{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JRTC37XHTWAP6YTYLZD2BQCPEO","short_pith_number":"pith:JRTC37XH","canonical_record":{"source":{"id":"2606.19587","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-06-17T20:42:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0d5ab582197b02a8d3ffd958956f1ff05d4153b0ff7c349237bb847f1c982ce8","abstract_canon_sha256":"201929c7f799b736ad0ad1538455a0dc98312a0401ee87d9e475a2865fbfcdcb"},"schema_version":"1.0"},"canonical_sha256":"4c662dfee79d80ff62785e47a0c04f238c209df44413f053ab90372b1295b1e3","source":{"kind":"arxiv","id":"2606.19587","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19587","created_at":"2026-06-19T16:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19587v1","created_at":"2026-06-19T16:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19587","created_at":"2026-06-19T16:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"JRTC37XHTWAP","created_at":"2026-06-19T16:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"JRTC37XHTWAP6YTY","created_at":"2026-06-19T16:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"JRTC37XH","created_at":"2026-06-19T16:12:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JRTC37XHTWAP6YTYLZD2BQCPEO","target":"record","payload":{"canonical_record":{"source":{"id":"2606.19587","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-06-17T20:42:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0d5ab582197b02a8d3ffd958956f1ff05d4153b0ff7c349237bb847f1c982ce8","abstract_canon_sha256":"201929c7f799b736ad0ad1538455a0dc98312a0401ee87d9e475a2865fbfcdcb"},"schema_version":"1.0"},"canonical_sha256":"4c662dfee79d80ff62785e47a0c04f238c209df44413f053ab90372b1295b1e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:29.554626Z","signature_b64":"drZ4SSik5PU9xCzVwboTr8sO7g7NVLxTtFRFGFVM2i9eL0nN1DvfasIkmT9+VqbpHxGEADQurCaxop2rGwWEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c662dfee79d80ff62785e47a0c04f238c209df44413f053ab90372b1295b1e3","last_reissued_at":"2026-06-19T16:12:29.554280Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:29.554280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.19587","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":"2026-06-19T16:12:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xNHziLg6wjvNjN1PJvoG49D4J2Dx8q/ZntTLGiO1uGScWBS/n2u3X7x1Ry5elZGXedFr/DbGCDv3H+U5YzvNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T17:04:22.044518Z"},"content_sha256":"ccce1537852cf48ca566abb5c31c2288de0cbf44303aef2bbd4d803713429744","schema_version":"1.0","event_id":"sha256:ccce1537852cf48ca566abb5c31c2288de0cbf44303aef2bbd4d803713429744"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JRTC37XHTWAP6YTYLZD2BQCPEO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Solver-Free Training Method for Predict-then-Optimize","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Beichen Wan, Mo Liu","submitted_at":"2026-06-17T20:42:49Z","abstract_excerpt":"We propose a scalable method for training prediction (machine learning) models in the predict-then-optimize paradigm, where model outputs serve as coefficients for a subsequent linear optimization task. Directly minimizing the empirical decision regret is intractable for linear programming and combinatorial optimization since the decision mapping is piecewise constant, and the gradients are zero almost everywhere. While existing methods address this by smoothing the differentiation process, they suffer from scalability issues, since a computationally expensive solver call is required for every"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19587","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/2606.19587/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":"2026-06-19T16:12:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zQoRde3O21mqC6v1AbRBsRLPSUMHeZWnJd1VsyFjXvVSeWuEu5fGz6WW163cmXt9RLhsmRltU2TE4mjgqbbzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T17:04:22.044908Z"},"content_sha256":"c41e4b9975baf6068df68f50a97929db233bb115c8a352ae951baa5134e5879d","schema_version":"1.0","event_id":"sha256:c41e4b9975baf6068df68f50a97929db233bb115c8a352ae951baa5134e5879d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JRTC37XHTWAP6YTYLZD2BQCPEO/bundle.json","state_url":"https