{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JTT7Z4WVWFQYVKNK633T23M2H2","short_pith_number":"pith:JTT7Z4WV","canonical_record":{"source":{"id":"2605.21573","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"29501998a7b9520f86aec77ab22a2e592103d7afbf08a07729b9b9894013729c","abstract_canon_sha256":"c81ac3cb95457918724737106fc86fe27b263c637520cbd0ecc8115388e47ad0"},"schema_version":"1.0"},"canonical_sha256":"4ce7fcf2d5b1618aa9aaf6f73d6d9a3e92ae94b104ca8db57050b1e8fd449580","source":{"kind":"arxiv","id":"2605.21573","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21573","created_at":"2026-05-22T01:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21573v1","created_at":"2026-05-22T01:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21573","created_at":"2026-05-22T01:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"JTT7Z4WVWFQY","created_at":"2026-05-22T01:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"JTT7Z4WVWFQYVKNK","created_at":"2026-05-22T01:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"JTT7Z4WV","created_at":"2026-05-22T01:03:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JTT7Z4WVWFQYVKNK633T23M2H2","target":"record","payload":{"canonical_record":{"source":{"id":"2605.21573","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"29501998a7b9520f86aec77ab22a2e592103d7afbf08a07729b9b9894013729c","abstract_canon_sha256":"c81ac3cb95457918724737106fc86fe27b263c637520cbd0ecc8115388e47ad0"},"schema_version":"1.0"},"canonical_sha256":"4ce7fcf2d5b1618aa9aaf6f73d6d9a3e92ae94b104ca8db57050b1e8fd449580","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:23.235917Z","signature_b64":"w+DyxIo0xFHY2r5zLj/95Xtk/tZ4pczS6pACeoSRRC9Qr/XPYHE35R4cFgvdwcf4C60IA70sZxVGjrWYf81lCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ce7fcf2d5b1618aa9aaf6f73d6d9a3e92ae94b104ca8db57050b1e8fd449580","last_reissued_at":"2026-05-22T01:03:23.234435Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:23.234435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.21573","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:03:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2JXV0wMEmWTnc9SxPXvUyloAd0C2+POdG5TIXbFQ54UBWgHIPDPsGvSt8p9c2RZ2IRjXGNzV9ZF4rPd53DdWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T15:47:18.674538Z"},"content_sha256":"87e0981612beda0995b7c8709b5ed4012f93972664e5acdaae9cb5c2bd3b02ff","schema_version":"1.0","event_id":"sha256:87e0981612beda0995b7c8709b5ed4012f93972664e5acdaae9cb5c2bd3b02ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JTT7Z4WVWFQYVKNK633T23M2H2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Chong Luo, Dong Chen, Dongdong Chen, Fangyun Wei, Jianmin Bao, Jiawei Zhang, Ji Li, Jinjing Zhao, Lei Shi, Qinhong Yang, Sirui Zhang, Xiuyu Wu, Xuelu Feng, Yanchen Dong, Yang Yue, Yan Lu, Yitong Wang, Yunuo Chen, Zhiyang Liang, Ziyu Wan","submitted_at":"2026-05-20T17:59:58Z","abstract_excerpt":"We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with more than 6B parameters across various benchmarks, while requiring significantly less training compute. For example, Lens requires only about 19.3% of the training compute used by Z-Image. The training efficiency of Lens stems from two key strategies beyond its compact model size. First, we maximize data information density per training batch by (i) training on Lens-800M, a dataset of 800M densely captioned image-text pairs whose captions are g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21573","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.21573/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:03:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S0mlTa3kfPEvpilfvSnp9KvtbK3Oje2ecCnsXFAXCPk+drK4PkmfeqSa4iN8YNzV2ukgXiFUaMHRlJerhUQmDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T15:47:18.675360Z"},"content_sha256":"7bc084c737928def13562fd9a035fdf73aae4d03502ea91c5ebc8dbbeab60747","schema_version":"1.0","event_id":"sha256:7bc084c737928def13562fd9a035fdf73aae4d03502ea91c5ebc8dbbeab60747"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JTT7Z4WVWFQYVKNK633T23M2H2/bundle.json","state_url":"https://pith.science/pith/JTT7Z4WVWFQYVKNK633T23M2H2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