{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K6LFOXWGROB7H4UL7N7IKEXKAK","short_pith_number":"pith:K6LFOXWG","schema_version":"1.0","canonical_sha256":"5796575ec68b83f3f28bfb7e8512ea02b2dffcd8cba9c34dd9657a74b29d60fc","source":{"kind":"arxiv","id":"2606.08802","version":1},"attestation_state":"computed","paper":{"title":"Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Bruce Lee, Cheng-Hao Liu, Cristian Perez Jensen, Kimon Protopapas, Pranam Chatterjee, Riccardo De Santi, Sophia Tang, Yisong Yue","submitted_at":"2026-06-07T19:43:22Z","abstract_excerpt":"Standard flow and diffusion pre-training matches the distribution of available data (e.g., molecules), which often covers only a small fraction of the valid design space. In generative discovery, however, one aims to sample valid new-to-nature designs, assigned negligible probability under, and thus inaccessible to, standard models fitted to the observed data. To overcome this limitation, we depart from data distribution matching and view a generative model through its generable set: the region it covers with non-negligible probability. This allows to introduce a new learning principle for out"},"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":"2606.08802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-07T19:43:22Z","cross_cats_sorted":[],"title_canon_sha256":"af3719801b199445d64f0dfe89c222d44a2c91c90f61143add6f7f8ab324fc8a","abstract_canon_sha256":"43e38821f53cf31d8f91bf2e4e0b9e465a805a1b34c99e914fea9164648e8a4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:40.368417Z","signature_b64":"C6c2zZuMbA6XEbnA7rQQf22wfqCtWzA3CBNUDYH6/agRuvRt06vGByHYOMeqqpNFDzTBu5xxDdutrM6l/gUNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5796575ec68b83f3f28bfb7e8512ea02b2dffcd8cba9c34dd9657a74b29d60fc","last_reissued_at":"2026-06-09T02:07:40.367443Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:40.367443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Bruce Lee, Cheng-Hao Liu, Cristian Perez Jensen, Kimon Protopapas, Pranam Chatterjee, Riccardo De Santi, Sophia Tang, Yisong Yue","submitted_at":"2026-06-07T19:43:22Z","abstract_excerpt":"Standard flow and diffusion pre-training matches the distribution of available data (e.g., molecules), which often covers only a small fraction of the valid design space. In generative discovery, however, one aims to sample valid new-to-nature designs, assigned negligible probability under, and thus inaccessible to, standard models fitted to the observed data. To overcome this limitation, we depart from data distribution matching and view a generative model through its generable set: the region it covers with non-negligible probability. This allows to introduce a new learning principle for out"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08802","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/2606.08802/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":"2606.08802","created_at":"2026-06-09T02:07:40.367595+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08802v1","created_at":"2026-06-09T02:07:40.367595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08802","created_at":"2026-06-09T02:07:40.367595+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6LFOXWGROB7","created_at":"2026-06-09T02:07:40.367595+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6LFOXWGROB7H4UL","created_at":"2026-06-09T02:07:40.367595+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6LFOXWG","created_at":"2026-06-09T02:07:40.367595+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/K6LFOXWGROB7H4UL7N7IKEXKAK","json":"https://pith.science/pith/K6LFOXWGROB7H4UL7N7IKEXKAK.json","graph_json":"https://pith.science/api/pith-number/K6LFOXWGROB7H4UL7N7IKEXKAK/graph.json","events_json":"https://pith.science/api/pith-number/K6LFOXWGROB7H4UL7N7IKEXKAK/events.json","paper":"https://pith.science/paper/K6LFOXWG"},"agent_actions":{"view_html":"https://pith.science/pith/K6LFOXWGROB7H4UL7N7IKEXKAK","download_json":"https://pith.science/pith/K6LFOXWGROB7H4UL7N7IKEXKAK.json","view_paper":"https://pith.science/paper/K6LFOXWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08802&json=true","fetch_graph":"https://pith.science/api/pith-number/K6LFOXWGROB7H4UL7N7IKEXKAK/graph.json","fetch_events":"https://pith.science/api/pith-number/K6LFOXWGROB7H4UL7N7IKEXKAK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6LFOXWGROB7H4UL7N7IKEXKAK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6LFOXWGROB7H4UL7N7IKEXKAK/action/storage_attestation","attest_author":"https://pith.science/pith/K6LFOXWGROB7H4UL7N7IKEXKAK/action/author_attestation","sign_citation":"https://pith.science/pith/K6LFOXWGROB7H4UL7N7IKEXKAK/action/citation_signature","submit_replication":"https://pith.science/pith/K6LFOXWGROB7H4UL7N7IKEXKAK/action/replication_record"}},"created_at":"2026-06-09T02:07:40.367595+00:00","updated_at":"2026-06-09T02:07:40.367595+00:00"}