{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:POKFP6OCYOCQ64NHNEJG7AT25X","short_pith_number":"pith:POKFP6OC","schema_version":"1.0","canonical_sha256":"7b9457f9c2c3850f71a769126f827aedfad77e473242884f12d147b28b150667","source":{"kind":"arxiv","id":"2605.11125","version":2},"attestation_state":"computed","paper":{"title":"Language Modeling with Hyperspherical Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"S-FLM rotates vectors on the hypersphere to let continuous flow language models approach masked diffusion on reasoning tasks.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Caglar Gulcehre, Justin Deschenaux","submitted_at":"2026-05-11T18:32:32Z","abstract_excerpt":"Discrete Diffusion Language Models progressed rapidly as an alternative to autoregressive (AR) models, motivated by their parallel generation abilities. However, for tractability, discrete diffusion models sample from a factorized distribution, which is less expressive than AR. Recent Flow Language Models (FLMs) apply continuous flows to language, transporting noise to data with a deterministic ODE that avoids factorized sampling. FLMs operate on one-hot vectors whose dimension scales with the vocabulary size, making FLMs costly to train. Moreover, since all distinct one-hot embeddings are equ"},"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":"2605.11125","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T18:32:32Z","cross_cats_sorted":[],"title_canon_sha256":"7dd277264b8017cb3edc7f4dd13a76827cf243306fcffe9f01e74e7f84281b48","abstract_canon_sha256":"4c1d93b0ab4c07bab89bfb895a6b1534d3b13139c60811c54c05609dda45629f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:17.324588Z","signature_b64":"tBjygOxwtcrd/lxY+zcSGUdcMKMkj+JF14SPMpVkwumdvK7l4PAa1Rf+rb95DaWXCrVGU2Zu3O6BvxzgsCXCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b9457f9c2c3850f71a769126f827aedfad77e473242884f12d147b28b150667","last_reissued_at":"2026-05-20T00:03:17.323579Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:17.323579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Modeling with Hyperspherical Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"S-FLM rotates vectors on the hypersphere to let continuous flow language models approach masked diffusion on reasoning tasks.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Caglar Gulcehre, Justin Deschenaux","submitted_at":"2026-05-11T18:32:32Z","abstract_excerpt":"Discrete Diffusion Language Models progressed rapidly as an alternative to autoregressive (AR) models, motivated by their parallel generation abilities. However, for tractability, discrete diffusion models sample from a factorized distribution, which is less expressive than AR. Recent Flow Language Models (FLMs) apply continuous flows to language, transporting noise to data with a deterministic ODE that avoids factorized sampling. FLMs operate on one-hot vectors whose dimension scales with the vocabulary size, making FLMs costly to train. Moreover, since all distinct one-hot embeddings are equ"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"S-FLM substantially improves continuous flow language models on large-vocabulary reasoning and closes the gap to masked diffusion under standard-temperature sampling (T=1), while a gap remains under optimized low-temperature (T=0.1) decoding.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That rotating vectors on the hypersphere along a learned velocity field provides a semantically meaningful transport from noise to data, unlike the equidistant one-hot vectors used in prior FLMs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"S-FLM rotates vectors on a hypersphere using a learned velocity field to generate language sequences, improving continuous flow models on large-vocabulary reasoning and closing the gap to masked diffusion at standard sampling temperature.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"S-FLM rotates vectors on the hypersphere to let continuous flow language models approach masked diffusion on reasoning tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d7eaa57b31220fabfe04bc9dc0d78c8c9d23fc50fd05547c8eb9168c9a0b655e"},"source":{"id":"2605.11125","kind":"arxiv","version":2},"verdict":{"id":"7bdfe128-8a58-47a8-a7d7-28cdece271b0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T06:49:29.117985Z","strongest_claim":"S-FLM substantially improves continuous flow language models on large-vocabulary reasoning and closes the gap to masked diffusion under standard-temperature sampling (T=1), while a gap remains under optimized low-temperature (T=0.1) decoding.","one_line_summary":"S-FLM rotates vectors on a hypersphere using a learned velocity field to generate language sequences, improving continuous flow models on large-vocabulary reasoning and closing the gap to masked diffusion at standard sampling temperature.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That rotating vectors on the hypersphere along a learned velocity field provides a semantically meaningful transport from noise to data, unlike the equidistant one-hot vectors used in prior FLMs.","pith_extraction_headline":"S-FLM rotates vectors on the hypersphere to let continuous flow language models approach masked diffusion on reasoning tasks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.11125/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:34:57.997291Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T10:31:16.785500Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T08:46:22.317458Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"65f1df7664bc36aef18680f71de21c53c557a193e6f0b0bbb155a68e571512a0"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2d14b24349c1215935cae1ca7c3c9d2be462079915fed421e3bfcb02d3ebc7b2"},"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":"2605.11125","created_at":"2026-05-20T00:03:17.323710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.11125v2","created_at":"2026-05-20T00:03:17.323710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11125","created_at":"2026-05-20T00:03:17.323710+00:00"},{"alias_kind":"pith_short_12","alias_value":"POKFP6OCYOCQ","created_at":"2026-05-20T00:03:17.323710+00:00"},{"alias_kind":"pith_short_16","alias_value":"POKFP6OCYOCQ64NH","created_at":"2026-05-20T00:03:17.323710+00:00"},{"alias_kind":"pith_short_8","alias_value":"POKFP6OC","created_at":"2026-05-20T00:03:17.323710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POKFP6OCYOCQ64NHNEJG7AT25X","json":"https://pith.science/pith/POKFP6OCYOCQ64NHNEJG7AT25X.json","graph_json":"https://pith.science/api/pith-number/POKFP6OCYOCQ64NHNEJG7AT25X/graph.json","events_json":"https://pith.science/api/pith-number/POKFP6OCYOCQ64NHNEJG7AT25X/events.json","paper":"https://pith.science/paper/POKFP6OC"},"agent_actions":{"view_html":"https://pith.science/pith/POKFP6OCYOCQ64NHNEJG7AT25X","download_json":"https://pith.science/pith/POKFP6OCYOCQ64NHNEJG7AT25X.json","view_paper":"https://pith.science/paper/POKFP6OC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.11125&json=true","fetch_graph":"https://pith.science/api/pith-number/POKFP6OCYOCQ64NHNEJG7AT25X/graph.json","fetch_events":"https://pith.science/api/pith-number/POKFP6OCYOCQ64NHNEJG7AT25X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POKFP6OCYOCQ64NHNEJG7AT25X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POKFP6OCYOCQ64NHNEJG7AT25X/action/storage_attestation","attest_author":"https://pith.science/pith/POKFP6OCYOCQ64NHNEJG7AT25X/action/author_attestation","sign_citation":"https://pith.science/pith/POKFP6OCYOCQ64NHNEJG7AT25X/action/citation_signature","submit_replication":"https://pith.science/pith/POKFP6OCYOCQ64NHNEJG7AT25X/action/replication_record"}},"created_at":"2026-05-20T00:03:17.323710+00:00","updated_at":"2026-05-20T00:03:17.323710+00:00"}