8fd88390ae8f6b1b12e4d83df265e4a3bbae856ddabb"},"schema_version":"1.0","source":{"id":"2303.02995","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02995","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02995v1","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02995","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"pith_short_12","alias_value":"KJ3VHAI33FAQ","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"pith_short_16","alias_value":"KJ3VHAI33FAQER3Z","created_at":"2026-07-05T05:48:18Z"},{"alias_kind":"pith_short_8","alias_value":"KJ3VHAI3","created_at":"2026-07-05T05:48:18Z"}],"graph_snapshots":[{"event_id":"sha256:8fefba4476aca71b7d35929766c9b53b1f292e9a9ae9e983ee43b150448fb910","target":"graph","created_at":"2026-07-05T05:48:18Z","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/2303.02995/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of large-scale contrastive vision-language pretraining (CLIP) has benefited both visual recognition and multimodal content understanding. The concise design brings CLIP the advantage in inference efficiency against other vision-language models with heavier cross-attention fusion layers, making it a popular choice for a wide spectrum of downstream tasks. However, CLIP does not explicitly capture the hierarchical nature of high-level and fine-grained semantics conveyed in images and texts, which is arguably critical to vision-language understanding and reasoning. To this end, we equi","authors_text":"Jianbo Yuan, Shijie Geng, Yongfeng Zhang, Yu Tian, Yuxiao Chen","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-06T09:44:01Z","title":"HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02995","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":"sha256:80f0179ea836bf3be254d2c6780b5caf35132f833eba1a8d848519926770e689","target":"record","created_at":"2026-07-05T05:48:18Z","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":"ad250daebb343855e94fb42ab5db55409b46b73ab33bf8ed10a2876b4858929c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-06T09:44:01Z","title_canon_sha256":"075d4955127c73c9948b8fd88390ae8f6b1b12e4d83df265e4a3bbae856ddabb"},"schema_version":"1.0","source":{"id":"2303.02995","kind":"arxiv","version":1}},"canonical_sha256":"527753811bd941024779008a4bad3d93fe8e1062aab81f0117fe54061e267b2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"527753811bd941024779008a4bad3d93fe8e1062aab81f0117fe54061e267b2f","first_computed_at":"2026-07-05T05:48:18.056182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:48:18.056182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"snhz0lF1JNu5mVvHfAtI8j/6UpSDOSje2XD9YLL9GLT4Ym7Li829FRdfslkCAHUPhnhMbS5exC4HZ8ZNECgoBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:48:18.056625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.02995","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80f0179ea836bf3be254d2c6780b5caf35132f833eba1a8d848519926770e689","sha256:8fefba4476aca71b7d35929766c9b53b1f292e9a9ae9e983ee43b150448fb910"],"state_sha256":"3ef0722eeced208b01bf35d336bbb563051fa142b9a96625dc2eba7a42c9ee9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LC1NNLalVpyuHOJD1lmxJSPzeMukRbR9BrTR1+Nzt5WXl8d5ijA+DReOAGXVvDktLYU6tmcohIr8WRPwaK33DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-15T13:15:53.134102Z","bundle_sha256":"020c9ac76071fd4ca058ffa27585a41d88077bff4b3d12cb67ee0240a0dbf7d5"}}