{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2JFWFWLZRRR2SSZUNIW55BTA5M","short_pith_number":"pith:2JFWFWLZ","canonical_record":{"source":{"id":"2506.12025","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T09:29:19Z","cross_cats_sorted":[],"title_canon_sha256":"fd4f567360ffaf6bdd0f78e321e7eea1d9913a1c12a51ab87ea0d7fa388255b1","abstract_canon_sha256":"acbb58f8924ebe3e07b21a7062f542d211f6d708e5fe1bb266a9d50aa1967156"},"schema_version":"1.0"},"canonical_sha256":"d24b62d9798c63a94b346a2dde8660eb026817f680abe70edb2423262fa5e520","source":{"kind":"arxiv","id":"2506.12025","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12025","created_at":"2026-07-05T11:33:24Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12025v3","created_at":"2026-07-05T11:33:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12025","created_at":"2026-07-05T11:33:24Z"},{"alias_kind":"pith_short_12","alias_value":"2JFWFWLZRRR2","created_at":"2026-07-05T11:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"2JFWFWLZRRR2SSZU","created_at":"2026-07-05T11:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"2JFWFWLZ","created_at":"2026-07-05T11:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2JFWFWLZRRR2SSZUNIW55BTA5M","target":"record","payload":{"canonical_record":{"source":{"id":"2506.12025","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T09:29:19Z","cross_cats_sorted":[],"title_canon_sha256":"fd4f567360ffaf6bdd0f78e321e7eea1d9913a1c12a51ab87ea0d7fa388255b1","abstract_canon_sha256":"acbb58f8924ebe3e07b21a7062f542d211f6d708e5fe1bb266a9d50aa1967156"},"schema_version":"1.0"},"canonical_sha256":"d24b62d9798c63a94b346a2dde8660eb026817f680abe70edb2423262fa5e520","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:24.741940Z","signature_b64":"oTkkZLkY4IjHBzRK2CN19Av5lAPQVo+P916Y1F2hR9nTzQkTS6zdWoIbWdJAIzoAwdHaSNVn+9OyYNe7775kBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d24b62d9798c63a94b346a2dde8660eb026817f680abe70edb2423262fa5e520","last_reissued_at":"2026-07-05T11:33:24.741381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:24.741381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.12025","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XBZTnip+qGPLri/p0P40ZnNAW17Lr65jvZ4OLrHh6KWWvPfAvn5OpCJupXhLWh6cTzgHPn/ySBNdmksTg1gaBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:57:59.141146Z"},"content_sha256":"7ef0336d73e29369ae50c06711718be3215e8aec040efbc9dc048a27b08a9bac","schema_version":"1.0","event_id":"sha256:7ef0336d73e29369ae50c06711718be3215e8aec040efbc9dc048a27b08a9bac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2JFWFWLZRRR2SSZUNIW55BTA5M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bertrand Thirion, R\\'emi Flamary, Sonia Mazelet","submitted_at":"2025-05-21T09:29:19Z","abstract_excerpt":"Optimal transport between graphs, based on Gromov-Wasserstein and other extensions, is a powerful tool for comparing and aligning graph structures. However, solving the associated non-convex optimization problems is computationally expensive, which limits the scalability of these methods to large graphs. In this work, we present Unbalanced Learning of Optimal Transport (ULOT), a deep learning method that predicts optimal transport plans between two graphs. Our method is trained by minimizing the fused unbalanced Gromov-Wasserstein (FUGW) loss. We propose a novel neural architecture with cross-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12025","kind":"arxiv","version":3},"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/2506.12025/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sxMukgwdyVhSaZIGNMwsUEmCxFyUmAHDX/gehTx4k39v187EHUf/egRvnTROmmnrHlKeDSpivMA224UTEv8vAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:57:59.141629Z"},"content_sha256":"f44996bef4645ec8ce2b2cf9d24616e8f33592a1f15137134400db2d24da1f97","schema_version":"1.0","event_id":"sha256:f44996bef4645ec8ce2b2cf9d24616e8f33592a1f15137134400db2d24da1f97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2JFWFWLZRRR2SSZUNIW55BTA5M/bundle.json","state_url":"https://pith.science/pith/2JFWFWLZRRR2SSZUNIW55BTA5M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