{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:33WOFFI43YCDXAWW76C236IKZB","short_pith_number":"pith:33WOFFI4","schema_version":"1.0","canonical_sha256":"deece2951cde043b82d6ff85adf90ac8422f0395dc7cd007c932dc50bfac9ca3","source":{"kind":"arxiv","id":"2606.10820","version":1},"attestation_state":"computed","paper":{"title":"K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bohan Zhuang, Fan Wang, Jiasheng Tang, Wangbo Zhao, Yizheng Han, Yuanyu He, Zhiwei Tang","submitted_at":"2026-06-09T13:02:00Z","abstract_excerpt":"Autoregressive (AR) language modeling is the dominant paradigm for text generation, yet its sequential token-by-token decoding makes inference memory-bound and inefficient. Existing acceleration approaches, such as speculative decoding and diffusion language models, can yield speedups under certain conditions but do not directly address high-load batch serving--the scenario most critical for industrial-scale deployment. We introduce K-Forcing, a push-forward language modeling paradigm for joint next-k-token decoding. K-Forcing distills an existing AR model into a conditional push-forward mappi"},"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":"2606.10820","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T13:02:00Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"282a98aef1e68e1202dddbb28ee9c31567390991c49b3cbe2fbde5b975f10f48","abstract_canon_sha256":"2e7ec559f89bcff324fa7c730d8dabd51041aabfb83df0a4e851620860e5c9e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:42.253185Z","signature_b64":"ZDusMpPOVXXFxNnhJvBpzaaWElNUF4NereI5UIxGhS0Tr7cZdSu8ky5Q46x080IKljfB79Jv6sh1rVB9GY2yCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"deece2951cde043b82d6ff85adf90ac8422f0395dc7cd007c932dc50bfac9ca3","last_reissued_at":"2026-06-10T01:10:42.252340Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:42.252340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bohan Zhuang, Fan Wang, Jiasheng Tang, Wangbo Zhao, Yizheng Han, Yuanyu He, Zhiwei Tang","submitted_at":"2026-06-09T13:02:00Z","abstract_excerpt":"Autoregressive (AR) language modeling is the dominant paradigm for text generation, yet its sequential token-by-token decoding makes inference memory-bound and inefficient. Existing acceleration approaches, such as speculative decoding and diffusion language models, can yield speedups under certain conditions but do not directly address high-load batch serving--the scenario most critical for industrial-scale deployment. We introduce K-Forcing, a push-forward language modeling paradigm for joint next-k-token decoding. K-Forcing distills an existing AR model into a conditional push-forward mappi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10820","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/2606.10820/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":"2606.10820","created_at":"2026-06-10T01:10:42.252499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10820v1","created_at":"2026-06-10T01:10:42.252499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10820","created_at":"2026-06-10T01:10:42.252499+00:00"},{"alias_kind":"pith_short_12","alias_value":"33WOFFI43YCD","created_at":"2026-06-10T01:10:42.252499+00:00"},{"alias_kind":"pith_short_16","alias_value":"33WOFFI43YCDXAWW","created_at":"2026-06-10T01:10:42.252499+00:00"},{"alias_kind":"pith_short_8","alias_value":"33WOFFI4","created_at":"2026-06-10T01:10:42.252499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.08810","citing_title":"Continuous Language Diffusion as a Decoder-Interface Problem","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/33WOFFI43YCDXAWW76C236IKZB","json":"https://pith.science/pith/33WOFFI43YCDXAWW76C236IKZB.json","graph_json":"https://pith.science/api/pith-number/33WOFFI43YCDXAWW76C236IKZB/graph.json","events_json":"https://pith.science/api/pith-number/33WOFFI43YCDXAWW76C236IKZB/events.json","paper":"https://pith.science/paper/33WOFFI4"},"agent_actions":{"view_html":"https://pith.science/pith/33WOFFI43YCDXAWW76C236IKZB","download_json":"https://pith.science/pith/33WOFFI43YCDXAWW76C236IKZB.json","view_paper":"https://pith.science/paper/33WOFFI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10820&json=true","fetch_graph":"https://pith.science/api/pith-number/33WOFFI43YCDXAWW76C236IKZB/graph.json","fetch_events":"https://pith.science/api/pith-number/33WOFFI43YCDXAWW76C236IKZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/33WOFFI43YCDXAWW76C236IKZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/33WOFFI43YCDXAWW76C236IKZB/action/storage_attestation","attest_author":"https://pith.science/pith/33WOFFI43YCDXAWW76C236IKZB/action/author_attestation","sign_citation":"https://pith.science/pith/33WOFFI43YCDXAWW76C236IKZB/action/citation_signature","submit_replication":"https://pith.science/pith/33WOFFI43YCDXAWW76C236IKZB/action/replication_record"}},"created_at":"2026-06-10T01:10:42.252499+00:00","updated_at":"2026-06-10T01:10:42.252499+00:00"}