{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6CRN3T5HCWOUVF6KEA4FGDTLS7","short_pith_number":"pith:6CRN3T5H","schema_version":"1.0","canonical_sha256":"f0a2ddcfa7159d4a97ca2038530e6b97dbd71545b389f9b26bee647b6fec00fc","source":{"kind":"arxiv","id":"2605.05629","version":3},"attestation_state":"computed","paper":{"title":"Spherical Flows for Sampling Categorical Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Spherical flows using the von Mises-Fisher distribution reduce categorical sequence sampling to solving a scalar ODE in cosine similarity.","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Gabriele Steidl, Gregor Kornhardt, Jannis Chemseddine","submitted_at":"2026-05-07T03:34:00Z","abstract_excerpt":"We study the problem of learning generative models for discrete sequences in a continuous embedding space. Whereas prior approaches typically operate in Euclidean space or on the probability simplex, we instead work on the sphere $\\mathbb S^{d-1}$. There the von Mises-Fisher (vMF) distribution induces a natural noise process and admits a closed-form conditional score. The conditional velocity is in general intractable. Exploiting the radial symmetry of the vMF density we reduce the continuity equation on $\\mathbb S^{d-1}$ to a scalar ODE in the cosine similarity, whose unique bounded solution "},"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":true},"canonical_record":{"source":{"id":"2605.05629","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-07T03:34:00Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"0a85d3ba640e33adae517a0da42237e37a0d8b61a3f63c2e9037dd15e9e59ac0","abstract_canon_sha256":"3576557003e26bc940a50eba6e5d6d3e4b85351aa2a2f508f5f4a974aa947145"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:50.994325Z","signature_b64":"HRrh2m5xHTpYcF5EscU9ZqeSYubukmSmBN276kVAhhH0ZEYPbrAf/83xsu8oXutT1Si7TQJOJwNRbGt2XS65Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0a2ddcfa7159d4a97ca2038530e6b97dbd71545b389f9b26bee647b6fec00fc","last_reissued_at":"2026-06-03T01:05:50.993923Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:50.993923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spherical Flows for Sampling Categorical Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Spherical flows using the von Mises-Fisher distribution reduce categorical sequence sampling to solving a scalar ODE in cosine similarity.","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Gabriele Steidl, Gregor Kornhardt, Jannis Chemseddine","submitted_at":"2026-05-07T03:34:00Z","abstract_excerpt":"We study the problem of learning generative models for discrete sequences in a continuous embedding space. Whereas prior approaches typically operate in Euclidean space or on the probability simplex, we instead work on the sphere $\\mathbb S^{d-1}$. There the von Mises-Fisher (vMF) distribution induces a natural noise process and admits a closed-form conditional score. The conditional velocity is in general intractable. Exploiting the radial symmetry of the vMF density we reduce the continuity equation on $\\mathbb S^{d-1}$ to a scalar ODE in the cosine similarity, whose unique bounded solution "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Exploiting the radial symmetry of the vMF density we reduce the continuity equation on S^{d-1} to a scalar ODE in the cosine similarity, whose unique bounded solution determines the velocity. The marginal velocity and marginal score on (S^{d-1})^L both decompose into posterior-weighted tangent sums.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the learned posterior (trained only by cross-entropy) is sufficiently accurate to produce stable posterior-weighted sums for both velocity and score during sampling on real discrete data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Spherical vMF flows reduce the continuity equation on the sphere to a scalar ODE in cosine similarity, enabling posterior-weighted sampling of categorical sequences via cross-entropy trained posteriors.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Spherical flows using the von Mises-Fisher distribution reduce categorical sequence sampling to solving a scalar ODE in cosine similarity.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5dba8ad76b754c2ccce72edc53616688e31ad48c202b926eead51abc737cd001"},"source":{"id":"2605.05629","kind":"arxiv","version":3},"verdict":{"id":"46e8b717-95a6-4529-9d2a-318bbb9dc7be","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T01:33:40.029370Z","strongest_claim":"Exploiting the radial symmetry of the vMF density we reduce the continuity equation on S^{d-1} to a scalar ODE in the cosine similarity, whose unique bounded solution determines the velocity. The marginal velocity and marginal score on (S^{d-1})^L both decompose into posterior-weighted tangent sums.","one_line_summary":"Spherical vMF flows reduce the continuity equation on the sphere to a scalar ODE in cosine similarity, enabling posterior-weighted sampling of categorical sequences via cross-entropy trained posteriors.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the learned posterior (trained only by cross-entropy) is sufficiently accurate to produce stable posterior-weighted sums for both velocity and score during sampling on real discrete data.","pith_extraction_headline":"Spherical flows using the von Mises-Fisher distribution reduce categorical sequence sampling to solving a scalar ODE in cosine similarity."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.05629/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T14:02:04.714146Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T09:38:52.990973Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T20:01:19.897579Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T13:24:31.981767Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"acfaac3f4c82d2e922172bb038e481a681472287bb125c8285606cd14f158427"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c78bc3072ef5ee2433ae6dc26c0c34cdaf3450b1d512b9ffb2061b55ed49c911"},"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":"2605.05629","created_at":"2026-06-03T01:05:50.993977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.05629v3","created_at":"2026-06-03T01:05:50.993977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05629","created_at":"2026-06-03T01:05:50.993977+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CRN3T5HCWOU","created_at":"2026-06-03T01:05:50.993977+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CRN3T5HCWOUVF6K","created_at":"2026-06-03T01:05:50.993977+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CRN3T5H","created_at":"2026-06-03T01:05:50.993977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.00714","citing_title":"Self-conditioned Flow Map Language Models via Fixed-point Flows","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CRN3T5HCWOUVF6KEA4FGDTLS7","json":"https://pith.science/pith/6CRN3T5HCWOUVF6KEA4FGDTLS7.json","graph_json":"https://pith.science/api/pith-number/6CRN3T5HCWOUVF6KEA4FGDTLS7/graph.json","events_json":"https://pith.science/api/pith-number/6CRN3T5HCWOUVF6KEA4FGDTLS7/events.json","paper":"https://pith.science/paper/6CRN3T5H"},"agent_actions":{"view_html":"https://pith.science/pith/6CRN3T5HCWOUVF6KEA4FGDTLS7","download_json":"https://pith.science/pith/6CRN3T5HCWOUVF6KEA4FGDTLS7.json","view_paper":"https://pith.science/paper/6CRN3T5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.05629&json=true","fetch_graph":"https://pith.science/api/pith-number/6CRN3T5HCWOUVF6KEA4FGDTLS7/graph.json","fetch_events":"https://pith.science/api/pith-number/6CRN3T5HCWOUVF6KEA4FGDTLS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CRN3T5HCWOUVF6KEA4FGDTLS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CRN3T5HCWOUVF6KEA4FGDTLS7/action/storage_attestation","attest_author":"https://pith.science/pith/6CRN3T5HCWOUVF6KEA4FGDTLS7/action/author_attestation","sign_citation":"https://pith.science/pith/6CRN3T5HCWOUVF6KEA4FGDTLS7/action/citation_signature","submit_replication":"https://pith.science/pith/6CRN3T5HCWOUVF6KEA4FGDTLS7/action/replication_record"}},"created_at":"2026-06-03T01:05:50.993977+00:00","updated_at":"2026-06-03T01:05:50.993977+00:00"}