{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NUIAVLIMYME7U7DKGY3TIIEZT2","short_pith_number":"pith:NUIAVLIM","schema_version":"1.0","canonical_sha256":"6d100aad0cc309fa7c6a36373420999e8bd3775d58a4067e94ca29e2f3884390","source":{"kind":"arxiv","id":"2608.06956","version":1},"attestation_state":"computed","paper":{"title":"How Molecular Generative Models Organize Molecular Identity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Alan Aspuru-Guzik, Jens S. Bakander, Luis Mantilla Calderon, Raul Ortega-Ochoa, Tejs Vegge, Tonio Buonassisi","submitted_at":"2026-08-07T08:32:13Z","abstract_excerpt":"Generative models for matter are often evaluated as samplers over output representations, and their latent spaces are commonly used as proxies for navigating chemical space. Much less is known about how these models internally arrange discrete chemical identities within those representations. We study this arrangement by making molecular identity explicit and pulling it back through the generative process. Through these pullbacks we probe the regions that generate the same object, exposing the trained model's internal repertoire: a fixed partition that determines which objects (novel or not) t"},"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":"2608.06956","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T08:32:13Z","cross_cats_sorted":["physics.chem-ph"],"title_canon_sha256":"3bf0c3da8e988c63b5903063cb6a2ed4e801b739e521630fed2f5a45289ebdee","abstract_canon_sha256":"0d7c32f566fbddf243c6f6fdbd12b50d5609f9d04fbaac2a7a3977f6362cc9b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:12:38.270167Z","signature_b64":"bTad5vLu6YXkM8jw5Ts6I1O6wsqL1/4ZuigrRDcUa/bHVAcL199UNtapzU3bCX6itkKOWcnsjuBhXsB6LxgKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d100aad0cc309fa7c6a36373420999e8bd3775d58a4067e94ca29e2f3884390","last_reissued_at":"2026-08-10T01:12:38.267372Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:12:38.267372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Molecular Generative Models Organize Molecular Identity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Alan Aspuru-Guzik, Jens S. Bakander, Luis Mantilla Calderon, Raul Ortega-Ochoa, Tejs Vegge, Tonio Buonassisi","submitted_at":"2026-08-07T08:32:13Z","abstract_excerpt":"Generative models for matter are often evaluated as samplers over output representations, and their latent spaces are commonly used as proxies for navigating chemical space. Much less is known about how these models internally arrange discrete chemical identities within those representations. We study this arrangement by making molecular identity explicit and pulling it back through the generative process. Through these pullbacks we probe the regions that generate the same object, exposing the trained model's internal repertoire: a fixed partition that determines which objects (novel or not) t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06956","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/2608.06956/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":"2608.06956","created_at":"2026-08-10T01:12:38.268617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06956v1","created_at":"2026-08-10T01:12:38.268617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06956","created_at":"2026-08-10T01:12:38.268617+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUIAVLIMYME7","created_at":"2026-08-10T01:12:38.268617+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUIAVLIMYME7U7DK","created_at":"2026-08-10T01:12:38.268617+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUIAVLIM","created_at":"2026-08-10T01:12:38.268617+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/NUIAVLIMYME7U7DKGY3TIIEZT2","json":"https://pith.science/pith/NUIAVLIMYME7U7DKGY3TIIEZT2.json","graph_json":"https://pith.science/api/pith-number/NUIAVLIMYME7U7DKGY3TIIEZT2/graph.json","events_json":"https://pith.science/api/pith-number/NUIAVLIMYME7U7DKGY3TIIEZT2/events.json","paper":"https://pith.science/paper/NUIAVLIM"},"agent_actions":{"view_html":"https://pith.science/pith/NUIAVLIMYME7U7DKGY3TIIEZT2","download_json":"https://pith.science/pith/NUIAVLIMYME7U7DKGY3TIIEZT2.json","view_paper":"https://pith.science/paper/NUIAVLIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06956&json=true","fetch_graph":"https://pith.science/api/pith-number/NUIAVLIMYME7U7DKGY3TIIEZT2/graph.json","fetch_events":"https://pith.science/api/pith-number/NUIAVLIMYME7U7DKGY3TIIEZT2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUIAVLIMYME7U7DKGY3TIIEZT2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUIAVLIMYME7U7DKGY3TIIEZT2/action/storage_attestation","attest_author":"https://pith.science/pith/NUIAVLIMYME7U7DKGY3TIIEZT2/action/author_attestation","sign_citation":"https://pith.science/pith/NUIAVLIMYME7U7DKGY3TIIEZT2/action/citation_signature","submit_replication":"https://pith.science/pith/NUIAVLIMYME7U7DKGY3TIIEZT2/action/replication_record"}},"created_at":"2026-08-10T01:12:38.268617+00:00","updated_at":"2026-08-10T01:12:38.268617+00:00"}