{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MI2RH5KWDBFY4DINNO2VNFNPA7","short_pith_number":"pith:MI2RH5KW","schema_version":"1.0","canonical_sha256":"623513f556184b8e0d0d6bb55695af07d4e89fa33f54b190d4038ea42f973a7c","source":{"kind":"arxiv","id":"2210.17432","version":2},"attestation_state":"computed","paper":{"title":"SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Sachin Kumar, Xiaochuang Han, Yulia Tsvetkov","submitted_at":"2022-10-31T16:02:00Z","abstract_excerpt":"Despite the growing success of diffusion models in continuous-valued domains (e.g., images), similar efforts for discrete domains such as text have yet to match the performance of autoregressive language models. In this work, we present SSD-LM -- a diffusion-based language model with two key design choices. First, SSD-LM is semi-autoregressive, iteratively generating blocks of text, allowing for flexible output length at decoding time while enabling local bidirectional context updates. Second, it is simplex-based, performing diffusion on the natural vocabulary space rather than a learned laten"},"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":"2210.17432","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T16:02:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d30115a7ecb44b7ccff35410fa3abd270998bc0c935b507c9562d24ae238d6c6","abstract_canon_sha256":"ef4a7daddd970e41502c8945ae4c9e7bbe77d718ebe54e3207d04d553a8093e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:45.341887Z","signature_b64":"KAYAXGbA6Jm6tgw2fSnlZkdRggtoGKb9GsqYooznbvUuLwNj9z9RtaQMr03XZ6C8ee2i4+dJAHQ/Q+v13G6xBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"623513f556184b8e0d0d6bb55695af07d4e89fa33f54b190d4038ea42f973a7c","last_reissued_at":"2026-07-05T06:24:45.341499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:45.341499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Sachin Kumar, Xiaochuang Han, Yulia Tsvetkov","submitted_at":"2022-10-31T16:02:00Z","abstract_excerpt":"Despite the growing success of diffusion models in continuous-valued domains (e.g., images), similar efforts for discrete domains such as text have yet to match the performance of autoregressive language models. In this work, we present SSD-LM -- a diffusion-based language model with two key design choices. First, SSD-LM is semi-autoregressive, iteratively generating blocks of text, allowing for flexible output length at decoding time while enabling local bidirectional context updates. Second, it is simplex-based, performing diffusion on the natural vocabulary space rather than a learned laten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17432","kind":"arxiv","version":2},"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/2210.17432/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":"2210.17432","created_at":"2026-07-05T06:24:45.341555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.17432v2","created_at":"2026-07-05T06:24:45.341555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17432","created_at":"2026-07-05T06:24:45.341555+00:00"},{"alias_kind":"pith_short_12","alias_value":"MI2RH5KWDBFY","created_at":"2026-07-05T06:24:45.341555+00:00"},{"alias_kind":"pith_short_16","alias_value":"MI2RH5KWDBFY4DIN","created_at":"2026-07-05T06:24:45.341555+00:00"},{"alias_kind":"pith_short_8","alias_value":"MI2RH5KW","created_at":"2026-07-05T06:24:45.341555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05722","citing_title":"Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01775","citing_title":"Set Diffusion: Interpolating Token Orderings Between Autoregression and Diffusion for Fast and Flexible Decoding","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08501","citing_title":"Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08417","citing_title":"Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27732","citing_title":"Bifocal Diffusion Language Models: Asymmetric Bidirectional Context for Parallel Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19726","citing_title":"Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03206","citing_title":"Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16933","citing_title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14067","citing_title":"Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09992","citing_title":"Large Language Diffusion Models","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MI2RH5KWDBFY4DINNO2VNFNPA7","json":"https://pith.science/pith/MI2RH5KWDBFY4DINNO2VNFNPA7.json","graph_json":"https://pith.science/api/pith-number/MI2RH5KWDBFY4DINNO2VNFNPA7/graph.json","events_json":"https://pith.science/api/pith-number/MI2RH5KWDBFY4DINNO2VNFNPA7/events.json","paper":"https://pith.science/paper/MI2RH5KW"},"agent_actions":{"view_html":"https://pith.science/pith/MI2RH5KWDBFY4DINNO2VNFNPA7","download_json":"https://pith.science/pith/MI2RH5KWDBFY4DINNO2VNFNPA7.json","view_paper":"https://pith.science/paper/MI2RH5KW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.17432&json=true","fetch_graph":"https://pith.science/api/pith-number/MI2RH5KWDBFY4DINNO2VNFNPA7/graph.json","fetch_events":"https://pith.science/api/pith-number/MI2RH5KWDBFY4DINNO2VNFNPA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MI2RH5KWDBFY4DINNO2VNFNPA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MI2RH5KWDBFY4DINNO2VNFNPA7/action/storage_attestation","attest_author":"https://pith.science/pith/MI2RH5KWDBFY4DINNO2VNFNPA7/action/author_attestation","sign_citation":"https://pith.science/pith/MI2RH5KWDBFY4DINNO2VNFNPA7/action/citation_signature","submit_replication":"https://pith.science/pith/MI2RH5KWDBFY4DINNO2VNFNPA7/action/replication_record"}},"created_at":"2026-07-05T06:24:45.341555+00:00","updated_at":"2026-07-05T06:24:45.341555+00:00"}