{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EWF7XLIQDOWOW4UBSOYQX33K3F","short_pith_number":"pith:EWF7XLIQ","canonical_record":{"source":{"id":"2507.13133","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T13:54:42Z","cross_cats_sorted":[],"title_canon_sha256":"e04695b7b467b49aca2908ce1458e768240d3b9ca29623ccb1c8fedeeb251227","abstract_canon_sha256":"a56507d0ecfa8dfcfa491844ac3e756bd67cba4310cf3307ef749d86977d7aee"},"schema_version":"1.0"},"canonical_sha256":"258bfbad101baceb728193b10bef6ad97ff61776f12a7cc0f3bc558d36697b26","source":{"kind":"arxiv","id":"2507.13133","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13133","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13133v1","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13133","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"EWF7XLIQDOWO","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"pith_short_16","alias_value":"EWF7XLIQDOWOW4UB","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"pith_short_8","alias_value":"EWF7XLIQ","created_at":"2026-07-05T11:38:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EWF7XLIQDOWOW4UBSOYQX33K3F","target":"record","payload":{"canonical_record":{"source":{"id":"2507.13133","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T13:54:42Z","cross_cats_sorted":[],"title_canon_sha256":"e04695b7b467b49aca2908ce1458e768240d3b9ca29623ccb1c8fedeeb251227","abstract_canon_sha256":"a56507d0ecfa8dfcfa491844ac3e756bd67cba4310cf3307ef749d86977d7aee"},"schema_version":"1.0"},"canonical_sha256":"258bfbad101baceb728193b10bef6ad97ff61776f12a7cc0f3bc558d36697b26","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:55.266735Z","signature_b64":"JjbloJVOR3gPhhazKEjtO2AB9aduTtngKnAbjQBy+Pemfsa5CsqTSHvSckAQp2O64428x+m4UFXjUGMa6wDkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"258bfbad101baceb728193b10bef6ad97ff61776f12a7cc0f3bc558d36697b26","last_reissued_at":"2026-07-05T11:38:55.266256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:55.266256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.13133","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:38:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A+TMeWYk/XUNPAwHDWaTSH4V70PgXT55glGwf/+cE1tqbbSw/E+CiLmqwfXKTguC0bme1Z2zjPnT/LQ8er13DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:45:40.989898Z"},"content_sha256":"f37df95737e4cbd0ceb78f831b0f8a638ca6c8d4bee1a0b38c48e038d063bc18","schema_version":"1.0","event_id":"sha256:f37df95737e4cbd0ceb78f831b0f8a638ca6c8d4bee1a0b38c48e038d063bc18"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EWF7XLIQDOWOW4UBSOYQX33K3F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NGTM: Substructure-based Neural Graph Topic Model for Interpretable Graph Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dazhong Shen, Ying Sun, Yuanxin Zhuang","submitted_at":"2025-07-17T13:54:42Z","abstract_excerpt":"Graph generation plays a pivotal role across numerous domains, including molecular design and knowledge graph construction. Although existing methods achieve considerable success in generating realistic graphs, their interpretability remains limited, often obscuring the rationale behind structural decisions. To address this challenge, we propose the Neural Graph Topic Model (NGTM), a novel generative framework inspired by topic modeling in natural language processing. NGTM represents graphs as mixtures of latent topics, each defining a distribution over semantically meaningful substructures, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13133","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/2507.13133/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:38:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"37TDz+yb3sC7pPwxFabzdQjnfb8CWIOHYXrpKlWubtU+KBftQuNmXBu9L+ZZe9IcmhuHVOXkabXpPo9wyIIcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:45:40.990426Z"},"content_sha256":"44671699f7cc63a90e5f8f22e6f9f1f7e4968a568d161b52e77a1a9b590bd18b","schema_version":"1.0","event_id":"sha256:44671699f7cc63a90e5f8f22e6f9f1f7e4968a568d161b52e77a1a9b590bd18b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EWF7XLIQDOWOW4UBSOYQX33K3F/bundle.json","state_url":"https