{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M3GUGPYRKN476WPHYNBBXU5X6O","short_pith_number":"pith:M3GUGPYR","schema_version":"1.0","canonical_sha256":"66cd433f115379ff59e7c3421bd3b7f3af0af91459ebc0e46143bf63c45aa2e0","source":{"kind":"arxiv","id":"2210.16886","version":1},"attestation_state":"computed","paper":{"title":"DiffusER: Discrete Diffusion via Edit-based Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Machel Reid, Vincent J. Hellendoorn","submitted_at":"2022-10-30T16:55:23Z","abstract_excerpt":"In text generation, models that generate text from scratch one token at a time are currently the dominant paradigm. Despite being performant, these models lack the ability to revise existing text, which limits their usability in many practical scenarios. We look to address this, with DiffusER (Diffusion via Edit-based Reconstruction), a new edit-based generative model for text based on denoising diffusion models -- a class of models that use a Markov chain of denoising steps to incrementally generate data. DiffusER is not only a strong generative model in general, rivalling autoregressive mode"},"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":"2210.16886","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-30T16:55:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7302ccc9ad1684e36c97f1301948f3d1d74b27a573bb323385bb9c747307d695","abstract_canon_sha256":"5192f4155bc61677c4223b044d543021d4868a187d3c40449653339f8e4d4242"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:51.946176Z","signature_b64":"kWsPixaToidNR0M6IQq3Hwc3inn8vfEy/ze45eNUKNvverVDQQZKSJOMg0XTx7KX21PbpTj3xLq4xDqNXzR6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66cd433f115379ff59e7c3421bd3b7f3af0af91459ebc0e46143bf63c45aa2e0","last_reissued_at":"2026-07-05T05:11:51.945716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:51.945716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffusER: Discrete Diffusion via Edit-based Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Machel Reid, Vincent J. Hellendoorn","submitted_at":"2022-10-30T16:55:23Z","abstract_excerpt":"In text generation, models that generate text from scratch one token at a time are currently the dominant paradigm. Despite being performant, these models lack the ability to revise existing text, which limits their usability in many practical scenarios. We look to address this, with DiffusER (Diffusion via Edit-based Reconstruction), a new edit-based generative model for text based on denoising diffusion models -- a class of models that use a Markov chain of denoising steps to incrementally generate data. DiffusER is not only a strong generative model in general, rivalling autoregressive mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16886","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/2210.16886/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":"2210.16886","created_at":"2026-07-05T05:11:51.945779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16886v1","created_at":"2026-07-05T05:11:51.945779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16886","created_at":"2026-07-05T05:11:51.945779+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3GUGPYRKN47","created_at":"2026-07-05T05:11:51.945779+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3GUGPYRKN476WPH","created_at":"2026-07-05T05:11:51.945779+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3GUGPYR","created_at":"2026-07-05T05:11:51.945779+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07915","citing_title":"EditSR: Enhancing Neural Symbolic Regression via Edit-based Rectification","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17119","citing_title":"Diffusion and Flow Matching Models for Tabular Data: A Survey","ref_index":147,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17071","citing_title":"AnchorDiff: Topology-Aware Masked Diffusion with Confidence-based Rewriting for Radiology Report Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09603","citing_title":"Edit-Based Refinement for Parallel Masked Diffusion Language Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18471","citing_title":"NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3GUGPYRKN476WPHYNBBXU5X6O","json":"https://pith.science/pith/M3GUGPYRKN476WPHYNBBXU5X6O.json","graph_json":"https://pith.science/api/pith-number/M3GUGPYRKN476WPHYNBBXU5X6O/graph.json","events_json":"https://pith.science/api/pith-number/M3GUGPYRKN476WPHYNBBXU5X6O/events.json","paper":"https://pith.science/paper/M3GUGPYR"},"agent_actions":{"view_html":"https://pith.science/pith/M3GUGPYRKN476WPHYNBBXU5X6O","download_json":"https://pith.science/pith/M3GUGPYRKN476WPHYNBBXU5X6O.json","view_paper":"https://pith.science/paper/M3GUGPYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16886&json=true","fetch_graph":"https://pith.science/api/pith-number/M3GUGPYRKN476WPHYNBBXU5X6O/graph.json","fetch_events":"https://pith.science/api/pith-number/M3GUGPYRKN476WPHYNBBXU5X6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3GUGPYRKN476WPHYNBBXU5X6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3GUGPYRKN476WPHYNBBXU5X6O/action/storage_attestation","attest_author":"https://pith.science/pith/M3GUGPYRKN476WPHYNBBXU5X6O/action/author_attestation","sign_citation":"https://pith.science/pith/M3GUGPYRKN476WPHYNBBXU5X6O/action/citation_signature","submit_replication":"https://pith.science/pith/M3GUGPYRKN476WPHYNBBXU5X6O/action/replication_record"}},"created_at":"2026-07-05T05:11:51.945779+00:00","updated_at":"2026-07-05T05:11:51.945779+00:00"}