{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2TYVKWULCAYRCUZGUDC2N3ENM5","short_pith_number":"pith:2TYVKWUL","schema_version":"1.0","canonical_sha256":"d4f1555a8b1031115326a0c5a6ec8d677e0242de4f241d742529ec0129956c4b","source":{"kind":"arxiv","id":"2507.18838","version":1},"attestation_state":"computed","paper":{"title":"Flow Stochastic Segmentation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Avinash Kori, Ben Glocker, Charles Jones, Fabio De Sousa Ribeiro, Omar Todd, Raghav Mehta","submitted_at":"2025-07-24T22:26:28Z","abstract_excerpt":"We introduce the Flow Stochastic Segmentation Network (Flow-SSN), a generative segmentation model family featuring discrete-time autoregressive and modern continuous-time flow variants. We prove fundamental limitations of the low-rank parameterisation of previous methods and show that Flow-SSNs can estimate arbitrarily high-rank pixel-wise covariances without assuming the rank or storing the distributional parameters. Flow-SSNs are also more efficient to sample from than standard diffusion-based segmentation models, thanks to most of the model capacity being allocated to learning the base dist"},"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":"2507.18838","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-24T22:26:28Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fef6c9c36b6540b77e15fb070e73350f11c31e02970dd3e508e6a7c49bcd9115","abstract_canon_sha256":"27f4ac426bd8cb716aa370c220bf76bf57824c3302e45725cd262a7e8862dc29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:59.137416Z","signature_b64":"mslcYD0gKSqQQpqMmzmGY0Ni2IMKsVQMv7C1vRDtRiymEv5HFMWeiMDihnTDynCHQZ1CfO3DGOAruCkshaQjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4f1555a8b1031115326a0c5a6ec8d677e0242de4f241d742529ec0129956c4b","last_reissued_at":"2026-07-05T11:42:59.136962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:59.136962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow Stochastic Segmentation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Avinash Kori, Ben Glocker, Charles Jones, Fabio De Sousa Ribeiro, Omar Todd, Raghav Mehta","submitted_at":"2025-07-24T22:26:28Z","abstract_excerpt":"We introduce the Flow Stochastic Segmentation Network (Flow-SSN), a generative segmentation model family featuring discrete-time autoregressive and modern continuous-time flow variants. We prove fundamental limitations of the low-rank parameterisation of previous methods and show that Flow-SSNs can estimate arbitrarily high-rank pixel-wise covariances without assuming the rank or storing the distributional parameters. Flow-SSNs are also more efficient to sample from than standard diffusion-based segmentation models, thanks to most of the model capacity being allocated to learning the base dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18838","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/2507.18838/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":"2507.18838","created_at":"2026-07-05T11:42:59.137020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18838v1","created_at":"2026-07-05T11:42:59.137020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18838","created_at":"2026-07-05T11:42:59.137020+00:00"},{"alias_kind":"pith_short_12","alias_value":"2TYVKWULCAYR","created_at":"2026-07-05T11:42:59.137020+00:00"},{"alias_kind":"pith_short_16","alias_value":"2TYVKWULCAYRCUZG","created_at":"2026-07-05T11:42:59.137020+00:00"},{"alias_kind":"pith_short_8","alias_value":"2TYVKWUL","created_at":"2026-07-05T11:42:59.137020+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/2TYVKWULCAYRCUZGUDC2N3ENM5","json":"https://pith.science/pith/2TYVKWULCAYRCUZGUDC2N3ENM5.json","graph_json":"https://pith.science/api/pith-number/2TYVKWULCAYRCUZGUDC2N3ENM5/graph.json","events_json":"https://pith.science/api/pith-number/2TYVKWULCAYRCUZGUDC2N3ENM5/events.json","paper":"https://pith.science/paper/2TYVKWUL"},"agent_actions":{"view_html":"https://pith.science/pith/2TYVKWULCAYRCUZGUDC2N3ENM5","download_json":"https://pith.science/pith/2TYVKWULCAYRCUZGUDC2N3ENM5.json","view_paper":"https://pith.science/paper/2TYVKWUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18838&json=true","fetch_graph":"https://pith.science/api/pith-number/2TYVKWULCAYRCUZGUDC2N3ENM5/graph.json","fetch_events":"https://pith.science/api/pith-number/2TYVKWULCAYRCUZGUDC2N3ENM5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2TYVKWULCAYRCUZGUDC2N3ENM5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2TYVKWULCAYRCUZGUDC2N3ENM5/action/storage_attestation","attest_author":"https://pith.science/pith/2TYVKWULCAYRCUZGUDC2N3ENM5/action/author_attestation","sign_citation":"https://pith.science/pith/2TYVKWULCAYRCUZGUDC2N3ENM5/action/citation_signature","submit_replication":"https://pith.science/pith/2TYVKWULCAYRCUZGUDC2N3ENM5/action/replication_record"}},"created_at":"2026-07-05T11:42:59.137020+00:00","updated_at":"2026-07-05T11:42:59.137020+00:00"}