{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZAIAU7Y2NG7HBXDCD5TKQQ5JMD","short_pith_number":"pith:ZAIAU7Y2","canonical_record":{"source":{"id":"2501.00343","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T08:32:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"685aef3fdbae96770df5ed857520a0802fa09cd55a19eb26c7278f480804f666","abstract_canon_sha256":"43b56da0b051b558406b6df11c4310f2a26fa5167588589a6b6bb700fac09644"},"schema_version":"1.0"},"canonical_sha256":"c8100a7f1a69be70dc621f66a843a960c42ba48031b2153b50b423ca4c1ca0f1","source":{"kind":"arxiv","id":"2501.00343","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00343","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00343v1","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00343","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZAIAU7Y2NG7H","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"pith_short_16","alias_value":"ZAIAU7Y2NG7HBXDC","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"pith_short_8","alias_value":"ZAIAU7Y2","created_at":"2026-07-05T09:55:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZAIAU7Y2NG7HBXDCD5TKQQ5JMD","target":"record","payload":{"canonical_record":{"source":{"id":"2501.00343","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T08:32:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"685aef3fdbae96770df5ed857520a0802fa09cd55a19eb26c7278f480804f666","abstract_canon_sha256":"43b56da0b051b558406b6df11c4310f2a26fa5167588589a6b6bb700fac09644"},"schema_version":"1.0"},"canonical_sha256":"c8100a7f1a69be70dc621f66a843a960c42ba48031b2153b50b423ca4c1ca0f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:43.329820Z","signature_b64":"80t4gEafqhzHkBKhWjCePntz4kfi8A4QDHPHG3Sui2n+wXiiE7RbFdcJdin929rBZ8s2nKcdhO5ENv1jOQmhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8100a7f1a69be70dc621f66a843a960c42ba48031b2153b50b423ca4c1ca0f1","last_reissued_at":"2026-07-05T09:55:43.327737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:43.327737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.00343","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":"2026-07-05T09:55:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1qh1/TYC1c3QxeW710vpClhuXAuUhI4fM/PF506J7Us4HkrcDktQy+WZwZLgdNEIYM+3b59aNKkyhjySTsa0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:42:23.595094Z"},"content_sha256":"70dc677f9e6bb8c77a50fa51cafcf5a6ab78c3913b9420be72d74c54f9e900ff","schema_version":"1.0","event_id":"sha256:70dc677f9e6bb8c77a50fa51cafcf5a6ab78c3913b9420be72d74c54f9e900ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZAIAU7Y2NG7HBXDCD5TKQQ5JMD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Chunk-Distilled Language Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiawei Zhou, Karen Livescu, Yanhong Li","submitted_at":"2024-12-31T08:32:15Z","abstract_excerpt":"We introduce Chunk-Distilled Language Modeling (CD-LM), an approach to text generation that addresses two challenges in current large language models (LLMs): the inefficiency of token-level generation, and the difficulty of adapting to new data and knowledge. Our method combines deep network-based LLMs with a straightforward retrieval module, which allows the generation of multi-token text chunks at a single decoding step. Our retrieval framework enables flexible construction of model- or domain-specific datastores, either leveraging the internal knowledge of existing models, or incorporating "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00343","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/2501.00343/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":"2026-07-05T09:55:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NBMec44VPRdsWXXACuvaPXQvCW2tKZYeKxrv32Lc9h9FenwpetjJiyPa13Dw9ccuR+8Uy/+WLBozh0Qys2PgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:42:23.595981Z"},"content_sha256":"ba1e6ea85a42e3b235506591e6d426956b031a44705f842a195d6ed047dffbe4","schema_version":"1.0","event_id":"sha256:ba1e6ea85a42e3b235506591e6d426956b031a44705f842a195d6ed047dffbe4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZAIAU7Y2NG7HBXDCD5TKQQ5JMD/bundle.json","state_url":"https