{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6YSQ7ZYAWHJPFPN4KVEJWBJ6A5","short_pith_number":"pith:6YSQ7ZYA","canonical_record":{"source":{"id":"2505.15514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T13:38:45Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"8e2b7aa656aae532f3fb0aa415405a0c3017cec7dee2ba860b9be79b80a5846b","abstract_canon_sha256":"f1314fe7371076b05b6709b8ff5e6ccb6ebda61932ff889199205eddbd152035"},"schema_version":"1.0"},"canonical_sha256":"f6250fe700b1d2f2bdbc55489b053e07603e066b2973409c1ae2f80506103302","source":{"kind":"arxiv","id":"2505.15514","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15514","created_at":"2026-07-05T11:06:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15514v1","created_at":"2026-07-05T11:06:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15514","created_at":"2026-07-05T11:06:47Z"},{"alias_kind":"pith_short_12","alias_value":"6YSQ7ZYAWHJP","created_at":"2026-07-05T11:06:47Z"},{"alias_kind":"pith_short_16","alias_value":"6YSQ7ZYAWHJPFPN4","created_at":"2026-07-05T11:06:47Z"},{"alias_kind":"pith_short_8","alias_value":"6YSQ7ZYA","created_at":"2026-07-05T11:06:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6YSQ7ZYAWHJPFPN4KVEJWBJ6A5","target":"record","payload":{"canonical_record":{"source":{"id":"2505.15514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T13:38:45Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"8e2b7aa656aae532f3fb0aa415405a0c3017cec7dee2ba860b9be79b80a5846b","abstract_canon_sha256":"f1314fe7371076b05b6709b8ff5e6ccb6ebda61932ff889199205eddbd152035"},"schema_version":"1.0"},"canonical_sha256":"f6250fe700b1d2f2bdbc55489b053e07603e066b2973409c1ae2f80506103302","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:47.068055Z","signature_b64":"iaWCzi8b8hADWg7op7NVVZkplQe9FttnPaog9Rzx4X/lpnBS5rV5cQRHXPM1uWTcL98cGhgFjSPShicYTkrQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6250fe700b1d2f2bdbc55489b053e07603e066b2973409c1ae2f80506103302","last_reissued_at":"2026-07-05T11:06:47.067454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:47.067454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.15514","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":"2026-07-05T11:06:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"emQ7HN6ywKDeRUWmkk0IhOlUch9PgEHzr91T22MxKn6TtHZw+PY1yw2mQGEZJG9aqJW3syaZY5QhB9vZIXRBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:25:08.465116Z"},"content_sha256":"cb9477bae26e325e5d6bc41388b4f957bd632765ffedea6c26fb720132323341","schema_version":"1.0","event_id":"sha256:cb9477bae26e325e5d6bc41388b4f957bd632765ffedea6c26fb720132323341"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6YSQ7ZYAWHJPFPN4KVEJWBJ6A5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AM-PPO: (Advantage) Alpha-Modulation with Proximal Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Soham Sane","submitted_at":"2025-05-21T13:38:45Z","abstract_excerpt":"Proximal Policy Optimization (PPO) is a widely used reinforcement learning algorithm that heavily relies on accurate advantage estimates for stable and efficient training. However, raw advantage signals can exhibit significant variance, noise, and scale-related issues, impeding optimal learning performance. To address this challenge, we introduce Advantage Modulation PPO (AM-PPO), a novel enhancement of PPO that adaptively modulates advantage estimates using a dynamic, non-linear scaling mechanism. This adaptive modulation employs an alpha controller that dynamically adjusts the scaling factor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15514","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/2505.15514/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":"2026-07-05T11:06:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/eRSrNyfJptUCPDkt8zchkTfquSLhnBIHw10txV8XWGlbUD4q69OXjYuBTqEeP8QYhStnvP4spp/d+rE2R5+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:25:08.465626Z"},"content_sha256":"c89cd2a9ebc7a7627451f4efc61946940a9f28b97bbf49485850e0a156bf012d","schema_version":"1.0","event_id":"sha256:c89cd2a9ebc7a7627451f4efc61946940a9f28b97bbf49485850e0a156bf012d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6YSQ7ZYAWHJPFPN4KVEJWBJ6A5/bundle.json","state_url":"https://