{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2F3356A4W5ND4G2LYUZIIZULFB","short_pith_number":"pith:2F3356A4","schema_version":"1.0","canonical_sha256":"d177bef81cb75a3e1b4bc53284668b287aa531eaaaeb6739a8588ced68f1d2fa","source":{"kind":"arxiv","id":"1910.05639","version":2},"attestation_state":"computed","paper":{"title":"Disentangling Interpretable Generative Parameters of Random and Real-World Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","nlin.CD","stat.ML"],"primary_cat":"cs.LG","authors_text":"Emine Yilmaz, Jan Stuehmer, Marc Brockschmidt, Niklas Stoehr","submitted_at":"2019-10-12T19:57:55Z","abstract_excerpt":"While a wide range of interpretable generative procedures for graphs exist, matching observed graph topologies with such procedures and choices for its parameters remains an open problem. Devising generative models that closely reproduce real-world graphs requires domain knowledge and time-consuming simulation. While existing deep learning approaches rely on less manual modelling, they offer little interpretability. This work approaches graph generation (decoding) as the inverse of graph compression (encoding). We show that in a disentanglement-focused deep autoencoding framework, specifically"},"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":"1910.05639","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-12T19:57:55Z","cross_cats_sorted":["cs.SI","nlin.CD","stat.ML"],"title_canon_sha256":"1b7745c719216b5499b32834251caee033cb6da8717b86aa95c94d37ad64c5f4","abstract_canon_sha256":"0b995c1bdaba768b021708adc1472697cf0570b99a145120b8343b2604f8f6ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:17:39.199185Z","signature_b64":"41Z0GxcV0Qwcby+vj6IekjgblLZpcf5Ml+E1fYbQWL2GtSApW4B2UjexIhrLC0E2a3czHn441F353Q4t+gSGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d177bef81cb75a3e1b4bc53284668b287aa531eaaaeb6739a8588ced68f1d2fa","last_reissued_at":"2026-07-05T00:17:39.198650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:17:39.198650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling Interpretable Generative Parameters of Random and Real-World Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","nlin.CD","stat.ML"],"primary_cat":"cs.LG","authors_text":"Emine Yilmaz, Jan Stuehmer, Marc Brockschmidt, Niklas Stoehr","submitted_at":"2019-10-12T19:57:55Z","abstract_excerpt":"While a wide range of interpretable generative procedures for graphs exist, matching observed graph topologies with such procedures and choices for its parameters remains an open problem. Devising generative models that closely reproduce real-world graphs requires domain knowledge and time-consuming simulation. While existing deep learning approaches rely on less manual modelling, they offer little interpretability. This work approaches graph generation (decoding) as the inverse of graph compression (encoding). We show that in a disentanglement-focused deep autoencoding framework, specifically"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05639","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/1910.05639/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":"1910.05639","created_at":"2026-07-05T00:17:39.198707+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.05639v2","created_at":"2026-07-05T00:17:39.198707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05639","created_at":"2026-07-05T00:17:39.198707+00:00"},{"alias_kind":"pith_short_12","alias_value":"2F3356A4W5ND","created_at":"2026-07-05T00:17:39.198707+00:00"},{"alias_kind":"pith_short_16","alias_value":"2F3356A4W5ND4G2L","created_at":"2026-07-05T00:17:39.198707+00:00"},{"alias_kind":"pith_short_8","alias_value":"2F3356A4","created_at":"2026-07-05T00:17:39.198707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13133","citing_title":"NGTM: Substructure-based Neural Graph Topic Model for Interpretable Graph Generation","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2F3356A4W5ND4G2LYUZIIZULFB","json":"https://pith.science/pith/2F3356A4W5ND4G2LYUZIIZULFB.json","graph_json":"https://pith.science/api/pith-number/2F3356A4W5ND4G2LYUZIIZULFB/graph.json","events_json":"https://pith.science/api/pith-number/2F3356A4W5ND4G2LYUZIIZULFB/events.json","paper":"https://pith.science/paper/2F3356A4"},"agent_actions":{"view_html":"https://pith.science/pith/2F3356A4W5ND4G2LYUZIIZULFB","download_json":"https://pith.science/pith/2F3356A4W5ND4G2LYUZIIZULFB.json","view_paper":"https://pith.science/paper/2F3356A4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.05639&json=true","fetch_graph":"https://pith.science/api/pith-number/2F3356A4W5ND4G2LYUZIIZULFB/graph.json","fetch_events":"https://pith.science/api/pith-number/2F3356A4W5ND4G2LYUZIIZULFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2F3356A4W5ND4G2LYUZIIZULFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2F3356A4W5ND4G2LYUZIIZULFB/action/storage_attestation","attest_author":"https://pith.science/pith/2F3356A4W5ND4G2LYUZIIZULFB/action/author_attestation","sign_citation":"https://pith.science/pith/2F3356A4W5ND4G2LYUZIIZULFB/action/citation_signature","submit_replication":"https://pith.science/pith/2F3356A4W5ND4G2LYUZIIZULFB/action/replication_record"}},"created_at":"2026-07-05T00:17:39.198707+00:00","updated_at":"2026-07-05T00:17:39.198707+00:00"}