{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FSTH5C5XUMQD6GEW7J7H5L2YZQ","short_pith_number":"pith:FSTH5C5X","canonical_record":{"source":{"id":"2606.10321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T02:18:30Z","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"title_canon_sha256":"7081ebd7bb2ae2ee7e4d138a0bf764c45f9780f01e94ab63b8e755574a84e39f","abstract_canon_sha256":"9d46966d4ed2c0dfbfc2817839effedf3f39375d56e03a5e81bc44ae08175322"},"schema_version":"1.0"},"canonical_sha256":"2ca67e8bb7a3203f1896fa7e7eaf58cc1cc21a39a5ad049f67974fe9cd17dbb6","source":{"kind":"arxiv","id":"2606.10321","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10321","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10321v1","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10321","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"FSTH5C5XUMQD","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"FSTH5C5XUMQD6GEW","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"FSTH5C5X","created_at":"2026-06-10T01:10:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FSTH5C5XUMQD6GEW7J7H5L2YZQ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.10321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T02:18:30Z","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"title_canon_sha256":"7081ebd7bb2ae2ee7e4d138a0bf764c45f9780f01e94ab63b8e755574a84e39f","abstract_canon_sha256":"9d46966d4ed2c0dfbfc2817839effedf3f39375d56e03a5e81bc44ae08175322"},"schema_version":"1.0"},"canonical_sha256":"2ca67e8bb7a3203f1896fa7e7eaf58cc1cc21a39a5ad049f67974fe9cd17dbb6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:11.792689Z","signature_b64":"pGi4+Eivn5BCHuLRCH8nFk30Z9rBVxMq5BmLRtvuhyanMb3/zuR354UYIHpDCb2kSktwl+c3zDR1pbgv98NaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ca67e8bb7a3203f1896fa7e7eaf58cc1cc21a39a5ad049f67974fe9cd17dbb6","last_reissued_at":"2026-06-10T01:10:11.791809Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:11.791809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.10321","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":"2026-06-10T01:10:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D2FN0KJPyCPTzBLyg49XOM9gkmAv0sSYZmhg1uy0+UXMkPbbCXS31E0GDaSRSxAmOvLl2t5IzBBbIwWxSCONAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T05:29:38.553668Z"},"content_sha256":"2e3a895ad1592a25c78eb07ba320156d488d92e5a31555e89d73af172c1c9ee2","schema_version":"1.0","event_id":"sha256:2e3a895ad1592a25c78eb07ba320156d488d92e5a31555e89d73af172c1c9ee2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FSTH5C5XUMQD6GEW7J7H5L2YZQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Baseline-Free Policy Optimization for Neural Combinatorial Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","math.OC"],"primary_cat":"cs.LG","authors_text":"Carlos S. Sep\\'ulveda, Gonzalo A. Ruz","submitted_at":"2026-06-09T02:18:30Z","abstract_excerpt":"Neural combinatorial optimization (NCO) trains autoregressive policies to solve routing problems. The standard training algorithm, REINFORCE with a rollout baseline, requires maintaining and periodically updating a frozen copy of the policy for variance reduction. This baseline introduces a structural vulnerability: on harder instances, a poor baseline produces noisy gradient estimates that can destabilize training. We evaluate Group Relative Policy Optimization (GRPO), an algorithm from large language model alignment that eliminates the baseline entirely by normalizing advantages within group"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10321","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/2606.10321/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":"2026-06-10T01:10:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MsHAPUv0r9rGHpcO29xF93Vkbf+mFNlkjRn6PYHlDUa+w8ObqugU09Ukd99oiokAZ1AfT1uDj7rhYluFhBTzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T05:29:38.554053Z"},"content_sha256":"d952b773a3fd9e42e96cd2adff239155dff3bb435e0289953427bd9541c17882","schema_version":"1.0","event_id":"sha256:d952b773a3fd9e42e96cd2adff239155dff3bb435e0289953427bd9541c17882"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FSTH5C5XUMQD6GEW7J7H5L2YZQ/bundle.json","state_url