{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5KW5MNSZQUGDRTZKQ5Y343OCAG","short_pith_number":"pith:5KW5MNSZ","canonical_record":{"source":{"id":"2204.14095","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-29T13:38:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"681a2bdb2a3446278f18730a3c622e8acb50416198452e47b653dc7dbd5f3782","abstract_canon_sha256":"3bb6df6c0afa42943faac4a61cd8aac1615f38f690634b06705b5daf170cab31"},"schema_version":"1.0"},"canonical_sha256":"eaadd63659850c38cf2a8771be6dc2018ef4cadc9c8847d92f85ae971d70d523","source":{"kind":"arxiv","id":"2204.14095","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.14095","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"arxiv_version","alias_value":"2204.14095v2","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.14095","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"pith_short_12","alias_value":"5KW5MNSZQUGD","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"pith_short_16","alias_value":"5KW5MNSZQUGDRTZK","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"pith_short_8","alias_value":"5KW5MNSZ","created_at":"2026-07-05T04:27:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5KW5MNSZQUGDRTZKQ5Y343OCAG","target":"record","payload":{"canonical_record":{"source":{"id":"2204.14095","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-29T13:38:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"681a2bdb2a3446278f18730a3c622e8acb50416198452e47b653dc7dbd5f3782","abstract_canon_sha256":"3bb6df6c0afa42943faac4a61cd8aac1615f38f690634b06705b5daf170cab31"},"schema_version":"1.0"},"canonical_sha256":"eaadd63659850c38cf2a8771be6dc2018ef4cadc9c8847d92f85ae971d70d523","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:13.198334Z","signature_b64":"R0bxzhhGmujBrgXRt0ZZ2iiMlfRJM4AGNrxqQsGAoC2x5Pis7hoU9T6YGDEH3lEdqyrGMS40mnAFIhdrjnfcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaadd63659850c38cf2a8771be6dc2018ef4cadc9c8847d92f85ae971d70d523","last_reissued_at":"2026-07-05T04:27:13.197836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:13.197836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.14095","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":"2026-07-05T04:27:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iRgK5oVfeC+OnQLYu47u1afY+jhvyCZxZNn6gD/XIh1DnXE71LkKUX3CADcPpMwNncFa3MMv6Salp7ANsye6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T22:50:14.176369Z"},"content_sha256":"970d7eb4a00ef8f328a957093b560b63156025be244b619079321ed4e8ee6b22","schema_version":"1.0","event_id":"sha256:970d7eb4a00ef8f328a957093b560b63156025be244b619079321ed4e8ee6b22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5KW5MNSZQUGDRTZKQ5Y343OCAG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Jinfeng Liu, Jun Zhang, Ke Li, Rongrong Ji, Yuting Gao, Zihan Xu","submitted_at":"2022-04-29T13:38:42Z","abstract_excerpt":"Large-scale vision-language pre-training has achieved promising results on downstream tasks. Existing methods highly rely on the assumption that the image-text pairs crawled from the Internet are in perfect one-to-one correspondence. However, in real scenarios, this assumption can be difficult to hold: the text description, obtained by crawling the affiliated metadata of the image, often suffers from the semantic mismatch and the mutual compatibility. To address these issues, we introduce PyramidCLIP, which constructs an input pyramid with different semantic levels for each modality, and align"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.14095","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/2204.14095/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":"2026-07-05T04:27:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wUp8BP/kiA53wbp7lJJu2DsnuXHNrGWZlTZhvxiuODFqdqF67LbOO+4p3ejldJQU5u+jGI/6o99gzi8h7hXMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T22:50:14.176939Z"},"content_sha256":"7d56ea8a497eb643cf0e240562be3da1d00bf313b90089d399f79f96099527d9","schema_version":"1.0","event_id":"sha256:7d56ea8a497eb643cf0e240562be3da1d00bf313b90089d399f79f96099527d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5KW5MNSZQUGDRTZKQ5Y343OCAG/bundle.json","state_url":"https://pith.science/pith/5KW5MNSZQUGDRTZKQ5Y343OCAG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5KW5MNSZQUGDRTZKQ5Y343OCAG/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":"2026-08-10T22:50:14Z","links":{"resolver":"https://pith.science/pith/5KW5MNSZQUGDRTZKQ5Y343OCAG","bundle":"https://pith.science/pith/5KW5MNSZQUGDRTZKQ5Y343OCAG/bundle.json","state":"https://pith.science/pith/5KW5MNSZQUGDRTZKQ5Y343OCAG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5KW5MNSZQUGDRTZKQ5Y343OCAG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5KW5MNSZQUGDRTZKQ5Y343OCAG","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":"3bb6df6c0afa42943faac4a61cd8aac1615f38f690634b06705b5daf170cab31","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-29T13:38:42Z","title_canon_sha256":"681a2bdb2a3446278f18730a3c622e8acb50416198452e47b653dc7dbd5f3782"},"schema_version":"1.0","source":{"id":"2204.14095","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.14095","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"arxiv_version","alias_value":"2204.14095v2","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.14095","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"pith_short_12","alias_value":"5KW5MNSZQUGD","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"pith_short_16","alias_value":"5KW5MNSZQUGDRTZK","created_at":"2026-07-05T04:27:13Z"},{"alias_kind":"pith_short_8","alias_value":"5KW5MNSZ","created_at":"2026-07-05T04:27:13Z"}],"graph_snapshots":[{"event_id":"sha256:7d56ea8a497eb643cf0e240562be3da1d00bf313b90089d399f79f96099527d9","target":"graph","created_at":"2026-07-05T04:27:13Z","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/2204.14095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale vision-language pre-training has achieved promising results on downstream tasks. Existing methods highly rely on the assumption that the image-text pairs crawled from the Internet are in perfect one-to-one correspondence. However, in real scenarios, this assumption can be difficult to hold: the text description, obtained by crawling the affiliated metadata of the image, often suffers from the semantic mismatch and the mutual compatibility. To address these issues, we introduce PyramidCLIP, which constructs an input pyramid with different semantic levels for each modality, and align","authors_text":"Chunhua Shen, Jinfeng Liu, Jun Zhang, Ke Li, Rongrong Ji, Yuting Gao, Zihan Xu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-29T13:38:42Z","title":"PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.14095","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":"sha256:970d7eb4a00ef8f328a957093b560b63156025be244b619079321ed4e8ee6b22","target":"record","created_at":"2026-07-05T04:27:13Z","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":"3bb6df6c0afa42943faac4a61cd8aac1615f38f690634b06705b5daf170cab31","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-29T13:38:42Z","title_canon_sha256":"681a2bdb2a3446278f18730a3c622e8acb50416198452e47b653dc7dbd5f3782"},"schema_version":"1.0","source":{"id":"2204.14095","kind":"arxiv","version":2}},"canonical_sha256":"eaadd63659850c38cf2a8771be6dc2018ef4cadc9c8847d92f85ae971d70d523","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eaadd63659850c38cf2a8771be6dc2018ef4cadc9c8847d92f85ae971d70d523","first_computed_at":"2026-07-05T04:27:13.197836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:13.197836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R0bxzhhGmujBrgXRt0ZZ2iiMlfRJM4AGNrxqQsGAoC2x5Pis7hoU9T6YGDEH3lEdqyrGMS40mnAFIhdrjnfcDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:13.198334Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.14095","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:970d7eb4a00ef8f328a957093b560b63156025be244b619079321ed4e8ee6b22","sha256:7d56ea8a497eb643cf0e240562be3da1d00bf313b90089d399f79f96099527d9"],"state_sha256":"e398be8a8f9a50e2a7ca47200cdc54b130e7fb2b9f7aad808b308e7d89880f98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TKTsDMIxONtdYty1JcqioQF2i4bPGzt+0Uq1oCr0CO6dfoYqdUvYRjZBRlVlZ0JjCEazkXzMEsDgrhP7iPK6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T22:50:14.181729Z","bundle_sha256":"23f45290cbe56220a1744a869ee4cb94c7fad0352a70c4df80beaab2910a6e17"}}