JTT7Z4WVWFQYVKNK633T23M2H2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-23T15:47:18Z","links":{"resolver":"https://pith.science/pith/JTT7Z4WVWFQYVKNK633T23M2H2","bundle":"https://pith.science/pith/JTT7Z4WVWFQYVKNK633T23M2H2/bundle.json","state":"https://pith.science/pith/JTT7Z4WVWFQYVKNK633T23M2H2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JTT7Z4WVWFQYVKNK633T23M2H2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JTT7Z4WVWFQYVKNK633T23M2H2","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":"c81ac3cb95457918724737106fc86fe27b263c637520cbd0ecc8115388e47ad0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T17:59:58Z","title_canon_sha256":"29501998a7b9520f86aec77ab22a2e592103d7afbf08a07729b9b9894013729c"},"schema_version":"1.0","source":{"id":"2605.21573","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21573","created_at":"2026-05-22T01:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21573v1","created_at":"2026-05-22T01:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21573","created_at":"2026-05-22T01:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"JTT7Z4WVWFQY","created_at":"2026-05-22T01:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"JTT7Z4WVWFQYVKNK","created_at":"2026-05-22T01:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"JTT7Z4WV","created_at":"2026-05-22T01:03:23Z"}],"graph_snapshots":[{"event_id":"sha256:7bc084c737928def13562fd9a035fdf73aae4d03502ea91c5ebc8dbbeab60747","target":"graph","created_at":"2026-05-22T01:03:23Z","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/2605.21573/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with more than 6B parameters across various benchmarks, while requiring significantly less training compute. For example, Lens requires only about 19.3% of the training compute used by Z-Image. The training efficiency of Lens stems from two key strategies beyond its compact model size. First, we maximize data information density per training batch by (i) training on Lens-800M, a dataset of 800M densely captioned image-text pairs whose captions are g","authors_text":"Baining Guo, Chong Luo, Dong Chen, Dongdong Chen, Fangyun Wei, Jianmin Bao, Jiawei Zhang, Ji Li, Jinjing Zhao, Lei Shi, Qinhong Yang, Sirui Zhang, Xiuyu Wu, Xuelu Feng, Yanchen Dong, Yang Yue, Yan Lu, Yitong Wang, Yunuo Chen, Zhiyang Liang, Ziyu Wan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T17:59:58Z","title":"Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21573","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":"sha256:87e0981612beda0995b7c8709b5ed4012f93972664e5acdaae9cb5c2bd3b02ff","target":"record","created_at":"2026-05-22T01:03:23Z","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":"c81ac3cb95457918724737106fc86fe27b263c637520cbd0ecc8115388e47ad0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T17:59:58Z","title_canon_sha256":"29501998a7b9520f86aec77ab22a2e592103d7afbf08a07729b9b9894013729c"},"schema_version":"1.0","source":{"id":"2605.21573","kind":"arxiv","version":1}},"canonical_sha256":"4ce7fcf2d5b1618aa9aaf6f73d6d9a3e92ae94b104ca8db57050b1e8fd449580","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ce7fcf2d5b1618aa9aaf6f73d6d9a3e92ae94b104ca8db57050b1e8fd449580","first_computed_at":"2026-05-22T01:03:23.234435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:23.234435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w+DyxIo0xFHY2r5zLj/95Xtk/tZ4pczS6pACeoSRRC9Qr/XPYHE35R4cFgvdwcf4C60IA70sZxVGjrWYf81lCg==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:23.235917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21573","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87e0981612beda0995b7c8709b5ed4012f93972664e5acdaae9cb5c2bd3b02ff","sha256:7bc084c737928def13562fd9a035fdf73aae4d03502ea91c5ebc8dbbeab60747"],"state_sha256":"a0441fd045bbad52e246c1ceddf267080c043277da805010334fe71012f942ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0NbbEzoOghGoTIl3OZeLci5gNQ0GErwcaxDhBbpDGltyVnBozdK7sFu1PleIbhtszr11Wo/bgtF2/+cTUjVVBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T15:47:18.681437Z","bundle_sha256":"7753d0761128f79942dd169e0f98cfdd9ecb80082f50f23960a235593c3e1ded"}}