{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YRGCEEG2XXEVN2R4AEWWSTFDF3","short_pith_number":"pith:YRGCEEG2","schema_version":"1.0","canonical_sha256":"c44c2210dabdc956ea3c012d694ca32ee98f906b24b53d31098f3c6ebec5bc17","source":{"kind":"arxiv","id":"2106.06189","version":2},"attestation_state":"computed","paper":{"title":"Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SI"],"primary_cat":"stat.ML","authors_text":"Francisco J. R. Ruiz, Jiajing Hu, Liping Liu, Xiaohui Chen, Xu Han","submitted_at":"2021-06-11T06:37:52Z","abstract_excerpt":"A graph generative model defines a distribution over graphs. One type of generative model is constructed by autoregressive neural networks, which sequentially add nodes and edges to generate a graph. However, the likelihood of a graph under the autoregressive model is intractable, as there are numerous sequences leading to the given graph; this makes maximum likelihood estimation challenging. Instead, in this work we derive the exact joint probability over the graph and the node ordering of the sequential process. From the joint, we approximately marginalize out the node orderings and compute "},"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":"2106.06189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-11T06:37:52Z","cross_cats_sorted":["cs.LG","cs.SI"],"title_canon_sha256":"1179581c9be0ae289fee1f21a8ebbdbd8aff7d15e3edf4a829a842d3176eea91","abstract_canon_sha256":"e0dbe4a6bb382add59b44f2f1fc9e96c31cc429e56e997e26556b031201ed90d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:01.728938Z","signature_b64":"LFxNUM8tIsxlUHqsv/onOY/5J4PmLNhYMuPzY8Ve6DyMrxLNBCsX5DTm4SYdNbxQJEno8dtsVLCKrLiT5rMYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c44c2210dabdc956ea3c012d694ca32ee98f906b24b53d31098f3c6ebec5bc17","last_reissued_at":"2026-07-05T02:49:01.728448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:01.728448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SI"],"primary_cat":"stat.ML","authors_text":"Francisco J. R. Ruiz, Jiajing Hu, Liping Liu, Xiaohui Chen, Xu Han","submitted_at":"2021-06-11T06:37:52Z","abstract_excerpt":"A graph generative model defines a distribution over graphs. One type of generative model is constructed by autoregressive neural networks, which sequentially add nodes and edges to generate a graph. However, the likelihood of a graph under the autoregressive model is intractable, as there are numerous sequences leading to the given graph; this makes maximum likelihood estimation challenging. Instead, in this work we derive the exact joint probability over the graph and the node ordering of the sequential process. From the joint, we approximately marginalize out the node orderings and compute "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06189","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/2106.06189/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":"2106.06189","created_at":"2026-07-05T02:49:01.728501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06189v2","created_at":"2026-07-05T02:49:01.728501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06189","created_at":"2026-07-05T02:49:01.728501+00:00"},{"alias_kind":"pith_short_12","alias_value":"YRGCEEG2XXEV","created_at":"2026-07-05T02:49:01.728501+00:00"},{"alias_kind":"pith_short_16","alias_value":"YRGCEEG2XXEVN2R4","created_at":"2026-07-05T02:49:01.728501+00:00"},{"alias_kind":"pith_short_8","alias_value":"YRGCEEG2","created_at":"2026-07-05T02:49:01.728501+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01073","citing_title":"Graph Generative Pre-trained Transformer","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YRGCEEG2XXEVN2R4AEWWSTFDF3","json":"https://pith.science/pith/YRGCEEG2XXEVN2R4AEWWSTFDF3.json","graph_json":"https://pith.science/api/pith-number/YRGCEEG2XXEVN2R4AEWWSTFDF3/graph.json","events_json":"https://pith.science/api/pith-number/YRGCEEG2XXEVN2R4AEWWSTFDF3/events.json","paper":"https://pith.science/paper/YRGCEEG2"},"agent_actions":{"view_html":"https://pith.science/pith/YRGCEEG2XXEVN2R4AEWWSTFDF3","download_json":"https://pith.science/pith/YRGCEEG2XXEVN2R4AEWWSTFDF3.json","view_paper":"https://pith.science/paper/YRGCEEG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06189&json=true","fetch_graph":"https://pith.science/api/pith-number/YRGCEEG2XXEVN2R4AEWWSTFDF3/graph.json","fetch_events":"https://pith.science/api/pith-number/YRGCEEG2XXEVN2R4AEWWSTFDF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YRGCEEG2XXEVN2R4AEWWSTFDF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YRGCEEG2XXEVN2R4AEWWSTFDF3/action/storage_attestation","attest_author":"https://pith.science/pith/YRGCEEG2XXEVN2R4AEWWSTFDF3/action/author_attestation","sign_citation":"https://pith.science/pith/YRGCEEG2XXEVN2R4AEWWSTFDF3/action/citation_signature","submit_replication":"https://pith.science/pith/YRGCEEG2XXEVN2R4AEWWSTFDF3/action/replication_record"}},"created_at":"2026-07-05T02:49:01.728501+00:00","updated_at":"2026-07-05T02:49:01.728501+00:00"}