{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SXDPRZQ4MQNPG6SUXRMHGIH7HK","short_pith_number":"pith:SXDPRZQ4","canonical_record":{"source":{"id":"2608.02343","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T14:57:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5f43d25863c750b60a1b025b4a418f8da6ffb2f449498e8518a93c8b544fbbe6","abstract_canon_sha256":"fdf11d5c51cee5443d940b3714fe72d4acdabe0e80b92bb8d914e23fd14f6de2"},"schema_version":"1.0"},"canonical_sha256":"95c6f8e61c641af37a54bc587320ff3a87045b499aa32bf6d060ae32f0ee3fa5","source":{"kind":"arxiv","id":"2608.02343","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02343","created_at":"2026-08-04T02:11:51Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02343v1","created_at":"2026-08-04T02:11:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02343","created_at":"2026-08-04T02:11:51Z"},{"alias_kind":"pith_short_12","alias_value":"SXDPRZQ4MQNP","created_at":"2026-08-04T02:11:51Z"},{"alias_kind":"pith_short_16","alias_value":"SXDPRZQ4MQNPG6SU","created_at":"2026-08-04T02:11:51Z"},{"alias_kind":"pith_short_8","alias_value":"SXDPRZQ4","created_at":"2026-08-04T02:11:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SXDPRZQ4MQNPG6SUXRMHGIH7HK","target":"record","payload":{"canonical_record":{"source":{"id":"2608.02343","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T14:57:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5f43d25863c750b60a1b025b4a418f8da6ffb2f449498e8518a93c8b544fbbe6","abstract_canon_sha256":"fdf11d5c51cee5443d940b3714fe72d4acdabe0e80b92bb8d914e23fd14f6de2"},"schema_version":"1.0"},"canonical_sha256":"95c6f8e61c641af37a54bc587320ff3a87045b499aa32bf6d060ae32f0ee3fa5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:11:51.332906Z","signature_b64":"Uw2FnDLDkj3+nyOQLlEzRmR9JuSNUviVp1tftzOo54n9XKerT6/zxtdXsJSZzyLus7/RjZMJaSKbusDB+rUNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95c6f8e61c641af37a54bc587320ff3a87045b499aa32bf6d060ae32f0ee3fa5","last_reissued_at":"2026-08-04T02:11:51.331154Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:11:51.331154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.02343","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":"2026-08-04T02:11:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Naw1W+UEO6rSFbqB7o+cC7I/ReIlrQnMipNNm+0RnfoYFeESZJ7BeYAM0qbFDcLqicZCl6BGBP6hA4x8c1rRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T11:02:29.165332Z"},"content_sha256":"a29e668a5bcfc231005ed71e68fb478fa35d8c3af4d2ca7cfbccef271a454e01","schema_version":"1.0","event_id":"sha256:a29e668a5bcfc231005ed71e68fb478fa35d8c3af4d2ca7cfbccef271a454e01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SXDPRZQ4MQNPG6SUXRMHGIH7HK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jan-Niklas Doerr, Joren Gijsbrechts, Patrick Helm, Stefan Minner","submitted_at":"2026-08-03T14:57:21Z","abstract_excerpt":"Many operational problems are constrained sequential decision processes with large, combinatorial action spaces and interdependent feasibility constraints. Mixed-integer linear programs (MILPs) handle such constraints flexibly but scale poorly in stochastic environments. Deep reinforcement learning (DRL) promises scalable decision rules, but existing methods either penalize constraints rather than enforce them, or rely on feasibility mechanisms that break down once constraints interact. We bridge this gap by embedding a differentiable convex optimization module inside the policy: a neural netw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02343","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/2608.02343/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":"2026-08-04T02:11:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eP1b1/zBzXtGn3FxLe/USvUtFll3yK1WCXe9KDUfdbp5gssZVbjhSa0SNVXqHlVY/fX7viAcWfiPZn3iO1e1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T11:02:29.165852Z"},"content_sha256":"790d1787a208a509447c171e85d31f44a5d8355a27a813fd63bad3e4ec8f4161","schema_version":"1.0","event_id":"sha256:790d1787a208a509447c171e85d31f44a5d8355a27a813fd63bad3e4ec8f4161"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SXDPRZQ4MQNPG6SUXRMHGIH7HK/bundle.json","state_url":"https://pith.science/pith/SXDPRZQ4MQNPG6SUXRMHGIH7HK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SXDPRZQ4MQNPG6SUXRMHGIH7HK/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":"2026-08-23T11:02:29Z","links":{"resolver":"https://pith.science/pith/SXDPRZQ4MQNPG6SUXRMHGIH7HK","bundle":"https://pith.science/pith/SXDPRZQ4MQNPG6SUXRMHGIH7HK/bundle.json","state":"https://pith.science/pith/SXDPRZQ4MQNPG6SUXRMHGIH7HK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SXDPRZQ4MQNPG6SUXRMHGIH7HK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SXDPRZQ4MQNPG6SUXRMHGIH7HK","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":"fdf11d5c51cee5443d940b3714fe72d4acdabe0e80b92bb8d914e23fd14f6de2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T14:57:21Z","title_canon_sha256":"5f43d25863c750b60a1b025b4a418f8da6ffb2f449498e8518a93c8b544fbbe6"},"schema_version":"1.0","source":{"id":"2608.02343","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02343","created_at":"2026-08-04T02:11:51Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02343v1","created_at":"2026-08-04T02:11:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02343","created_at":"2026-08-04T02:11:51Z"},{"alias_kind":"pith_short_12","alias_value":"SXDPRZQ4MQNP","created_at":"2026-08-04T02:11:51Z"},{"alias_kind":"pith_short_16","alias_value":"SXDPRZQ4MQNPG6SU","created_at":"2026-08-04T02:11:51Z"},{"alias_kind":"pith_short_8","alias_value":"SXDPRZQ4","created_at":"2026-08-04T02:11:51Z"}],"graph_snapshots":[{"event_id":"sha256:790d1787a208a509447c171e85d31f44a5d8355a27a813fd63bad3e4ec8f4161","target":"graph","created_at":"2026-08-04T02:11:51Z","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/2608.02343/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many operational problems are constrained sequential decision processes with large, combinatorial action spaces and interdependent feasibility constraints. Mixed-integer linear programs (MILPs) handle such constraints flexibly but scale poorly in stochastic environments. Deep reinforcement learning (DRL) promises scalable decision rules, but existing methods either penalize constraints rather than enforce them, or rely on feasibility mechanisms that break down once constraints interact. We bridge this gap by embedding a differentiable convex optimization module inside the policy: a neural netw","authors_text":"Jan-Niklas Doerr, Joren Gijsbrechts, Patrick Helm, Stefan Minner","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T14:57:21Z","title":"Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02343","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:a29e668a5bcfc231005ed71e68fb478fa35d8c3af4d2ca7cfbccef271a454e01","target":"record","created_at":"2026-08-04T02:11:51Z","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":"fdf11d5c51cee5443d940b3714fe72d4acdabe0e80b92bb8d914e23fd14f6de2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T14:57:21Z","title_canon_sha256":"5f43d25863c750b60a1b025b4a418f8da6ffb2f449498e8518a93c8b544fbbe6"},"schema_version":"1.0","source":{"id":"2608.02343","kind":"arxiv","version":1}},"canonical_sha256":"95c6f8e61c641af37a54bc587320ff3a87045b499aa32bf6d060ae32f0ee3fa5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95c6f8e61c641af37a54bc587320ff3a87045b499aa32bf6d060ae32f0ee3fa5","first_computed_at":"2026-08-04T02:11:51.331154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:11:51.331154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uw2FnDLDkj3+nyOQLlEzRmR9JuSNUviVp1tftzOo54n9XKerT6/zxtdXsJSZzyLus7/RjZMJaSKbusDB+rUNBw==","signature_status":"signed_v1","signed_at":"2026-08-04T02:11:51.332906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02343","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a29e668a5bcfc231005ed71e68fb478fa35d8c3af4d2ca7cfbccef271a454e01","sha256:790d1787a208a509447c171e85d31f44a5d8355a27a813fd63bad3e4ec8f4161"],"state_sha256":"5f8a1214bc73b8b00f01a23ab148036dddb245bea7392d0b880f1c54bcdd12de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hKZ8uUWxD25CrNPHVw3nIFLEm2Lhnn6JeoxWqgeCLnzVNmQmNVhH7scAOmHekgmQVhsT1Ci4GdPjCGMtuZRQBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T11:02:29.170564Z","bundle_sha256":"40538a54632ec7ec37635b39a0e43d951be78227c96cb2bdb0eb638406cf89cc"}}