{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PABK2LOT4YPGONPQUT5YLIWNHC","short_pith_number":"pith:PABK2LOT","schema_version":"1.0","canonical_sha256":"7802ad2dd3e61e6735f0a4fb85a2cd38bf9b45c064c558d37bbac4f237b34982","source":{"kind":"arxiv","id":"2607.16051","version":1},"attestation_state":"computed","paper":{"title":"Loop the Loopies!","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bryan Dai, Joey Zhou, Ran Tao, Xinyu Yang, Yihao Xiao, Yilong Chen, Zitian Gao","submitted_at":"2026-07-17T15:28:43Z","abstract_excerpt":"We present Loopie, the most powerful looped Transformer to date. The Loopie series consists of two Mixture-of-Experts (MoE) models: a 20B-parameter model with 2B active parameters and a 6Bparameter model with 0.6B active parameters. Looped Transformers have long faced a challenge: given an N-fold increase in pre-training compute, increasing the parameter count by a factor of N usually outperforms looping a model N times. Loopie addresses this challenge. Extensive ablation studies, including comparisons with a vanilla 30B-A3B model, show that Loopie substantially outperforms vanilla Transformer"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.16051","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-17T15:28:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4529776c6346c6f5be035d002e342ddc76ff14c65f010f8adcbe7ce5f5995033","abstract_canon_sha256":"54f46f9e3df31a9450f50908e2c8fc500eb8f7e56e83bc11bbbd8c5806a64b99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T02:19:28.302660Z","signature_b64":"FZASK8xLVDmJZbZN6j8k36eAgNaNNAYanOdlyq+UfkpaQX9HxhH3M72DRumBAGuqBuw/PUTfCpaumiIb3nFxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7802ad2dd3e61e6735f0a4fb85a2cd38bf9b45c064c558d37bbac4f237b34982","last_reissued_at":"2026-07-20T02:19:28.301796Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T02:19:28.301796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Loop the Loopies!","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bryan Dai, Joey Zhou, Ran Tao, Xinyu Yang, Yihao Xiao, Yilong Chen, Zitian Gao","submitted_at":"2026-07-17T15:28:43Z","abstract_excerpt":"We present Loopie, the most powerful looped Transformer to date. The Loopie series consists of two Mixture-of-Experts (MoE) models: a 20B-parameter model with 2B active parameters and a 6Bparameter model with 0.6B active parameters. Looped Transformers have long faced a challenge: given an N-fold increase in pre-training compute, increasing the parameter count by a factor of N usually outperforms looping a model N times. Loopie addresses this challenge. Extensive ablation studies, including comparisons with a vanilla 30B-A3B model, show that Loopie substantially outperforms vanilla Transformer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16051","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/2607.16051/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.16051","created_at":"2026-07-20T02:19:28.302245+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16051v1","created_at":"2026-07-20T02:19:28.302245+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16051","created_at":"2026-07-20T02:19:28.302245+00:00"},{"alias_kind":"pith_short_12","alias_value":"PABK2LOT4YPG","created_at":"2026-07-20T02:19:28.302245+00:00"},{"alias_kind":"pith_short_16","alias_value":"PABK2LOT4YPGONPQ","created_at":"2026-07-20T02:19:28.302245+00:00"},{"alias_kind":"pith_short_8","alias_value":"PABK2LOT","created_at":"2026-07-20T02:19:28.302245+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PABK2LOT4YPGONPQUT5YLIWNHC","json":"https://pith.science/pith/PABK2LOT4YPGONPQUT5YLIWNHC.json","graph_json":"https://pith.science/api/pith-number/PABK2LOT4YPGONPQUT5YLIWNHC/graph.json","events_json":"https://pith.science/api/pith-number/PABK2LOT4YPGONPQUT5YLIWNHC/events.json","paper":"https://pith.science/paper/PABK2LOT"},"agent_actions":{"view_html":"https://pith.science/pith/PABK2LOT4YPGONPQUT5YLIWNHC","download_json":"https://pith.science/pith/PABK2LOT4YPGONPQUT5YLIWNHC.json","view_paper":"https://pith.science/paper/PABK2LOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16051&json=true","fetch_graph":"https://pith.science/api/pith-number/PABK2LOT4YPGONPQUT5YLIWNHC/graph.json","fetch_events":"https://pith.science/api/pith-number/PABK2LOT4YPGONPQUT5YLIWNHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PABK2LOT4YPGONPQUT5YLIWNHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PABK2LOT4YPGONPQUT5YLIWNHC/action/storage_attestation","attest_author":"https://pith.science/pith/PABK2LOT4YPGONPQUT5YLIWNHC/action/author_attestation","sign_citation":"https://pith.science/pith/PABK2LOT4YPGONPQUT5YLIWNHC/action/citation_signature","submit_replication":"https://pith.science/pith/PABK2LOT4YPGONPQUT5YLIWNHC/action/replication_record"}},"created_at":"2026-07-20T02:19:28.302245+00:00","updated_at":"2026-07-20T02:19:28.302245+00:00"}