{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J7K2I5GKAT2VGRLJS2FGTNS5P5","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":"50692823e873e39b34b246bde8048d63b9ca858850257f106d07e937c2594f9b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T17:51:56Z","title_canon_sha256":"3dbd31e9faeba8c3d8bf667b4ca608a86bea7378df79c29a92b0cd698fd12a99"},"schema_version":"1.0","source":{"id":"2506.04209","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04209","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04209v1","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04209","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_12","alias_value":"J7K2I5GKAT2V","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_16","alias_value":"J7K2I5GKAT2VGRLJ","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_8","alias_value":"J7K2I5GK","created_at":"2026-07-05T11:15:58Z"}],"graph_snapshots":[{"event_id":"sha256:cc3da513dae411638fddb5c0e2fb142abadb57fc1ea53563755a895cfb26ee35","target":"graph","created_at":"2026-07-05T11:15:58Z","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/2506.04209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Currently, the most dominant approach to establishing language-image alignment is to pre-train text and image encoders jointly through contrastive learning, such as CLIP and its variants. In this work, we question whether such a costly joint training is necessary. In particular, we investigate if a pre-trained fixed large language model (LLM) offers a good enough text encoder to guide visual representation learning. That is, we propose to learn Language-Image alignment with a Fixed Text encoder (LIFT) from an LLM by training only the image encoder. Somewhat surprisingly, through comprehensive ","authors_text":"Jingfeng Yang, Yi Ma, Yue Zhao, Ziyang Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T17:51:56Z","title":"Language-Image Alignment with Fixed Text Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04209","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":"sha256:9e4d42bb8b73047182158026057a2d352bfcbbdb007fc9e34bf59e103eacb7f6","target":"record","created_at":"2026-07-05T11:15:58Z","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":"50692823e873e39b34b246bde8048d63b9ca858850257f106d07e937c2594f9b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T17:51:56Z","title_canon_sha256":"3dbd31e9faeba8c3d8bf667b4ca608a86bea7378df79c29a92b0cd698fd12a99"},"schema_version":"1.0","source":{"id":"2506.04209","kind":"arxiv","version":1}},"canonical_sha256":"4fd5a474ca04f5534569968a69b65d7f5cb647a77c95376883093936d44070e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fd5a474ca04f5534569968a69b65d7f5cb647a77c95376883093936d44070e2","first_computed_at":"2026-07-05T11:15:58.936641Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:58.936641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0rrqzjzNKY9C2B4X9p8c1Pf0kSoiUCAuGircPndAg7TGSfcvMmwlUX4crKcsQ/On8ZjcrZQccVqd5zMGu19PDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:58.937141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04209","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e4d42bb8b73047182158026057a2d352bfcbbdb007fc9e34bf59e103eacb7f6","sha256:cc3da513dae411638fddb5c0e2fb142abadb57fc1ea53563755a895cfb26ee35"],"state_sha256":"c5136cc3e1c74781e79f6a10ddfadffb3ac4c240aefa473131d54aa39f50c6b1"}