{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YT2NLIULMEVGDIT7TM7XZGFA4Y","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":"9e9e1a4a7ff041658e50d7731d1b85c0834232fa45b102005acadafad67e9977","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T18:59:57Z","title_canon_sha256":"78132c63ef322cfec46d5dde3007b01478345ece6f41395a8c206adb1eac49f8"},"schema_version":"1.0","source":{"id":"2502.05178","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05178","created_at":"2026-07-05T10:11:10Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05178v1","created_at":"2026-07-05T10:11:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05178","created_at":"2026-07-05T10:11:10Z"},{"alias_kind":"pith_short_12","alias_value":"YT2NLIULMEVG","created_at":"2026-07-05T10:11:10Z"},{"alias_kind":"pith_short_16","alias_value":"YT2NLIULMEVGDIT7","created_at":"2026-07-05T10:11:10Z"},{"alias_kind":"pith_short_8","alias_value":"YT2NLIUL","created_at":"2026-07-05T10:11:10Z"}],"graph_snapshots":[{"event_id":"sha256:3bd6d8a5bd6304b6e5ecddaad0058311c85741a529c85b426c4b0e8d45b0e0d7","target":"graph","created_at":"2026-07-05T10:11:10Z","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/2502.05178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Quantized Language-Image Pretraining (QLIP), a visual tokenization method that combines state-of-the-art reconstruction quality with state-of-the-art zero-shot image understanding. QLIP trains a binary-spherical-quantization-based autoencoder with reconstruction and language-image alignment objectives. We are the first to show that the two objectives do not need to be at odds. We balance the two loss terms dynamically during training and show that a two-stage training pipeline effectively mixes the large-batch requirements of image-language pre-training with the memory bottleneck ","authors_text":"De-An Huang, Fuzhao Xue, Jan Kautz, Linxi Fan, Philipp Kr\\\"ahenb\\\"uhl, Scott Reed, Yue Zhao, Yuke Zhu, Zhiding Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T18:59:57Z","title":"QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05178","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":"sha256:0722682f611577be684159b00eeb43e05a074d4c5ee9a09e0b34130f9000053a","target":"record","created_at":"2026-07-05T10:11:10Z","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":"9e9e1a4a7ff041658e50d7731d1b85c0834232fa45b102005acadafad67e9977","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T18:59:57Z","title_canon_sha256":"78132c63ef322cfec46d5dde3007b01478345ece6f41395a8c206adb1eac49f8"},"schema_version":"1.0","source":{"id":"2502.05178","kind":"arxiv","version":1}},"canonical_sha256":"c4f4d5a28b612a61a27f9b3f7c98a0e621bc8b9749dfeb5325c0d20522d9b2be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4f4d5a28b612a61a27f9b3f7c98a0e621bc8b9749dfeb5325c0d20522d9b2be","first_computed_at":"2026-07-05T10:11:10.342890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:10.342890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j0lP/bGBpPx0f96t0lNnMzAVZoStk0urlF+elI6afzL7X/ILXukw8u6NNI101A9uk9lLoREbYPMI8YWWFqUJCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:10.343396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.05178","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0722682f611577be684159b00eeb43e05a074d4c5ee9a09e0b34130f9000053a","sha256:3bd6d8a5bd6304b6e5ecddaad0058311c85741a529c85b426c4b0e8d45b0e0d7"],"state_sha256":"ee94f006e75b80d3575950abffc77c282fd595099a6c85b7ff5b7441fbd901af"}