{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3NB2H4VYUZFSTYYDONHPOW3EDF","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":"8c72884473fa4e49086183a5b1b13840a00fd4cd60471fc595cb4d6944973a34","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T15:49:11Z","title_canon_sha256":"42da6000a47080e117ab4c3c1ea7fb61df67a6ff3de0b360b12c970a7bffc471"},"schema_version":"1.0","source":{"id":"2406.01460","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01460","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01460v2","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01460","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"pith_short_12","alias_value":"3NB2H4VYUZFS","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"pith_short_16","alias_value":"3NB2H4VYUZFSTYYD","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"pith_short_8","alias_value":"3NB2H4VY","created_at":"2026-07-05T08:27:10Z"}],"graph_snapshots":[{"event_id":"sha256:88dfa019da630b3e5f3aa0d6abea93ef4c8ba3c6c760c11906beb5409f90971d","target":"graph","created_at":"2026-07-05T08:27:10Z","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/2406.01460/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms of inefficient data utilization. It relies on a single contrastive supervision for each image-text pair during representation learning, disregarding a substantial amount of valuable information that could offer richer supervision. Additionally, the retention of non-informative tokens leads to increased computational demands and time costs, particularly in CLIP's ViT image encoder. To address these issues, we propose","authors_text":"Changwei Wang, Duoqian Miao, Ke Liu, Kun Yi, Liang Hu, Qi Zhang, Wei Fan, Yang Liu, Yepeng Liu, Yiwei Shi, Yu Zhang, Zixuan Gong","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T15:49:11Z","title":"MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01460","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":"sha256:6c3d95b97cb91bc1a9e7966665517fac26a53d2cbd3dfefa6c7e68dbcc86191e","target":"record","created_at":"2026-07-05T08:27:10Z","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":"8c72884473fa4e49086183a5b1b13840a00fd4cd60471fc595cb4d6944973a34","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T15:49:11Z","title_canon_sha256":"42da6000a47080e117ab4c3c1ea7fb61df67a6ff3de0b360b12c970a7bffc471"},"schema_version":"1.0","source":{"id":"2406.01460","kind":"arxiv","version":2}},"canonical_sha256":"db43a3f2b8a64b29e303734ef75b64196f40c99894b9463503d07c58b11dda5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db43a3f2b8a64b29e303734ef75b64196f40c99894b9463503d07c58b11dda5f","first_computed_at":"2026-07-05T08:27:10.946625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:10.946625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WS4PqqBYW/QYlmj9zP4llrJnwV4d0a+01/jZZYVS2BbzoxPxwRjZ6VwmLhD1dWBBojGGA0NKnK28qkRLF5zEDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:10.947051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01460","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c3d95b97cb91bc1a9e7966665517fac26a53d2cbd3dfefa6c7e68dbcc86191e","sha256:88dfa019da630b3e5f3aa0d6abea93ef4c8ba3c6c760c11906beb5409f90971d"],"state_sha256":"67b1c5ed26d31d864a254eea3914257dba2020b91f51f64f86c9a46e3f11fd4c"}