2JFWFWLZRRR2SSZUNIW55BTA5M/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T16:57:59Z","links":{"resolver":"https://pith.science/pith/2JFWFWLZRRR2SSZUNIW55BTA5M","bundle":"https://pith.science/pith/2JFWFWLZRRR2SSZUNIW55BTA5M/bundle.json","state":"https://pith.science/pith/2JFWFWLZRRR2SSZUNIW55BTA5M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2JFWFWLZRRR2SSZUNIW55BTA5M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2JFWFWLZRRR2SSZUNIW55BTA5M","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":"acbb58f8924ebe3e07b21a7062f542d211f6d708e5fe1bb266a9d50aa1967156","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T09:29:19Z","title_canon_sha256":"fd4f567360ffaf6bdd0f78e321e7eea1d9913a1c12a51ab87ea0d7fa388255b1"},"schema_version":"1.0","source":{"id":"2506.12025","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12025","created_at":"2026-07-05T11:33:24Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12025v3","created_at":"2026-07-05T11:33:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12025","created_at":"2026-07-05T11:33:24Z"},{"alias_kind":"pith_short_12","alias_value":"2JFWFWLZRRR2","created_at":"2026-07-05T11:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"2JFWFWLZRRR2SSZU","created_at":"2026-07-05T11:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"2JFWFWLZ","created_at":"2026-07-05T11:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:f44996bef4645ec8ce2b2cf9d24616e8f33592a1f15137134400db2d24da1f97","target":"graph","created_at":"2026-07-05T11:33:24Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.12025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimal transport between graphs, based on Gromov-Wasserstein and other extensions, is a powerful tool for comparing and aligning graph structures. However, solving the associated non-convex optimization problems is computationally expensive, which limits the scalability of these methods to large graphs. In this work, we present Unbalanced Learning of Optimal Transport (ULOT), a deep learning method that predicts optimal transport plans between two graphs. Our method is trained by minimizing the fused unbalanced Gromov-Wasserstein (FUGW) loss. We propose a novel neural architecture with cross-","authors_text":"Bertrand Thirion, R\\'emi Flamary, Sonia Mazelet","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T09:29:19Z","title":"Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12025","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7ef0336d73e29369ae50c06711718be3215e8aec040efbc9dc048a27b08a9bac","target":"record","created_at":"2026-07-05T11:33:24Z","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":"acbb58f8924ebe3e07b21a7062f542d211f6d708e5fe1bb266a9d50aa1967156","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T09:29:19Z","title_canon_sha256":"fd4f567360ffaf6bdd0f78e321e7eea1d9913a1c12a51ab87ea0d7fa388255b1"},"schema_version":"1.0","source":{"id":"2506.12025","kind":"arxiv","version":3}},"canonical_sha256":"d24b62d9798c63a94b346a2dde8660eb026817f680abe70edb2423262fa5e520","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d24b62d9798c63a94b346a2dde8660eb026817f680abe70edb2423262fa5e520","first_computed_at":"2026-07-05T11:33:24.741381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:24.741381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oTkkZLkY4IjHBzRK2CN19Av5lAPQVo+P916Y1F2hR9nTzQkTS6zdWoIbWdJAIzoAwdHaSNVn+9OyYNe7775kBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:24.741940Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12025","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ef0336d73e29369ae50c06711718be3215e8aec040efbc9dc048a27b08a9bac","sha256:f44996bef4645ec8ce2b2cf9d24616e8f33592a1f15137134400db2d24da1f97"],"state_sha256":"e7e84051448df5b2ff94e1a76e34caee42be7b300ee2d1b2086f9765a0b02a40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k0C+yIQNBVyIMwgvq2dMQtqpnvDe3+NiBQUflgUfAfUNYbsucc1cGYO7vifiY+ZxHzw/Ic4sVBAOEXKxO3sHBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T16:57:59.145199Z","bundle_sha256":"f9eb60553d305d9cce8e506aea50b7b3fb0b56aa14ad08de30c4db91d599d324"}}