pith.science/pith/6YSQ7ZYAWHJPFPN4KVEJWBJ6A5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6YSQ7ZYAWHJPFPN4KVEJWBJ6A5/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":"2026-08-10T18:25:08Z","links":{"resolver":"https://pith.science/pith/6YSQ7ZYAWHJPFPN4KVEJWBJ6A5","bundle":"https://pith.science/pith/6YSQ7ZYAWHJPFPN4KVEJWBJ6A5/bundle.json","state":"https://pith.science/pith/6YSQ7ZYAWHJPFPN4KVEJWBJ6A5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6YSQ7ZYAWHJPFPN4KVEJWBJ6A5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6YSQ7ZYAWHJPFPN4KVEJWBJ6A5","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":"f1314fe7371076b05b6709b8ff5e6ccb6ebda61932ff889199205eddbd152035","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T13:38:45Z","title_canon_sha256":"8e2b7aa656aae532f3fb0aa415405a0c3017cec7dee2ba860b9be79b80a5846b"},"schema_version":"1.0","source":{"id":"2505.15514","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15514","created_at":"2026-07-05T11:06:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15514v1","created_at":"2026-07-05T11:06:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15514","created_at":"2026-07-05T11:06:47Z"},{"alias_kind":"pith_short_12","alias_value":"6YSQ7ZYAWHJP","created_at":"2026-07-05T11:06:47Z"},{"alias_kind":"pith_short_16","alias_value":"6YSQ7ZYAWHJPFPN4","created_at":"2026-07-05T11:06:47Z"},{"alias_kind":"pith_short_8","alias_value":"6YSQ7ZYA","created_at":"2026-07-05T11:06:47Z"}],"graph_snapshots":[{"event_id":"sha256:c89cd2a9ebc7a7627451f4efc61946940a9f28b97bbf49485850e0a156bf012d","target":"graph","created_at":"2026-07-05T11:06:47Z","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/2505.15514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Proximal Policy Optimization (PPO) is a widely used reinforcement learning algorithm that heavily relies on accurate advantage estimates for stable and efficient training. However, raw advantage signals can exhibit significant variance, noise, and scale-related issues, impeding optimal learning performance. To address this challenge, we introduce Advantage Modulation PPO (AM-PPO), a novel enhancement of PPO that adaptively modulates advantage estimates using a dynamic, non-linear scaling mechanism. This adaptive modulation employs an alpha controller that dynamically adjusts the scaling factor","authors_text":"Soham Sane","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T13:38:45Z","title":"AM-PPO: (Advantage) Alpha-Modulation with Proximal Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15514","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:cb9477bae26e325e5d6bc41388b4f957bd632765ffedea6c26fb720132323341","target":"record","created_at":"2026-07-05T11:06:47Z","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":"f1314fe7371076b05b6709b8ff5e6ccb6ebda61932ff889199205eddbd152035","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T13:38:45Z","title_canon_sha256":"8e2b7aa656aae532f3fb0aa415405a0c3017cec7dee2ba860b9be79b80a5846b"},"schema_version":"1.0","source":{"id":"2505.15514","kind":"arxiv","version":1}},"canonical_sha256":"f6250fe700b1d2f2bdbc55489b053e07603e066b2973409c1ae2f80506103302","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6250fe700b1d2f2bdbc55489b053e07603e066b2973409c1ae2f80506103302","first_computed_at":"2026-07-05T11:06:47.067454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:47.067454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iaWCzi8b8hADWg7op7NVVZkplQe9FttnPaog9Rzx4X/lpnBS5rV5cQRHXPM1uWTcL98cGhgFjSPShicYTkrQBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:47.068055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15514","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb9477bae26e325e5d6bc41388b4f957bd632765ffedea6c26fb720132323341","sha256:c89cd2a9ebc7a7627451f4efc61946940a9f28b97bbf49485850e0a156bf012d"],"state_sha256":"59c3614e08877c72f29a5f8fb65d796a08746decb40cd25d257778c1ea68a8f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G0yVTbyCvWYgyTNysYt45e/UXcuwf/TU+Ne4/PxvhdnC+x+IPB0RoF6V6jtdL4T8hP5WCj+VKbEtkOjT4uzgCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:25:08.470653Z","bundle_sha256":"2e7295cce6d5a64779be6d639f4828144539582143aabe35fabdb5ea7388af5d"}}