://pith.science/pith/EWF7XLIQDOWOW4UBSOYQX33K3F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EWF7XLIQDOWOW4UBSOYQX33K3F/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T04:45:40Z","links":{"resolver":"https://pith.science/pith/EWF7XLIQDOWOW4UBSOYQX33K3F","bundle":"https://pith.science/pith/EWF7XLIQDOWOW4UBSOYQX33K3F/bundle.json","state":"https://pith.science/pith/EWF7XLIQDOWOW4UBSOYQX33K3F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EWF7XLIQDOWOW4UBSOYQX33K3F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EWF7XLIQDOWOW4UBSOYQX33K3F","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a56507d0ecfa8dfcfa491844ac3e756bd67cba4310cf3307ef749d86977d7aee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T13:54:42Z","title_canon_sha256":"e04695b7b467b49aca2908ce1458e768240d3b9ca29623ccb1c8fedeeb251227"},"schema_version":"1.0","source":{"id":"2507.13133","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13133","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13133v1","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13133","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"EWF7XLIQDOWO","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"pith_short_16","alias_value":"EWF7XLIQDOWOW4UB","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"pith_short_8","alias_value":"EWF7XLIQ","created_at":"2026-07-05T11:38:55Z"}],"graph_snapshots":[{"event_id":"sha256:44671699f7cc63a90e5f8f22e6f9f1f7e4968a568d161b52e77a1a9b590bd18b","target":"graph","created_at":"2026-07-05T11:38:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.13133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph generation plays a pivotal role across numerous domains, including molecular design and knowledge graph construction. Although existing methods achieve considerable success in generating realistic graphs, their interpretability remains limited, often obscuring the rationale behind structural decisions. To address this challenge, we propose the Neural Graph Topic Model (NGTM), a novel generative framework inspired by topic modeling in natural language processing. NGTM represents graphs as mixtures of latent topics, each defining a distribution over semantically meaningful substructures, w","authors_text":"Dazhong Shen, Ying Sun, Yuanxin Zhuang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T13:54:42Z","title":"NGTM: Substructure-based Neural Graph Topic Model for Interpretable Graph Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13133","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f37df95737e4cbd0ceb78f831b0f8a638ca6c8d4bee1a0b38c48e038d063bc18","target":"record","created_at":"2026-07-05T11:38:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a56507d0ecfa8dfcfa491844ac3e756bd67cba4310cf3307ef749d86977d7aee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T13:54:42Z","title_canon_sha256":"e04695b7b467b49aca2908ce1458e768240d3b9ca29623ccb1c8fedeeb251227"},"schema_version":"1.0","source":{"id":"2507.13133","kind":"arxiv","version":1}},"canonical_sha256":"258bfbad101baceb728193b10bef6ad97ff61776f12a7cc0f3bc558d36697b26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"258bfbad101baceb728193b10bef6ad97ff61776f12a7cc0f3bc558d36697b26","first_computed_at":"2026-07-05T11:38:55.266256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:55.266256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JjbloJVOR3gPhhazKEjtO2AB9aduTtngKnAbjQBy+Pemfsa5CsqTSHvSckAQp2O64428x+m4UFXjUGMa6wDkBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:55.266735Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13133","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f37df95737e4cbd0ceb78f831b0f8a638ca6c8d4bee1a0b38c48e038d063bc18","sha256:44671699f7cc63a90e5f8f22e6f9f1f7e4968a568d161b52e77a1a9b590bd18b"],"state_sha256":"325e2a2f8674c66dea6e8fb53f3ef62f86fb178733b3090e00c7cac3c465cac3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wQZj7ph/CPSjjH2aFBKZM4GNBDuA7fumwBMaoKlDnOu6l3vuhce0UsxCaJ7xDsVIf+MetvtPovL1tOZjwVVmBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T04:45:40.995495Z","bundle_sha256":"07ec0a77f766e14133b8452171ff0023110410e4e26a176926902a7d95502fb3"}}