":"https://pith.science/pith/FSTH5C5XUMQD6GEW7J7H5L2YZQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FSTH5C5XUMQD6GEW7J7H5L2YZQ/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":"2026-07-04T05:29:38Z","links":{"resolver":"https://pith.science/pith/FSTH5C5XUMQD6GEW7J7H5L2YZQ","bundle":"https://pith.science/pith/FSTH5C5XUMQD6GEW7J7H5L2YZQ/bundle.json","state":"https://pith.science/pith/FSTH5C5XUMQD6GEW7J7H5L2YZQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FSTH5C5XUMQD6GEW7J7H5L2YZQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FSTH5C5XUMQD6GEW7J7H5L2YZQ","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":"9d46966d4ed2c0dfbfc2817839effedf3f39375d56e03a5e81bc44ae08175322","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T02:18:30Z","title_canon_sha256":"7081ebd7bb2ae2ee7e4d138a0bf764c45f9780f01e94ab63b8e755574a84e39f"},"schema_version":"1.0","source":{"id":"2606.10321","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10321","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10321v1","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10321","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"FSTH5C5XUMQD","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"FSTH5C5XUMQD6GEW","created_at":"2026-06-10T01:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"FSTH5C5X","created_at":"2026-06-10T01:10:11Z"}],"graph_snapshots":[{"event_id":"sha256:d952b773a3fd9e42e96cd2adff239155dff3bb435e0289953427bd9541c17882","target":"graph","created_at":"2026-06-10T01:10:11Z","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/2606.10321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural combinatorial optimization (NCO) trains autoregressive policies to solve routing problems. The standard training algorithm, REINFORCE with a rollout baseline, requires maintaining and periodically updating a frozen copy of the policy for variance reduction. This baseline introduces a structural vulnerability: on harder instances, a poor baseline produces noisy gradient estimates that can destabilize training. We evaluate Group Relative Policy Optimization (GRPO), an algorithm from large language model alignment that eliminates the baseline entirely by normalizing advantages within group","authors_text":"Carlos S. Sep\\'ulveda, Gonzalo A. Ruz","cross_cats":["cs.AI","cs.RO","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T02:18:30Z","title":"Baseline-Free Policy Optimization for Neural Combinatorial Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10321","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":"sha256:2e3a895ad1592a25c78eb07ba320156d488d92e5a31555e89d73af172c1c9ee2","target":"record","created_at":"2026-06-10T01:10:11Z","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":"9d46966d4ed2c0dfbfc2817839effedf3f39375d56e03a5e81bc44ae08175322","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T02:18:30Z","title_canon_sha256":"7081ebd7bb2ae2ee7e4d138a0bf764c45f9780f01e94ab63b8e755574a84e39f"},"schema_version":"1.0","source":{"id":"2606.10321","kind":"arxiv","version":1}},"canonical_sha256":"2ca67e8bb7a3203f1896fa7e7eaf58cc1cc21a39a5ad049f67974fe9cd17dbb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ca67e8bb7a3203f1896fa7e7eaf58cc1cc21a39a5ad049f67974fe9cd17dbb6","first_computed_at":"2026-06-10T01:10:11.791809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:11.791809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pGi4+Eivn5BCHuLRCH8nFk30Z9rBVxMq5BmLRtvuhyanMb3/zuR354UYIHpDCb2kSktwl+c3zDR1pbgv98NaBg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:11.792689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10321","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e3a895ad1592a25c78eb07ba320156d488d92e5a31555e89d73af172c1c9ee2","sha256:d952b773a3fd9e42e96cd2adff239155dff3bb435e0289953427bd9541c17882"],"state_sha256":"3af8f217833b1f8dae859abe1e7c4dafab0836fd1e606b4cd11e71ac2389d57a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vxg7c2YDJG1wIyDFskCSvnm57oFBrFd9dM62V5ROcnc7aar5/3fgBdRE3SINF0XoyeDfVy6qu40Yl05SwG0KAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T05:29:38.556094Z","bundle_sha256":"2bea13a8bbb6c04f5d233ec5149e40ee25f35fe1c883a56fbc9f018edfe4a4a7"}}