{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JWQT7JRUZYE5GUXGWE34F4FXZ3","short_pith_number":"pith:JWQT7JRU","canonical_record":{"source":{"id":"2608.00296","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T21:11:48Z","cross_cats_sorted":[],"title_canon_sha256":"6e8763dfb16c4bb73af157987da7fb7bda664392a258235fee0bec7b2907d995","abstract_canon_sha256":"c4e2b8995a39d8bf2442bdf84c503db748f62e1e0b1b08c251e54401f08c9600"},"schema_version":"1.0"},"canonical_sha256":"4da13fa634ce09d352e6b137c2f0b7cec2d8a26d6f364304ae5b51c6012b9ae6","source":{"kind":"arxiv","id":"2608.00296","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00296","created_at":"2026-08-04T00:34:56Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00296v1","created_at":"2026-08-04T00:34:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00296","created_at":"2026-08-04T00:34:56Z"},{"alias_kind":"pith_short_12","alias_value":"JWQT7JRUZYE5","created_at":"2026-08-04T00:34:56Z"},{"alias_kind":"pith_short_16","alias_value":"JWQT7JRUZYE5GUXG","created_at":"2026-08-04T00:34:56Z"},{"alias_kind":"pith_short_8","alias_value":"JWQT7JRU","created_at":"2026-08-04T00:34:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JWQT7JRUZYE5GUXGWE34F4FXZ3","target":"record","payload":{"canonical_record":{"source":{"id":"2608.00296","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T21:11:48Z","cross_cats_sorted":[],"title_canon_sha256":"6e8763dfb16c4bb73af157987da7fb7bda664392a258235fee0bec7b2907d995","abstract_canon_sha256":"c4e2b8995a39d8bf2442bdf84c503db748f62e1e0b1b08c251e54401f08c9600"},"schema_version":"1.0"},"canonical_sha256":"4da13fa634ce09d352e6b137c2f0b7cec2d8a26d6f364304ae5b51c6012b9ae6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:34:56.184777Z","signature_b64":"1qSsN1iy0CAaZbkPM4jQidRcUH/YDgymJTsL0udzTzkF9xTiantWLntmKM3ZpmiLUba5+p3+34VmHzYzIJDFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4da13fa634ce09d352e6b137c2f0b7cec2d8a26d6f364304ae5b51c6012b9ae6","last_reissued_at":"2026-08-04T00:34:56.183267Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:34:56.183267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.00296","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":"2026-08-04T00:34:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cJrrITNaJNZpw6ve6iTPBTkN2NiM/5smYjlkUzshpfhpCBKquUhXXsag5nDFm002UygVSPe/FVT4kVpJw7viAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:51:17.639440Z"},"content_sha256":"2b16a5ca868355c564d6dbacdc51d909e845393fa9db44530a2f26c129291b48","schema_version":"1.0","event_id":"sha256:2b16a5ca868355c564d6dbacdc51d909e845393fa9db44530a2f26c129291b48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JWQT7JRUZYE5GUXGWE34F4FXZ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stabilized Best-of-$K$ Training for Neural Combinatorial Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Melveena Jolly, Midhun Xavier","submitted_at":"2026-07-31T21:11:48Z","abstract_excerpt":"Leader Reward modifies POMO training to emphasize the best trajectory produced by repeated inference. We test a narrow extension: replace its binary leader/non-leader distinction with a stabilized rank signal indexed by a sampling budget $K$. With the POMO architecture, 3,050-epoch schedule, and TSP-100 test set held fixed, the Leader Reward reimplementation obtains $7.7662$ under 100-start, 8-augmentation greedy decoding, matching the reported $7.766$ at its displayed precision. Under independent sampling, the stabilized $K=8$ recipe lowers realized Best-of-8 cost in all three paired training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00296","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/2608.00296/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":"2026-08-04T00:34:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A62o4mxKbUO/gxb1MxXsHZVCrpDNYkMSCjZUswKJeaw30m6C7bkBiUk1qVQoMRFsAFK1IHU3AFANXaAy4ywzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:51:17.639996Z"},"content_sha256":"e745972a3116944420445534ed6658c60917c7a437fa08dd5ea431254734925f","schema_version":"1.0","event_id":"sha256:e745972a3116944420445534ed6658c60917c7a437fa08dd5ea431254734925f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JWQT7JRUZYE5GUXGWE34F4FXZ3/bundle.json","state_url":"https://pith.science/