://pith.science/pith/ZAIAU7Y2NG7HBXDCD5TKQQ5JMD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZAIAU7Y2NG7HBXDCD5TKQQ5JMD/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":"2026-08-13T08:42:23Z","links":{"resolver":"https://pith.science/pith/ZAIAU7Y2NG7HBXDCD5TKQQ5JMD","bundle":"https://pith.science/pith/ZAIAU7Y2NG7HBXDCD5TKQQ5JMD/bundle.json","state":"https://pith.science/pith/ZAIAU7Y2NG7HBXDCD5TKQQ5JMD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZAIAU7Y2NG7HBXDCD5TKQQ5JMD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZAIAU7Y2NG7HBXDCD5TKQQ5JMD","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":"43b56da0b051b558406b6df11c4310f2a26fa5167588589a6b6bb700fac09644","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T08:32:15Z","title_canon_sha256":"685aef3fdbae96770df5ed857520a0802fa09cd55a19eb26c7278f480804f666"},"schema_version":"1.0","source":{"id":"2501.00343","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00343","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00343v1","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00343","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZAIAU7Y2NG7H","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"pith_short_16","alias_value":"ZAIAU7Y2NG7HBXDC","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"pith_short_8","alias_value":"ZAIAU7Y2","created_at":"2026-07-05T09:55:43Z"}],"graph_snapshots":[{"event_id":"sha256:ba1e6ea85a42e3b235506591e6d426956b031a44705f842a195d6ed047dffbe4","target":"graph","created_at":"2026-07-05T09:55:43Z","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/2501.00343/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Chunk-Distilled Language Modeling (CD-LM), an approach to text generation that addresses two challenges in current large language models (LLMs): the inefficiency of token-level generation, and the difficulty of adapting to new data and knowledge. Our method combines deep network-based LLMs with a straightforward retrieval module, which allows the generation of multi-token text chunks at a single decoding step. Our retrieval framework enables flexible construction of model- or domain-specific datastores, either leveraging the internal knowledge of existing models, or incorporating ","authors_text":"Jiawei Zhou, Karen Livescu, Yanhong Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T08:32:15Z","title":"Chunk-Distilled Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00343","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":"sha256:70dc677f9e6bb8c77a50fa51cafcf5a6ab78c3913b9420be72d74c54f9e900ff","target":"record","created_at":"2026-07-05T09:55:43Z","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":"43b56da0b051b558406b6df11c4310f2a26fa5167588589a6b6bb700fac09644","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T08:32:15Z","title_canon_sha256":"685aef3fdbae96770df5ed857520a0802fa09cd55a19eb26c7278f480804f666"},"schema_version":"1.0","source":{"id":"2501.00343","kind":"arxiv","version":1}},"canonical_sha256":"c8100a7f1a69be70dc621f66a843a960c42ba48031b2153b50b423ca4c1ca0f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8100a7f1a69be70dc621f66a843a960c42ba48031b2153b50b423ca4c1ca0f1","first_computed_at":"2026-07-05T09:55:43.327737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:43.327737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"80t4gEafqhzHkBKhWjCePntz4kfi8A4QDHPHG3Sui2n+wXiiE7RbFdcJdin929rBZ8s2nKcdhO5ENv1jOQmhDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:43.329820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00343","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70dc677f9e6bb8c77a50fa51cafcf5a6ab78c3913b9420be72d74c54f9e900ff","sha256:ba1e6ea85a42e3b235506591e6d426956b031a44705f842a195d6ed047dffbe4"],"state_sha256":"1bfa2dc94715148af2b23515e68e4089369164096fb7d4adb2a17278673ccac9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DeGjvFv1z9nBJLGqA9INVoYFJWXS1FaFc+Pveqd1tS42Ku2ZJnwK7royoX8Ep4/Ac+kgtMRF0b+Ww2QsayUcBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T08:42:23.683288Z","bundle_sha256":"c1d72caebe9d513cd714da8384a769b5290b333393c0f7d9a0b0e5adcc0c0923"}}