{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BPHKZV6NKKDOUBH7GYQX2UTKEQ","short_pith_number":"pith:BPHKZV6N","canonical_record":{"source":{"id":"2605.28134","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-27T08:20:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"83d491c4aeab19f513f7f073f88a35a671bfc33586249546f72ca32cc8ea59ad","abstract_canon_sha256":"5e964ae3b781bf1569645dbcdbf0f2586f5cdb2b1d623d6cfbbeb49d9f42f5d5"},"schema_version":"1.0"},"canonical_sha256":"0bceacd7cd5286ea04ff36217d526a241f011dccc2a76b7577daba99dad4ec6d","source":{"kind":"arxiv","id":"2605.28134","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28134","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28134v1","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28134","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"BPHKZV6NKKDO","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"BPHKZV6NKKDOUBH7","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"BPHKZV6N","created_at":"2026-05-28T01:05:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BPHKZV6NKKDOUBH7GYQX2UTKEQ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.28134","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-27T08:20:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"83d491c4aeab19f513f7f073f88a35a671bfc33586249546f72ca32cc8ea59ad","abstract_canon_sha256":"5e964ae3b781bf1569645dbcdbf0f2586f5cdb2b1d623d6cfbbeb49d9f42f5d5"},"schema_version":"1.0"},"canonical_sha256":"0bceacd7cd5286ea04ff36217d526a241f011dccc2a76b7577daba99dad4ec6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:00.071651Z","signature_b64":"pdJQ1WL0muss/XXPRfncaIOFu5HZsnlRF6FUdtFghGtQ4mpt4uYaadriHct2OGSVDvzamY7Y4Ftm+eRz0bpoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bceacd7cd5286ea04ff36217d526a241f011dccc2a76b7577daba99dad4ec6d","last_reissued_at":"2026-05-28T01:05:00.071255Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:00.071255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.28134","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xf+ILgeEt7gOqLIAwETbUWT2WBSKDGiarS/V1jFP6oVQ1/JjscPQSflC+GfJoRZCWUKj7aHgH4105OTICC9OAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T21:32:12.776907Z"},"content_sha256":"e6d9e6a15dcd8762e5f5eac435a238fbce3c6bd75380306444fe3604722e1e73","schema_version":"1.0","event_id":"sha256:e6d9e6a15dcd8762e5f5eac435a238fbce3c6bd75380306444fe3604722e1e73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BPHKZV6NKKDOUBH7GYQX2UTKEQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convergence of empirical subgradients for optimal transport-based objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Tam Le (LPSM, UPCit\\'e)","submitted_at":"2026-05-27T08:20:24Z","abstract_excerpt":"Optimal transport is widely used to learn distributions, enforce distributional constraints, and model uncertainty. In applications, transport losses are often computed from samples through tractable representations, such as one-dimensional sorting formulas or sliced Wasserstein costs, making them practical components in training pipelines. We study parameterized objectives defined by sampled transport costs and prove graphical convergence of their subdifferentials to the subdifferential of the population objective. In particular, this ensures that standard subgradient methods consistently app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28134","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/2605.28134/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":"2026-05-28T01:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cSgpxhuQIjwD/hErsksSNxADvuBwqHc+8dXUm974YEGZHiAEBM6GTZhJKRtMsjsM6k1VXFgz0wfJusSyvBmMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T21:32:12.777274Z"},"content_sha256":"fd29837171661f0727e8be7b4778d3f8eee2aced3f4b69297d38a6fb8f16f55c","schema_version":"1.0","event_id":"sha256:fd29837171661f0727e8be7b4778d3f8eee2aced3f4b69297d38a6fb8f16f55c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BPHKZV6NKKDOUBH7GYQX2UTKEQ/bundle.json","state_url":"https://pith.science/pith/BPHKZV6NKKDOUBH7GYQX2UTKEQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BPHKZV6NKKDOUBH7GYQX2UTKEQ/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":"2026-06-29T21:32:12Z","links":{"resolver":"https://pith.science/pith/BPHKZV6NKKDOUBH7GYQX2UTKEQ","bundle":"https://pith.science/pith/BPHKZV6NKKDOUBH7GYQX2UTKEQ/bundle.json","state":"https://pith.science/pith/BPHKZV6NKKDOUBH7GYQX2UTKEQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BPHKZV6NKKDOUBH7GYQX2UTKEQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BPHKZV6NKKDOUBH7GYQX2UTKEQ","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":"5e964ae3b781bf1569645dbcdbf0f2586f5cdb2b1d623d6cfbbeb49d9f42f5d5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-27T08:20:24Z","title_canon_sha256":"83d491c4aeab19f513f7f073f88a35a671bfc33586249546f72ca32cc8ea59ad"},"schema_version":"1.0","source":{"id":"2605.28134","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28134","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28134v1","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28134","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"BPHKZV6NKKDO","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"BPHKZV6NKKDOUBH7","created_at":"2026-05-28T01:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"BPHKZV6N","created_at":"2026-05-28T01:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:fd29837171661f0727e8be7b4778d3f8eee2aced3f4b69297d38a6fb8f16f55c","target":"graph","created_at":"2026-05-28T01:05:00Z","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/2605.28134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimal transport is widely used to learn distributions, enforce distributional constraints, and model uncertainty. In applications, transport losses are often computed from samples through tractable representations, such as one-dimensional sorting formulas or sliced Wasserstein costs, making them practical components in training pipelines. We study parameterized objectives defined by sampled transport costs and prove graphical convergence of their subdifferentials to the subdifferential of the population objective. In particular, this ensures that standard subgradient methods consistently app","authors_text":"Tam Le (LPSM, UPCit\\'e)","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-27T08:20:24Z","title":"Convergence of empirical subgradients for optimal transport-based objectives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28134","kind":"arxiv","version":1},"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:e6d9e6a15dcd8762e5f5eac435a238fbce3c6bd75380306444fe3604722e1e73","target":"record","created_at":"2026-05-28T01:05:00Z","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":"5e964ae3b781bf1569645dbcdbf0f2586f5cdb2b1d623d6cfbbeb49d9f42f5d5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-27T08:20:24Z","title_canon_sha256":"83d491c4aeab19f513f7f073f88a35a671bfc33586249546f72ca32cc8ea59ad"},"schema_version":"1.0","source":{"id":"2605.28134","kind":"arxiv","version":1}},"canonical_sha256":"0bceacd7cd5286ea04ff36217d526a241f011dccc2a76b7577daba99dad4ec6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bceacd7cd5286ea04ff36217d526a241f011dccc2a76b7577daba99dad4ec6d","first_computed_at":"2026-05-28T01:05:00.071255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:00.071255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pdJQ1WL0muss/XXPRfncaIOFu5HZsnlRF6FUdtFghGtQ4mpt4uYaadriHct2OGSVDvzamY7Y4Ftm+eRz0bpoDQ==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:00.071651Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28134","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6d9e6a15dcd8762e5f5eac435a238fbce3c6bd75380306444fe3604722e1e73","sha256:fd29837171661f0727e8be7b4778d3f8eee2aced3f4b69297d38a6fb8f16f55c"],"state_sha256":"7345c66783c85029e6f4d3276d7a3128e1d5c15b0a19c8fa2324a7361c6914bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CCMFusPs+kqZFUzwxAfb8VQrbFR8rQqLZdU4OYop8WUTeMIc0J9qtCkRkjoJ67zS1Szoe0YA09JlDFFrE/ONAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T21:32:12.779224Z","bundle_sha256":"f91977aa57f131538fe028b74d35a22a91efe5ca25fc759af73a5751bc53c552"}}