pith/JWQT7JRUZYE5GUXGWE34F4FXZ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JWQT7JRUZYE5GUXGWE34F4FXZ3/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":"2026-08-10T01:51:17Z","links":{"resolver":"https://pith.science/pith/JWQT7JRUZYE5GUXGWE34F4FXZ3","bundle":"https://pith.science/pith/JWQT7JRUZYE5GUXGWE34F4FXZ3/bundle.json","state":"https://pith.science/pith/JWQT7JRUZYE5GUXGWE34F4FXZ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JWQT7JRUZYE5GUXGWE34F4FXZ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JWQT7JRUZYE5GUXGWE34F4FXZ3","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":"c4e2b8995a39d8bf2442bdf84c503db748f62e1e0b1b08c251e54401f08c9600","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T21:11:48Z","title_canon_sha256":"6e8763dfb16c4bb73af157987da7fb7bda664392a258235fee0bec7b2907d995"},"schema_version":"1.0","source":{"id":"2608.00296","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00296","created_at":"2026-08-04T00:34:56Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00296v1","created_at":"2026-08-04T00:34:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00296","created_at":"2026-08-04T00:34:56Z"},{"alias_kind":"pith_short_12","alias_value":"JWQT7JRUZYE5","created_at":"2026-08-04T00:34:56Z"},{"alias_kind":"pith_short_16","alias_value":"JWQT7JRUZYE5GUXG","created_at":"2026-08-04T00:34:56Z"},{"alias_kind":"pith_short_8","alias_value":"JWQT7JRU","created_at":"2026-08-04T00:34:56Z"}],"graph_snapshots":[{"event_id":"sha256:e745972a3116944420445534ed6658c60917c7a437fa08dd5ea431254734925f","target":"graph","created_at":"2026-08-04T00:34:56Z","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/2608.00296/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Leader Reward modifies POMO training to emphasize the best trajectory produced by repeated inference. We test a narrow extension: replace its binary leader/non-leader distinction with a stabilized rank signal indexed by a sampling budget $K$. With the POMO architecture, 3,050-epoch schedule, and TSP-100 test set held fixed, the Leader Reward reimplementation obtains $7.7662$ under 100-start, 8-augmentation greedy decoding, matching the reported $7.766$ at its displayed precision. Under independent sampling, the stabilized $K=8$ recipe lowers realized Best-of-8 cost in all three paired training","authors_text":"Melveena Jolly, Midhun Xavier","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T21:11:48Z","title":"Stabilized Best-of-$K$ Training for Neural Combinatorial Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00296","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":"sha256:2b16a5ca868355c564d6dbacdc51d909e845393fa9db44530a2f26c129291b48","target":"record","created_at":"2026-08-04T00:34:56Z","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":"c4e2b8995a39d8bf2442bdf84c503db748f62e1e0b1b08c251e54401f08c9600","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T21:11:48Z","title_canon_sha256":"6e8763dfb16c4bb73af157987da7fb7bda664392a258235fee0bec7b2907d995"},"schema_version":"1.0","source":{"id":"2608.00296","kind":"arxiv","version":1}},"canonical_sha256":"4da13fa634ce09d352e6b137c2f0b7cec2d8a26d6f364304ae5b51c6012b9ae6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4da13fa634ce09d352e6b137c2f0b7cec2d8a26d6f364304ae5b51c6012b9ae6","first_computed_at":"2026-08-04T00:34:56.183267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:34:56.183267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1qSsN1iy0CAaZbkPM4jQidRcUH/YDgymJTsL0udzTzkF9xTiantWLntmKM3ZpmiLUba5+p3+34VmHzYzIJDFBg==","signature_status":"signed_v1","signed_at":"2026-08-04T00:34:56.184777Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00296","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b16a5ca868355c564d6dbacdc51d909e845393fa9db44530a2f26c129291b48","sha256:e745972a3116944420445534ed6658c60917c7a437fa08dd5ea431254734925f"],"state_sha256":"4bdeff22ca071cc5fa68ec114ad1540328b03b73e39734150a5c87fa3058ea99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OKZnaFC9aTD3bQht48NWi7aRIBMhGF7nW7THGmSzCPiku9pH6NirOPr9wKCFf52IiQOAd30WDOpxSr8ToFviBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T01:51:17.645935Z","bundle_sha256":"d715ae49cb38e95f6d88a4302483700f33ed3337acfad8026dd461ab8bef960e"}}