{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VHLS6M2TWOLA4R3SSYSNHENZ3W","short_pith_number":"pith:VHLS6M2T","schema_version":"1.0","canonical_sha256":"a9d72f3353b3960e47729624d391b9dd9609f03f83afb1109a69ac4dfd92ebf8","source":{"kind":"arxiv","id":"2608.05806","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Latent Prediction for Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang Shi, John Langford, Manan Tomar, Siddhartha Sen, Tim Pearce","submitted_at":"2026-08-06T09:41:41Z","abstract_excerpt":"While standard Next-Token Prediction (NTP) lays the foundation of language model pre- training, its teacher-forced training paradigm may not be optimal for long-horizon reasoning and planning. Recent works such as Multi-Token Prediction (MTP) and Next-Latent prediction (NextLat) try to mitigate the problem through predicting multiple future tokens and self-supervised prediction in the latent space. However, those auxiliary objectives either have a limited horizon or suffer from compounding error from multi-step rollout. We introduce Hierarchical Latent Prediction (HiLP), which introduces an au"},"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":"2608.05806","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T09:41:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"764d730a161a4db39b68d4dcb919f51f5fb44cdb3e74d419aa96fa4d4e2792dd","abstract_canon_sha256":"1b2da22556e434c5b074b27cf27bfc130b727c6d673c8021777f70c8eb466372"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:52:47.579955Z","signature_b64":"tpm5gUj8ycjvqz4Rt8SDNLlCcne6jE20HTdf3sg1PUZxwp/ojbxo5nvgnNf3Ax4t2zvTLHgK4oLGV+viPftDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9d72f3353b3960e47729624d391b9dd9609f03f83afb1109a69ac4dfd92ebf8","last_reissued_at":"2026-08-07T00:52:47.578583Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:52:47.578583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Latent Prediction for Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang Shi, John Langford, Manan Tomar, Siddhartha Sen, Tim Pearce","submitted_at":"2026-08-06T09:41:41Z","abstract_excerpt":"While standard Next-Token Prediction (NTP) lays the foundation of language model pre- training, its teacher-forced training paradigm may not be optimal for long-horizon reasoning and planning. Recent works such as Multi-Token Prediction (MTP) and Next-Latent prediction (NextLat) try to mitigate the problem through predicting multiple future tokens and self-supervised prediction in the latent space. However, those auxiliary objectives either have a limited horizon or suffer from compounding error from multi-step rollout. We introduce Hierarchical Latent Prediction (HiLP), which introduces an au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05806","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/2608.05806/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":"2608.05806","created_at":"2026-08-07T00:52:47.580068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05806v1","created_at":"2026-08-07T00:52:47.580068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05806","created_at":"2026-08-07T00:52:47.580068+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHLS6M2TWOLA","created_at":"2026-08-07T00:52:47.580068+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHLS6M2TWOLA4R3S","created_at":"2026-08-07T00:52:47.580068+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHLS6M2T","created_at":"2026-08-07T00:52:47.580068+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/VHLS6M2TWOLA4R3SSYSNHENZ3W","json":"https://pith.science/pith/VHLS6M2TWOLA4R3SSYSNHENZ3W.json","graph_json":"https://pith.science/api/pith-number/VHLS6M2TWOLA4R3SSYSNHENZ3W/graph.json","events_json":"https://pith.science/api/pith-number/VHLS6M2TWOLA4R3SSYSNHENZ3W/events.json","paper":"https://pith.science/paper/VHLS6M2T"},"agent_actions":{"view_html":"https://pith.science/pith/VHLS6M2TWOLA4R3SSYSNHENZ3W","download_json":"https://pith.science/pith/VHLS6M2TWOLA4R3SSYSNHENZ3W.json","view_paper":"https://pith.science/paper/VHLS6M2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05806&json=true","fetch_graph":"https://pith.science/api/pith-number/VHLS6M2TWOLA4R3SSYSNHENZ3W/graph.json","fetch_events":"https://pith.science/api/pith-number/VHLS6M2TWOLA4R3SSYSNHENZ3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHLS6M2TWOLA4R3SSYSNHENZ3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHLS6M2TWOLA4R3SSYSNHENZ3W/action/storage_attestation","attest_author":"https://pith.science/pith/VHLS6M2TWOLA4R3SSYSNHENZ3W/action/author_attestation","sign_citation":"https://pith.science/pith/VHLS6M2TWOLA4R3SSYSNHENZ3W/action/citation_signature","submit_replication":"https://pith.science/pith/VHLS6M2TWOLA4R3SSYSNHENZ3W/action/replication_record"}},"created_at":"2026-08-07T00:52:47.580068+00:00","updated_at":"2026-08-07T00:52:47.580068+00:00"}