{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KOLB7YFGTFXY4R6BTU5HQ7DB6A","short_pith_number":"pith:KOLB7YFG","schema_version":"1.0","canonical_sha256":"53961fe0a6996f8e47c19d3a787c61f01054a1873b8822032381d4c9eaed003f","source":{"kind":"arxiv","id":"2602.13061","version":2},"attestation_state":"computed","paper":{"title":"Native Extrapolation Awareness in Flow-Based Conditional Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Constantinos Tsakonas, Jean-Baptiste Mouret, Serena Ivaldi","submitted_at":"2026-02-13T16:15:58Z","abstract_excerpt":"The ability of Flow Matching (FM) to model complex conditional distributions has established it as the state-of-the-art for prediction tasks (e.g., robotics, weather forecasting). However, deployment in safety-critical settings is hindered by a critical extrapolation hazard: driven by smoothness biases, flow models yield plausible outputs even for off-manifold conditions, resulting in silent failures indistinguishable from valid predictions. In this work, we introduce Diverging Flows, a novel approach that enables a single model to simultaneously perform conditional generation and native extra"},"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":"2602.13061","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-13T16:15:58Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1e0ec41815d2ec36e7105fb643045d84975d1b0ff7f8097898be315611c4fba8","abstract_canon_sha256":"06d933e824b8c9bd1b6bfba4c727a9ba4d085f662dd16ceb2bb7bd28828f6e60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:20:44.852938Z","signature_b64":"FEuoWGvLgO7bF3+vsnADBctjP3xpnLjC6pWwubjQtG38Vmm4VQueebT2CPqeLKTgNRMjJ/MosJ8MZslwtijeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53961fe0a6996f8e47c19d3a787c61f01054a1873b8822032381d4c9eaed003f","last_reissued_at":"2026-07-17T00:20:44.852004Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:20:44.852004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Native Extrapolation Awareness in Flow-Based Conditional Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Constantinos Tsakonas, Jean-Baptiste Mouret, Serena Ivaldi","submitted_at":"2026-02-13T16:15:58Z","abstract_excerpt":"The ability of Flow Matching (FM) to model complex conditional distributions has established it as the state-of-the-art for prediction tasks (e.g., robotics, weather forecasting). However, deployment in safety-critical settings is hindered by a critical extrapolation hazard: driven by smoothness biases, flow models yield plausible outputs even for off-manifold conditions, resulting in silent failures indistinguishable from valid predictions. In this work, we introduce Diverging Flows, a novel approach that enables a single model to simultaneously perform conditional generation and native extra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.13061","kind":"arxiv","version":2},"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/2602.13061/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":"2602.13061","created_at":"2026-07-17T00:20:44.852453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.13061v2","created_at":"2026-07-17T00:20:44.852453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.13061","created_at":"2026-07-17T00:20:44.852453+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOLB7YFGTFXY","created_at":"2026-07-17T00:20:44.852453+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOLB7YFGTFXY4R6B","created_at":"2026-07-17T00:20:44.852453+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOLB7YFG","created_at":"2026-07-17T00:20:44.852453+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/KOLB7YFGTFXY4R6BTU5HQ7DB6A","json":"https://pith.science/pith/KOLB7YFGTFXY4R6BTU5HQ7DB6A.json","graph_json":"https://pith.science/api/pith-number/KOLB7YFGTFXY4R6BTU5HQ7DB6A/graph.json","events_json":"https://pith.science/api/pith-number/KOLB7YFGTFXY4R6BTU5HQ7DB6A/events.json","paper":"https://pith.science/paper/KOLB7YFG"},"agent_actions":{"view_html":"https://pith.science/pith/KOLB7YFGTFXY4R6BTU5HQ7DB6A","download_json":"https://pith.science/pith/KOLB7YFGTFXY4R6BTU5HQ7DB6A.json","view_paper":"https://pith.science/paper/KOLB7YFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.13061&json=true","fetch_graph":"https://pith.science/api/pith-number/KOLB7YFGTFXY4R6BTU5HQ7DB6A/graph.json","fetch_events":"https://pith.science/api/pith-number/KOLB7YFGTFXY4R6BTU5HQ7DB6A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOLB7YFGTFXY4R6BTU5HQ7DB6A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOLB7YFGTFXY4R6BTU5HQ7DB6A/action/storage_attestation","attest_author":"https://pith.science/pith/KOLB7YFGTFXY4R6BTU5HQ7DB6A/action/author_attestation","sign_citation":"https://pith.science/pith/KOLB7YFGTFXY4R6BTU5HQ7DB6A/action/citation_signature","submit_replication":"https://pith.science/pith/KOLB7YFGTFXY4R6BTU5HQ7DB6A/action/replication_record"}},"created_at":"2026-07-17T00:20:44.852453+00:00","updated_at":"2026-07-17T00:20:44.852453+00:00"}