{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4ZVIP2LDYFUAW255I7CJUFEEVM","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":"d46ff0005426d580e1a08410843a52f4c3133bb4eb688e918e59b3de30f8cd54","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T09:41:26Z","title_canon_sha256":"71fb85d2795fd00f3c8c88c642b6a71632c702e6798c1e04390b13dbb19dd2be"},"schema_version":"1.0","source":{"id":"2504.14992","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14992","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14992v2","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14992","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"pith_short_12","alias_value":"4ZVIP2LDYFUA","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"pith_short_16","alias_value":"4ZVIP2LDYFUAW255","created_at":"2026-07-05T10:53:17Z"},{"alias_kind":"pith_short_8","alias_value":"4ZVIP2LD","created_at":"2026-07-05T10:53:17Z"}],"graph_snapshots":[{"event_id":"sha256:c8be050e1ee791660a59a6ae9b7c10d72d294da4daac4515883a52a2eeb4d3e5","target":"graph","created_at":"2026-07-05T10:53:17Z","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/2504.14992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models have demonstrated the effectiveness of length scaling during post-training, yet its potential in pre-training remains underexplored. We present the Parallel Hidden Decoding Transformer (\\textit{PHD}-Transformer), a novel framework that enables efficient length scaling during pre-training while maintaining inference efficiency. \\textit{PHD}-Transformer achieves this through an innovative KV cache management strategy that distinguishes between original tokens and hidden decoding tokens. By retaining only the KV cache of original tokens for long-range depe","authors_text":"Bohong Wu, Jianqiao Lu, Shen Yan, Sijun Zhang, Xun Zhou, Ya Wang, Yutao Zeng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T09:41:26Z","title":"Efficient Pretraining Length Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14992","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:efd5eb9727f76c9a73f8e632d8e6cd292e4e6c6ef8c143007ac8a7d2a50c3743","target":"record","created_at":"2026-07-05T10:53:17Z","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":"d46ff0005426d580e1a08410843a52f4c3133bb4eb688e918e59b3de30f8cd54","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T09:41:26Z","title_canon_sha256":"71fb85d2795fd00f3c8c88c642b6a71632c702e6798c1e04390b13dbb19dd2be"},"schema_version":"1.0","source":{"id":"2504.14992","kind":"arxiv","version":2}},"canonical_sha256":"e66a87e963c1680b6bbd47c49a1484ab0ddfdd9d60d0c7eb6ca3d28b5b997c52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e66a87e963c1680b6bbd47c49a1484ab0ddfdd9d60d0c7eb6ca3d28b5b997c52","first_computed_at":"2026-07-05T10:53:17.900457Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:17.900457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yr1HKqllJBBjdOVcvQiG+XMfG2e0Bx6a2igxqMY3vZqS/7t8PLP3KhXdyiB1gSAqsvESeQSW2luZwOIPk6q9CA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:17.900934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14992","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efd5eb9727f76c9a73f8e632d8e6cd292e4e6c6ef8c143007ac8a7d2a50c3743","sha256:c8be050e1ee791660a59a6ae9b7c10d72d294da4daac4515883a52a2eeb4d3e5"],"state_sha256":"251d9e9173e487848b43aaa5cfae328812bb03cf3cd233fe42d50a323bdac723"}