{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2BJLVBCZFZDAUO2PK3SNBNQ2BZ","short_pith_number":"pith:2BJLVBCZ","schema_version":"1.0","canonical_sha256":"d052ba84592e460a3b4f56e4d0b61a0e74e6ffccfcfb59d4dcffa89a1d19fadb","source":{"kind":"arxiv","id":"2304.12895","version":1},"attestation_state":"computed","paper":{"title":"Discovering Graph Generation Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Karolis Martinkus, Mihai Babiac, Roger Wattenhofer","submitted_at":"2023-04-25T15:06:22Z","abstract_excerpt":"We provide a novel approach to construct generative models for graphs. Instead of using the traditional probabilistic models or deep generative models, we propose to instead find an algorithm that generates the data. We achieve this using evolutionary search and a powerful fitness function, implemented by a randomly initialized graph neural network. This brings certain advantages over current deep generative models, for instance, a higher potential for out-of-training-distribution generalization and direct interpretability, as the final graph generative process is expressed as a Python functio"},"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":"2304.12895","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T15:06:22Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"5fe240d8ab652630e103544bf75502466cff86330fea527a22b0dfcaff147089","abstract_canon_sha256":"ad254857d2c1b3eb90443bbaf9695420587d2be7327f28c9417c73da5323132f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:22.123871Z","signature_b64":"Zr4Y0/2n/ZYV+l5HygfVd3OE0kWr7+ZW8iX5lhq6v0WbW6mxeox9xY99chP6xVt/UrLLlGcLMDo3VnTI8VFKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d052ba84592e460a3b4f56e4d0b61a0e74e6ffccfcfb59d4dcffa89a1d19fadb","last_reissued_at":"2026-07-05T06:04:22.123465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:22.123465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discovering Graph Generation Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Karolis Martinkus, Mihai Babiac, Roger Wattenhofer","submitted_at":"2023-04-25T15:06:22Z","abstract_excerpt":"We provide a novel approach to construct generative models for graphs. Instead of using the traditional probabilistic models or deep generative models, we propose to instead find an algorithm that generates the data. We achieve this using evolutionary search and a powerful fitness function, implemented by a randomly initialized graph neural network. This brings certain advantages over current deep generative models, for instance, a higher potential for out-of-training-distribution generalization and direct interpretability, as the final graph generative process is expressed as a Python functio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12895","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/2304.12895/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":"2304.12895","created_at":"2026-07-05T06:04:22.123522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.12895v1","created_at":"2026-07-05T06:04:22.123522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12895","created_at":"2026-07-05T06:04:22.123522+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BJLVBCZFZDA","created_at":"2026-07-05T06:04:22.123522+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BJLVBCZFZDAUO2P","created_at":"2026-07-05T06:04:22.123522+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BJLVBCZ","created_at":"2026-07-05T06:04:22.123522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2BJLVBCZFZDAUO2PK3SNBNQ2BZ","json":"https://pith.science/pith/2BJLVBCZFZDAUO2PK3SNBNQ2BZ.json","graph_json":"https://pith.science/api/pith-number/2BJLVBCZFZDAUO2PK3SNBNQ2BZ/graph.json","events_json":"https://pith.science/api/pith-number/2BJLVBCZFZDAUO2PK3SNBNQ2BZ/events.json","paper":"https://pith.science/paper/2BJLVBCZ"},"agent_actions":{"view_html":"https://pith.science/pith/2BJLVBCZFZDAUO2PK3SNBNQ2BZ","download_json":"https://pith.science/pith/2BJLVBCZFZDAUO2PK3SNBNQ2BZ.json","view_paper":"https://pith.science/paper/2BJLVBCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.12895&json=true","fetch_graph":"https://pith.science/api/pith-number/2BJLVBCZFZDAUO2PK3SNBNQ2BZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2BJLVBCZFZDAUO2PK3SNBNQ2BZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BJLVBCZFZDAUO2PK3SNBNQ2BZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BJLVBCZFZDAUO2PK3SNBNQ2BZ/action/storage_attestation","attest_author":"https://pith.science/pith/2BJLVBCZFZDAUO2PK3SNBNQ2BZ/action/author_attestation","sign_citation":"https://pith.science/pith/2BJLVBCZFZDAUO2PK3SNBNQ2BZ/action/citation_signature","submit_replication":"https://pith.science/pith/2BJLVBCZFZDAUO2PK3SNBNQ2BZ/action/replication_record"}},"created_at":"2026-07-05T06:04:22.123522+00:00","updated_at":"2026-07-05T06:04:22.123522+00:00"}