{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7XKD2IJVL5JUXQGIAUVERMZPS7","short_pith_number":"pith:7XKD2IJV","schema_version":"1.0","canonical_sha256":"fdd43d21355f534bc0c8052a48b32f97dae52245d3774aebc1315d80f18ae4a4","source":{"kind":"arxiv","id":"2607.27372","version":1},"attestation_state":"computed","paper":{"title":"Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Alexi Gladstone, Heng Ji, Yilun Du","submitted_at":"2026-07-29T18:25:17Z","abstract_excerpt":"The deep learning revolution, kicked off by AlexNet, taught us that end-to-end training beats decomposing a problem into hand-designed stages. Generative modeling, however, has remained the exception-despite generative models being remarkably capable, they are still not trained end-to-end. This is because, at its core, generative modeling is about handling distributions with many modes, and existing scalable approaches handle this the same way, by factoring the generation procedure, which prevents end-to-end generation. In this work, we introduce Explorative Modeling, a new paradigm that inste"},"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":"2607.27372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T18:25:17Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"d07021f854185dfdfc7a03a32911ed7217d41b88a118d2d4b2a27441c10696a4","abstract_canon_sha256":"885e47c2641af87eb525088294b6f54819b9d35a3283458a9fe9d61f6609a204"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdd43d21355f534bc0c8052a48b32f97dae52245d3774aebc1315d80f18ae4a4","last_reissued_at":"2026-07-31T00:10:47.825882Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T00:10:47.825882Z"},"graph_snapshot":{"paper":{"title":"Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Alexi Gladstone, Heng Ji, Yilun Du","submitted_at":"2026-07-29T18:25:17Z","abstract_excerpt":"The deep learning revolution, kicked off by AlexNet, taught us that end-to-end training beats decomposing a problem into hand-designed stages. Generative modeling, however, has remained the exception-despite generative models being remarkably capable, they are still not trained end-to-end. This is because, at its core, generative modeling is about handling distributions with many modes, and existing scalable approaches handle this the same way, by factoring the generation procedure, which prevents end-to-end generation. In this work, we introduce Explorative Modeling, a new paradigm that inste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27372","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/2607.27372/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":"2607.27372","created_at":"2026-07-31T00:10:47.828187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27372v1","created_at":"2026-07-31T00:10:47.828187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27372","created_at":"2026-07-31T00:10:47.828187+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XKD2IJVL5JU","created_at":"2026-07-31T00:10:47.828187+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XKD2IJVL5JUXQGI","created_at":"2026-07-31T00:10:47.828187+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XKD2IJV","created_at":"2026-07-31T00:10:47.828187+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/7XKD2IJVL5JUXQGIAUVERMZPS7","json":"https://pith.science/pith/7XKD2IJVL5JUXQGIAUVERMZPS7.json","graph_json":"https://pith.science/api/pith-number/7XKD2IJVL5JUXQGIAUVERMZPS7/graph.json","events_json":"https://pith.science/api/pith-number/7XKD2IJVL5JUXQGIAUVERMZPS7/events.json","paper":"https://pith.science/paper/7XKD2IJV"},"agent_actions":{"view_html":"https://pith.science/pith/7XKD2IJVL5JUXQGIAUVERMZPS7","download_json":"https://pith.science/pith/7XKD2IJVL5JUXQGIAUVERMZPS7.json","view_paper":"https://pith.science/paper/7XKD2IJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27372&json=true","fetch_graph":"https://pith.science/api/pith-number/7XKD2IJVL5JUXQGIAUVERMZPS7/graph.json","fetch_events":"https://pith.science/api/pith-number/7XKD2IJVL5JUXQGIAUVERMZPS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XKD2IJVL5JUXQGIAUVERMZPS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XKD2IJVL5JUXQGIAUVERMZPS7/action/storage_attestation","attest_author":"https://pith.science/pith/7XKD2IJVL5JUXQGIAUVERMZPS7/action/author_attestation","sign_citation":"https://pith.science/pith/7XKD2IJVL5JUXQGIAUVERMZPS7/action/citation_signature","submit_replication":"https://pith.science/pith/7XKD2IJVL5JUXQGIAUVERMZPS7/action/replication_record"}},"created_at":"2026-07-31T00:10:47.828187+00:00","updated_at":"2026-07-31T00:10:47.828187+00:00"}