{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FBYIJC6EVTR6FOXCIFH5DQODDK","short_pith_number":"pith:FBYIJC6E","schema_version":"1.0","canonical_sha256":"2870848bc4ace3e2bae2414fd1c1c31a9c4535bdd180c92e12d8e041d7194269","source":{"kind":"arxiv","id":"2602.18084","version":2},"attestation_state":"computed","paper":{"title":"Balancing Symmetry and Efficiency in Graph Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alba Carballo-Castro, Benjamin Honor\\'e, Pascal Frossard, Yiming Qin","submitted_at":"2026-02-20T09:17:57Z","abstract_excerpt":"Equivariance is central to graph generative models, as it ensures the model respects the permutation symmetry of graphs. However, strict equivariance can increase computational cost due to added architectural constraints, and can slow down convergence because the model must be consistent across a large space of possible node permutations. We study this trade-off for graph generative models. Specifically, we start from an equivariant discrete flow-matching model, and relax its equivariance during training via a controllable symmetry modulation scheme based on sinusoidal positional encodings and"},"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":"2602.18084","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-20T09:17:57Z","cross_cats_sorted":[],"title_canon_sha256":"f7efe4dfd5a872502fe91f0899663f5a685e9ae1c8a3ce18268d9eb831b8672b","abstract_canon_sha256":"1fa69a98e6446daad269823f448ca2cf3ef7cb5afa035151a6c975ffbb2b46fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:49.078747Z","signature_b64":"O1A90WyVv9dRXeESoNkNLtqerf0+DmSyCGtptrYVnbU0apwAWa5YBOmRSpxOsdGvJNQPeVRmvWh5jDr8qvOuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2870848bc4ace3e2bae2414fd1c1c31a9c4535bdd180c92e12d8e041d7194269","last_reissued_at":"2026-06-03T01:05:49.078267Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:49.078267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Balancing Symmetry and Efficiency in Graph Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alba Carballo-Castro, Benjamin Honor\\'e, Pascal Frossard, Yiming Qin","submitted_at":"2026-02-20T09:17:57Z","abstract_excerpt":"Equivariance is central to graph generative models, as it ensures the model respects the permutation symmetry of graphs. However, strict equivariance can increase computational cost due to added architectural constraints, and can slow down convergence because the model must be consistent across a large space of possible node permutations. We study this trade-off for graph generative models. Specifically, we start from an equivariant discrete flow-matching model, and relax its equivariance during training via a controllable symmetry modulation scheme based on sinusoidal positional encodings and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.18084","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/2602.18084/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":"2602.18084","created_at":"2026-06-03T01:05:49.078327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.18084v2","created_at":"2026-06-03T01:05:49.078327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.18084","created_at":"2026-06-03T01:05:49.078327+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBYIJC6EVTR6","created_at":"2026-06-03T01:05:49.078327+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBYIJC6EVTR6FOXC","created_at":"2026-06-03T01:05:49.078327+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBYIJC6E","created_at":"2026-06-03T01:05:49.078327+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/FBYIJC6EVTR6FOXCIFH5DQODDK","json":"https://pith.science/pith/FBYIJC6EVTR6FOXCIFH5DQODDK.json","graph_json":"https://pith.science/api/pith-number/FBYIJC6EVTR6FOXCIFH5DQODDK/graph.json","events_json":"https://pith.science/api/pith-number/FBYIJC6EVTR6FOXCIFH5DQODDK/events.json","paper":"https://pith.science/paper/FBYIJC6E"},"agent_actions":{"view_html":"https://pith.science/pith/FBYIJC6EVTR6FOXCIFH5DQODDK","download_json":"https://pith.science/pith/FBYIJC6EVTR6FOXCIFH5DQODDK.json","view_paper":"https://pith.science/paper/FBYIJC6E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.18084&json=true","fetch_graph":"https://pith.science/api/pith-number/FBYIJC6EVTR6FOXCIFH5DQODDK/graph.json","fetch_events":"https://pith.science/api/pith-number/FBYIJC6EVTR6FOXCIFH5DQODDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBYIJC6EVTR6FOXCIFH5DQODDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBYIJC6EVTR6FOXCIFH5DQODDK/action/storage_attestation","attest_author":"https://pith.science/pith/FBYIJC6EVTR6FOXCIFH5DQODDK/action/author_attestation","sign_citation":"https://pith.science/pith/FBYIJC6EVTR6FOXCIFH5DQODDK/action/citation_signature","submit_replication":"https://pith.science/pith/FBYIJC6EVTR6FOXCIFH5DQODDK/action/replication_record"}},"created_at":"2026-06-03T01:05:49.078327+00:00","updated_at":"2026-06-03T01:05:49.078327+00:00"}