{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SU2DVCOIORM5KHWPJZ3NQ6UE5Z","short_pith_number":"pith:SU2DVCOI","canonical_record":{"source":{"id":"2605.30201","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:38:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"245ad04f0ee70f7160016701ba1b11c8b514f23ac4b9d1fdbaf58b1e76978d22","abstract_canon_sha256":"bf561a9a284873dac9f56aaba5c83c74b12f8642a7e6e8ae8f4f908cf6ed66e2"},"schema_version":"1.0"},"canonical_sha256":"95343a89c87459d51ecf4e76d87a84ee662dc110bbf67d6514ebbba32401907f","source":{"kind":"arxiv","id":"2605.30201","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30201","created_at":"2026-05-29T02:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30201v1","created_at":"2026-05-29T02:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30201","created_at":"2026-05-29T02:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"SU2DVCOIORM5","created_at":"2026-05-29T02:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"SU2DVCOIORM5KHWP","created_at":"2026-05-29T02:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"SU2DVCOI","created_at":"2026-05-29T02:06:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SU2DVCOIORM5KHWPJZ3NQ6UE5Z","target":"record","payload":{"canonical_record":{"source":{"id":"2605.30201","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:38:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"245ad04f0ee70f7160016701ba1b11c8b514f23ac4b9d1fdbaf58b1e76978d22","abstract_canon_sha256":"bf561a9a284873dac9f56aaba5c83c74b12f8642a7e6e8ae8f4f908cf6ed66e2"},"schema_version":"1.0"},"canonical_sha256":"95343a89c87459d51ecf4e76d87a84ee662dc110bbf67d6514ebbba32401907f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:12.665466Z","signature_b64":"AJZD6wnCxRdUGD7D2n0ac7/UWFQ9SWiSoKwYnqspbznD6Cg0cFKLN0YF5gGGAu3vsBIxEVB1GLkOjBxEoCApCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95343a89c87459d51ecf4e76d87a84ee662dc110bbf67d6514ebbba32401907f","last_reissued_at":"2026-05-29T02:06:12.665108Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:12.665108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.30201","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":"2026-05-29T02:06:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WLipuLUKk4Hou+vh90ItiVVgK7NvnGYpOl4i+Rx/ODLyRewTGPfNeZUzk9eWz1nzUcyFyenk5m9HhvBrkQhuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:58:32.283810Z"},"content_sha256":"6656542009715e42477642df7299d8a9255b16b3e943ba017a2a0da7385ef6a8","schema_version":"1.0","event_id":"sha256:6656542009715e42477642df7299d8a9255b16b3e943ba017a2a0da7385ef6a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SU2DVCOIORM5KHWPJZ3NQ6UE5Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HPO: Hysteretic Policy Optimization for Stable and Efficient Training under Sparse-Reward Regime","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonio De Domenico, Fadhel Ayed, Haozhe Zhang, Mohamed Sana, Nicola Piovesan","submitted_at":"2026-05-28T16:38:21Z","abstract_excerpt":"We investigate a narrow but common failure mode of GRPO-style reinforcement learning in the context of sparse verifiable rewards: early updates contain more responses with negative advantages than those with positive advantages, while response-level length normalization ties the magnitude of the update to the length of the output. We propose Hysteretic Policy Optimization (HPO), a minimal modification of GRPO that reduces the weight of negative-advantage updates and replaces per-response length normalization with mean-length normalization. We further introduce Adaptive HPO (A-HPO), which sets "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30201","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/2605.30201/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":"2026-05-29T02:06:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KuF9Xpw6UkdZThIOjd8RpIO49KUxyvQzRG24E5WYbyN8TttDZJ1TsxQJTCI7ApAn0m8Crgm5fBQKHRECaBWsCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:58:32.284820Z"},"content_sha256":"9eefb05c8633ac848cc5b9647c7d56106e2e94c6cb8b387a1b6f35a572d921c3","schema_version":"1.0","event_id":"sha256:9eefb05c8633ac848cc5b9647c7d56106e2e94c6cb8b387a1b6f35a572d921c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SU2DVCOIORM5KHWPJZ3NQ6UE5Z/bundle.json","state_url":"https