{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GHZAQT3GPWSPY6MZRMHCBVH2K2","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":"fc8a65690cfa2cd214e763f3fc0f3909c206d018f2a81dd4af55747f7e89addc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-09T17:15:38Z","title_canon_sha256":"3ee72395c2fd37503d0a9c4ba92eb27d3631c43d89b22c5d1b011cebcbee9339"},"schema_version":"1.0","source":{"id":"2111.07783","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.07783","created_at":"2026-07-05T03:31:43Z"},{"alias_kind":"arxiv_version","alias_value":"2111.07783v1","created_at":"2026-07-05T03:31:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.07783","created_at":"2026-07-05T03:31:43Z"},{"alias_kind":"pith_short_12","alias_value":"GHZAQT3GPWSP","created_at":"2026-07-05T03:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"GHZAQT3GPWSPY6MZ","created_at":"2026-07-05T03:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"GHZAQT3G","created_at":"2026-07-05T03:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:c87674620753a2c9cd2b7c96bcfeeee41d3eda5fd85809fc2e4ce3b1a029b2d3","target":"graph","created_at":"2026-07-05T03:31:43Z","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/2111.07783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised large-scale vision-language pre-training has shown promising advances on various downstream tasks. Existing methods often model the cross-modal interaction either via the similarity of the global feature of each modality which misses sufficient information, or finer-grained interactions using cross/self-attention upon visual and textual tokens. However, cross/self-attention suffers from inferior efficiency in both training and inference. In this paper, we introduce a large-scale Fine-grained Interactive Language-Image Pre-training (FILIP) to achieve finer-level alignment through a","authors_text":"Chunjing Xu, Guansong Lu, Hang Xu, Lewei Yao, Lu Hou, Minzhe Niu, Runhui Huang, Xiaodan Liang, Xin Jiang, Zhenguo Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-09T17:15:38Z","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.07783","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:b5b92acabbe875e672ac5b05f2aad4e17720568bf9f3218a6318d9723415a34c","target":"record","created_at":"2026-07-05T03:31:43Z","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":"fc8a65690cfa2cd214e763f3fc0f3909c206d018f2a81dd4af55747f7e89addc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-09T17:15:38Z","title_canon_sha256":"3ee72395c2fd37503d0a9c4ba92eb27d3631c43d89b22c5d1b011cebcbee9339"},"schema_version":"1.0","source":{"id":"2111.07783","kind":"arxiv","version":1}},"canonical_sha256":"31f2084f667da4fc79998b0e20d4fa56abec7dc1fd48e4c8c4c6ed4eacf8da27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31f2084f667da4fc79998b0e20d4fa56abec7dc1fd48e4c8c4c6ed4eacf8da27","first_computed_at":"2026-07-05T03:31:43.705306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:31:43.705306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XS/HvJM0q1y/rINZKmRkROxr6TzTAwDJJ5TbS2bCj1hZviKclPqFI42RsD4Obe37UewNtkaH9kW5nfpD/RaqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:31:43.705798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.07783","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5b92acabbe875e672ac5b05f2aad4e17720568bf9f3218a6318d9723415a34c","sha256:c87674620753a2c9cd2b7c96bcfeeee41d3eda5fd85809fc2e4ce3b1a029b2d3"],"state_sha256":"59c23096d965d95c79d6bda70ec1244fd4e22009a66e9e110fd937b6d0d32915"}