{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4Y26HST4CYXZLR4U7NSSIES4X3","short_pith_number":"pith:4Y26HST4","schema_version":"1.0","canonical_sha256":"e635e3ca7c162f95c794fb6524125cbec34ea557c79149ad2e6de1de3b1a2a81","source":{"kind":"arxiv","id":"2209.14734","version":4},"attestation_state":"computed","paper":{"title":"DiGress: Discrete Denoising diffusion for graph generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antoine Siraudin, Bohan Wang, Clement Vignac, Igor Krawczuk, Pascal Frossard, Volkan Cevher","submitted_at":"2022-09-29T12:55:03Z","abstract_excerpt":"This work introduces DiGress, a discrete denoising diffusion model for generating graphs with categorical node and edge attributes. Our model utilizes a discrete diffusion process that progressively edits graphs with noise, through the process of adding or removing edges and changing the categories. A graph transformer network is trained to revert this process, simplifying the problem of distribution learning over graphs into a sequence of node and edge classification tasks. We further improve sample quality by introducing a Markovian noise model that preserves the marginal distribution of nod"},"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":"2209.14734","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T12:55:03Z","cross_cats_sorted":[],"title_canon_sha256":"281b24595cafab30dd8e84190e30ad2bb4e596e1ba8e6d545306d52b4a70f075","abstract_canon_sha256":"08b11587cce034cf05c1980b49c1d4194d0352f88601c3a12813a5244ac1b9e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:36.973392Z","signature_b64":"qtFLMsKxXykHGuStPRiIaadm/kmkspnAk9N85n54vBmXHUE6mv3g9caXTnbSSFi+Jj8vjXmtFo3FYzmjkeM6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e635e3ca7c162f95c794fb6524125cbec34ea557c79149ad2e6de1de3b1a2a81","last_reissued_at":"2026-07-05T06:12:36.972884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:36.972884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiGress: Discrete Denoising diffusion for graph generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antoine Siraudin, Bohan Wang, Clement Vignac, Igor Krawczuk, Pascal Frossard, Volkan Cevher","submitted_at":"2022-09-29T12:55:03Z","abstract_excerpt":"This work introduces DiGress, a discrete denoising diffusion model for generating graphs with categorical node and edge attributes. Our model utilizes a discrete diffusion process that progressively edits graphs with noise, through the process of adding or removing edges and changing the categories. A graph transformer network is trained to revert this process, simplifying the problem of distribution learning over graphs into a sequence of node and edge classification tasks. We further improve sample quality by introducing a Markovian noise model that preserves the marginal distribution of nod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14734","kind":"arxiv","version":4},"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/2209.14734/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":"2209.14734","created_at":"2026-07-05T06:12:36.972944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.14734v4","created_at":"2026-07-05T06:12:36.972944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14734","created_at":"2026-07-05T06:12:36.972944+00:00"},{"alias_kind":"pith_short_12","alias_value":"4Y26HST4CYXZ","created_at":"2026-07-05T06:12:36.972944+00:00"},{"alias_kind":"pith_short_16","alias_value":"4Y26HST4CYXZLR4U","created_at":"2026-07-05T06:12:36.972944+00:00"},{"alias_kind":"pith_short_8","alias_value":"4Y26HST4","created_at":"2026-07-05T06:12:36.972944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06546","citing_title":"Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22702","citing_title":"Modular Diffusion Models for Structured Visual Recognition","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20497","citing_title":"Interpretable Meta-Learning for Multi-Objective Chemical Search","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01775","citing_title":"Set Diffusion: Interpolating Token Orderings Between Autoregression and Diffusion for Fast and Flexible Decoding","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07239","citing_title":"Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00773","citing_title":"Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02133","citing_title":"Variational Learning for Insertion-based Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28225","citing_title":"Estimation-Prediction Tradeoff in Causal Probabilistic Temporal Graphs","ref_index":257,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26540","citing_title":"Domain-Gated Latent Diffusion: Generative Inverse Design of HMX-Class Energetic Materials with First-Principles Validation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00295","citing_title":"Adaptive Order Policies for Masked Diffusion","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18570","citing_title":"Streamlining Analysis and Design of Two-Dimensional Electronic Spectroscopy using Machine Learning","ref_index":194,"is_internal_anchor":false},{"citing_arxiv_id":"2407.20067","citing_title":"xAI-Drop: Don't Use What You Cannot Explain","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2501.11568","citing_title":"Graph Defense Diffusion Model","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2508.08441","citing_title":"SpectraLLM: Uncovering the Ability of LLMs for Molecular Structure Elucidation from Multi-Spectral Data","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2509.17291","citing_title":"GraphWeave: Interpretable and Robust Graph Generation via Random Walk Trajectories","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2510.12916","citing_title":"Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2511.03015","citing_title":"Discrete Bayesian Sample Inference for Graph Generation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08404","citing_title":"Built Environment Reasoning from Remote Sensing Imagery Using Large Vision--Language Models","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05689","citing_title":"GCCM: Enhancing Generative Graph Prediction via Contrastive Consistency Model","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11748","citing_title":"LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07020","citing_title":"FlashMol: High-Quality Molecule Generation in as Few as Four Steps","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14705","citing_title":"SynHAT: A Two-stage Coarse-to-Fine Diffusion Framework for Synthesizing Human Activity Traces","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18344","citing_title":"One Pass for All: A Discrete Diffusion Model for Knowledge Graph Triple Set Prediction","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17310","citing_title":"Interpolating Discrete Diffusion Models with Controllable Resampling","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4Y26HST4CYXZLR4U7NSSIES4X3","json":"https://pith.science/pith/4Y26HST4CYXZLR4U7NSSIES4X3.json","graph_json":"https://pith.science/api/pith-number/4Y26HST4CYXZLR4U7NSSIES4X3/graph.json","events_json":"https://pith.science/api/pith-number/4Y26HST4CYXZLR4U7NSSIES4X3/events.json","paper":"https://pith.science/paper/4Y26HST4"},"agent_actions":{"view_html":"https://pith.science/pith/4Y26HST4CYXZLR4U7NSSIES4X3","download_json":"https://pith.science/pith/4Y26HST4CYXZLR4U7NSSIES4X3.json","view_paper":"https://pith.science/paper/4Y26HST4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.14734&json=true","fetch_graph":"https://pith.science/api/pith-number/4Y26HST4CYXZLR4U7NSSIES4X3/graph.json","fetch_events":"https://pith.science/api/pith-number/4Y26HST4CYXZLR4U7NSSIES4X3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4Y26HST4CYXZLR4U7NSSIES4X3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4Y26HST4CYXZLR4U7NSSIES4X3/action/storage_attestation","attest_author":"https://pith.science/pith/4Y26HST4CYXZLR4U7NSSIES4X3/action/author_attestation","sign_citation":"https://pith.science/pith/4Y26HST4CYXZLR4U7NSSIES4X3/action/citation_signature","submit_replication":"https://pith.science/pith/4Y26HST4CYXZLR4U7NSSIES4X3/action/replication_record"}},"created_at":"2026-07-05T06:12:36.972944+00:00","updated_at":"2026-07-05T06:12:36.972944+00:00"}