{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:POKFP6OCYOCQ64NHNEJG7AT25X","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4c1d93b0ab4c07bab89bfb895a6b1534d3b13139c60811c54c05609dda45629f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T18:32:32Z","title_canon_sha256":"7dd277264b8017cb3edc7f4dd13a76827cf243306fcffe9f01e74e7f84281b48"},"schema_version":"1.0","source":{"id":"2605.11125","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.11125","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.11125v2","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11125","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"pith_short_12","alias_value":"POKFP6OCYOCQ","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"pith_short_16","alias_value":"POKFP6OCYOCQ64NH","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"pith_short_8","alias_value":"POKFP6OC","created_at":"2026-05-20T00:03:17Z"}],"graph_snapshots":[{"event_id":"sha256:ab2665c6a86e26cf8feef80cf7cd3fcc946d2756960ef393413950dabccc519e","target":"graph","created_at":"2026-05-20T00:03:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"S-FLM rotates vectors on the hypersphere to let continuous flow language models approach masked diffusion on reasoning tasks."}],"snapshot_sha256":"d7eaa57b31220fabfe04bc9dc0d78c8c9d23fc50fd05547c8eb9168c9a0b655e"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2d14b24349c1215935cae1ca7c3c9d2be462079915fed421e3bfcb02d3ebc7b2"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.11125/integrity.json","findings":[],"snapshot_sha256":"65f1df7664bc36aef18680f71de21c53c557a193e6f0b0bbb155a68e571512a0","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Caglar Gulcehre, Justin Deschenaux","cross_cats":[],"headline":"S-FLM rotates vectors on the hypersphere to let continuous flow language models approach masked diffusion on reasoning tasks.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T18:32:32Z","title":"Language Modeling with Hyperspherical Flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.11125","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T06:49:29.117985Z","id":"7bdfe128-8a58-47a8-a7d7-28cdece271b0","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"S-FLM rotates vectors on the hypersphere to let continuous flow language models approach masked diffusion on reasoning tasks.","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.","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."}},"verdict_id":"7bdfe128-8a58-47a8-a7d7-28cdece271b0"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:279b293fe356fa38783d300ebb4a465ca643d320bda5586db20c40af67664347","target":"record","created_at":"2026-05-20T00:03:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4c1d93b0ab4c07bab89bfb895a6b1534d3b13139c60811c54c05609dda45629f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T18:32:32Z","title_canon_sha256":"7dd277264b8017cb3edc7f4dd13a76827cf243306fcffe9f01e74e7f84281b48"},"schema_version":"1.0","source":{"id":"2605.11125","kind":"arxiv","version":2}},"canonical_sha256":"7b9457f9c2c3850f71a769126f827aedfad77e473242884f12d147b28b150667","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b9457f9c2c3850f71a769126f827aedfad77e473242884f12d147b28b150667","first_computed_at":"2026-05-20T00:03:17.323579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:17.323579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tBjygOxwtcrd/lxY+zcSGUdcMKMkj+JF14SPMpVkwumdvK7l4PAa1Rf+rb95DaWXCrVGU2Zu3O6BvxzgsCXCCA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:17.324588Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.11125","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:279b293fe356fa38783d300ebb4a465ca643d320bda5586db20c40af67664347","sha256:ab2665c6a86e26cf8feef80cf7cd3fcc946d2756960ef393413950dabccc519e"],"state_sha256":"a153dc6ef2f41c10c4e6a342a5706c5025baa53bee261df0a07ea01e4c66927d"}