{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3OLMVMZ33U7EWQIJQGR75CY35W","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":"2fa7b5279f7ad84a15ae6a3cb506b48ab71941d92871d5f1ebf0cfc895b82879","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T15:54:55Z","title_canon_sha256":"fff913fb4886e40e23b2f7f9d9d5d5650b9b5e68c3fb8e03ad72bfa1f30e4236"},"schema_version":"1.0","source":{"id":"2312.00674","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.00674","created_at":"2026-07-05T07:19:12Z"},{"alias_kind":"arxiv_version","alias_value":"2312.00674v1","created_at":"2026-07-05T07:19:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00674","created_at":"2026-07-05T07:19:12Z"},{"alias_kind":"pith_short_12","alias_value":"3OLMVMZ33U7E","created_at":"2026-07-05T07:19:12Z"},{"alias_kind":"pith_short_16","alias_value":"3OLMVMZ33U7EWQIJ","created_at":"2026-07-05T07:19:12Z"},{"alias_kind":"pith_short_8","alias_value":"3OLMVMZ3","created_at":"2026-07-05T07:19:12Z"}],"graph_snapshots":[{"event_id":"sha256:a8d176ce04dc7cd958127ba3cf428659c651b36939ca2ce8974225589a9ed82e","target":"graph","created_at":"2026-07-05T07:19:12Z","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/2312.00674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language pre-training like CLIP has shown promising performance on various downstream tasks such as zero-shot image classification and image-text retrieval. Most of the existing CLIP-alike works usually adopt relatively large image encoders like ResNet50 and ViT, while the lightweight counterparts are rarely discussed. In this paper, we propose a multi-level interaction paradigm for training lightweight CLIP models. Firstly, to mitigate the problem that some image-text pairs are not strictly one-to-one correspondence, we improve the conventional global instance-level alignment objective","authors_text":"Fanyi Du, Kai Han, Tianyu Guo, Wei He, Yehui Tang, Ying Nie, Yunhe Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T15:54:55Z","title":"LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00674","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":"sha256:0d84613bc8e96c2db7eb5009a28826a6b88bf706e2874a0baf2d1ef21cb260f2","target":"record","created_at":"2026-07-05T07:19:12Z","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":"2fa7b5279f7ad84a15ae6a3cb506b48ab71941d92871d5f1ebf0cfc895b82879","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T15:54:55Z","title_canon_sha256":"fff913fb4886e40e23b2f7f9d9d5d5650b9b5e68c3fb8e03ad72bfa1f30e4236"},"schema_version":"1.0","source":{"id":"2312.00674","kind":"arxiv","version":1}},"canonical_sha256":"db96cab33bdd3e4b410981a3fe8b1beda61ca4ec4cd90dc1f28715c206370e57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db96cab33bdd3e4b410981a3fe8b1beda61ca4ec4cd90dc1f28715c206370e57","first_computed_at":"2026-07-05T07:19:12.920359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:19:12.920359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sUKPbYAzUbSeDJCBOuMlmoiR74UHNKzdBlWpiS/uWbKtcLIIJDWWso5iiiIiOrc/UJNNov/jbW4PkE5Q0T67DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:19:12.920810Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.00674","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d84613bc8e96c2db7eb5009a28826a6b88bf706e2874a0baf2d1ef21cb260f2","sha256:a8d176ce04dc7cd958127ba3cf428659c651b36939ca2ce8974225589a9ed82e"],"state_sha256":"905d0ab7466d358765f6c7e4fa15866b1d046f81b4ecb61a946b2648955b3e40"}