://pith.science/pith/JRTC37XHTWAP6YTYLZD2BQCPEO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JRTC37XHTWAP6YTYLZD2BQCPEO/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":"2026-06-29T17:04:22Z","links":{"resolver":"https://pith.science/pith/JRTC37XHTWAP6YTYLZD2BQCPEO","bundle":"https://pith.science/pith/JRTC37XHTWAP6YTYLZD2BQCPEO/bundle.json","state":"https://pith.science/pith/JRTC37XHTWAP6YTYLZD2BQCPEO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JRTC37XHTWAP6YTYLZD2BQCPEO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JRTC37XHTWAP6YTYLZD2BQCPEO","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":"201929c7f799b736ad0ad1538455a0dc98312a0401ee87d9e475a2865fbfcdcb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-06-17T20:42:49Z","title_canon_sha256":"0d5ab582197b02a8d3ffd958956f1ff05d4153b0ff7c349237bb847f1c982ce8"},"schema_version":"1.0","source":{"id":"2606.19587","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19587","created_at":"2026-06-19T16:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19587v1","created_at":"2026-06-19T16:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19587","created_at":"2026-06-19T16:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"JRTC37XHTWAP","created_at":"2026-06-19T16:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"JRTC37XHTWAP6YTY","created_at":"2026-06-19T16:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"JRTC37XH","created_at":"2026-06-19T16:12:29Z"}],"graph_snapshots":[{"event_id":"sha256:c41e4b9975baf6068df68f50a97929db233bb115c8a352ae951baa5134e5879d","target":"graph","created_at":"2026-06-19T16:12:29Z","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/2606.19587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a scalable method for training prediction (machine learning) models in the predict-then-optimize paradigm, where model outputs serve as coefficients for a subsequent linear optimization task. Directly minimizing the empirical decision regret is intractable for linear programming and combinatorial optimization since the decision mapping is piecewise constant, and the gradients are zero almost everywhere. While existing methods address this by smoothing the differentiation process, they suffer from scalability issues, since a computationally expensive solver call is required for every","authors_text":"Beichen Wan, Mo Liu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-06-17T20:42:49Z","title":"A Solver-Free Training Method for Predict-then-Optimize"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19587","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:ccce1537852cf48ca566abb5c31c2288de0cbf44303aef2bbd4d803713429744","target":"record","created_at":"2026-06-19T16:12:29Z","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":"201929c7f799b736ad0ad1538455a0dc98312a0401ee87d9e475a2865fbfcdcb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-06-17T20:42:49Z","title_canon_sha256":"0d5ab582197b02a8d3ffd958956f1ff05d4153b0ff7c349237bb847f1c982ce8"},"schema_version":"1.0","source":{"id":"2606.19587","kind":"arxiv","version":1}},"canonical_sha256":"4c662dfee79d80ff62785e47a0c04f238c209df44413f053ab90372b1295b1e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c662dfee79d80ff62785e47a0c04f238c209df44413f053ab90372b1295b1e3","first_computed_at":"2026-06-19T16:12:29.554280Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:29.554280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"drZ4SSik5PU9xCzVwboTr8sO7g7NVLxTtFRFGFVM2i9eL0nN1DvfasIkmT9+VqbpHxGEADQurCaxop2rGwWEDQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:29.554626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19587","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccce1537852cf48ca566abb5c31c2288de0cbf44303aef2bbd4d803713429744","sha256:c41e4b9975baf6068df68f50a97929db233bb115c8a352ae951baa5134e5879d"],"state_sha256":"15370ffeb02b6824607af98b6540e2834803a1c4425fa6c6bd7458ecaa650495"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sj+JCi9b75g11b7JNMAG0mC5Gkt5rx/bk6+fZqgr4QPjX2irrVZzpZe34VUcXHXRP/R3DEv7TW/tCd/PPwC6DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T17:04:22.046982Z","bundle_sha256":"da9d184aaf8e857fca7f36881c7ae5351606542af463a107dde8d8ebc3e57a35"}}