://pith.science/pith/SU2DVCOIORM5KHWPJZ3NQ6UE5Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SU2DVCOIORM5KHWPJZ3NQ6UE5Z/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":"2026-08-10T03:58:32Z","links":{"resolver":"https://pith.science/pith/SU2DVCOIORM5KHWPJZ3NQ6UE5Z","bundle":"https://pith.science/pith/SU2DVCOIORM5KHWPJZ3NQ6UE5Z/bundle.json","state":"https://pith.science/pith/SU2DVCOIORM5KHWPJZ3NQ6UE5Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SU2DVCOIORM5KHWPJZ3NQ6UE5Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SU2DVCOIORM5KHWPJZ3NQ6UE5Z","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":"bf561a9a284873dac9f56aaba5c83c74b12f8642a7e6e8ae8f4f908cf6ed66e2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:38:21Z","title_canon_sha256":"245ad04f0ee70f7160016701ba1b11c8b514f23ac4b9d1fdbaf58b1e76978d22"},"schema_version":"1.0","source":{"id":"2605.30201","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30201","created_at":"2026-05-29T02:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30201v1","created_at":"2026-05-29T02:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30201","created_at":"2026-05-29T02:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"SU2DVCOIORM5","created_at":"2026-05-29T02:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"SU2DVCOIORM5KHWP","created_at":"2026-05-29T02:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"SU2DVCOI","created_at":"2026-05-29T02:06:12Z"}],"graph_snapshots":[{"event_id":"sha256:9eefb05c8633ac848cc5b9647c7d56106e2e94c6cb8b387a1b6f35a572d921c3","target":"graph","created_at":"2026-05-29T02:06:12Z","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/2605.30201/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate a narrow but common failure mode of GRPO-style reinforcement learning in the context of sparse verifiable rewards: early updates contain more responses with negative advantages than those with positive advantages, while response-level length normalization ties the magnitude of the update to the length of the output. We propose Hysteretic Policy Optimization (HPO), a minimal modification of GRPO that reduces the weight of negative-advantage updates and replaces per-response length normalization with mean-length normalization. We further introduce Adaptive HPO (A-HPO), which sets ","authors_text":"Antonio De Domenico, Fadhel Ayed, Haozhe Zhang, Mohamed Sana, Nicola Piovesan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:38:21Z","title":"HPO: Hysteretic Policy Optimization for Stable and Efficient Training under Sparse-Reward Regime"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30201","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":"sha256:6656542009715e42477642df7299d8a9255b16b3e943ba017a2a0da7385ef6a8","target":"record","created_at":"2026-05-29T02:06:12Z","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":"bf561a9a284873dac9f56aaba5c83c74b12f8642a7e6e8ae8f4f908cf6ed66e2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:38:21Z","title_canon_sha256":"245ad04f0ee70f7160016701ba1b11c8b514f23ac4b9d1fdbaf58b1e76978d22"},"schema_version":"1.0","source":{"id":"2605.30201","kind":"arxiv","version":1}},"canonical_sha256":"95343a89c87459d51ecf4e76d87a84ee662dc110bbf67d6514ebbba32401907f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95343a89c87459d51ecf4e76d87a84ee662dc110bbf67d6514ebbba32401907f","first_computed_at":"2026-05-29T02:06:12.665108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:12.665108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AJZD6wnCxRdUGD7D2n0ac7/UWFQ9SWiSoKwYnqspbznD6Cg0cFKLN0YF5gGGAu3vsBIxEVB1GLkOjBxEoCApCg==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:12.665466Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30201","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6656542009715e42477642df7299d8a9255b16b3e943ba017a2a0da7385ef6a8","sha256:9eefb05c8633ac848cc5b9647c7d56106e2e94c6cb8b387a1b6f35a572d921c3"],"state_sha256":"65f9eda200455c9aacf718658024ff6b5d0c9608821d79e9c83b0673d10b857c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S8YtsosWsuJyj/3IMwYrntSOolAjRxlvAWudZkcsyvMYRLi1gVACb21FROHemvTem2BXJJ+QV/YkHyzRVzSBDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:58:32.322101Z","bundle_sha256":"4464093cee09ab50d75559c34a23aa30f75b08acbde14a18953fcfa1a4817706"}}