{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WIXV5TB2YWVE42FQHGLWPOP6BU","short_pith_number":"pith:WIXV5TB2","canonical_record":{"source":{"id":"2509.08721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T16:14:20Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"772544a6e7044ce0d99e7ed1c24ec4c90e5a281902e3429d646e14610af267e0","abstract_canon_sha256":"5edc3c20b7b6f0db258a292f8bbd197c2a6dcd414fef6874a5bd19ecef9fd6c4"},"schema_version":"1.0"},"canonical_sha256":"b22f5ecc3ac5aa4e68b0399767b9fe0d31e7350250a3973baf4f4b1099ca1164","source":{"kind":"arxiv","id":"2509.08721","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08721","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08721v1","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08721","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"pith_short_12","alias_value":"WIXV5TB2YWVE","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"pith_short_16","alias_value":"WIXV5TB2YWVE42FQ","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"pith_short_8","alias_value":"WIXV5TB2","created_at":"2026-07-05T12:08:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WIXV5TB2YWVE42FQHGLWPOP6BU","target":"record","payload":{"canonical_record":{"source":{"id":"2509.08721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T16:14:20Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"772544a6e7044ce0d99e7ed1c24ec4c90e5a281902e3429d646e14610af267e0","abstract_canon_sha256":"5edc3c20b7b6f0db258a292f8bbd197c2a6dcd414fef6874a5bd19ecef9fd6c4"},"schema_version":"1.0"},"canonical_sha256":"b22f5ecc3ac5aa4e68b0399767b9fe0d31e7350250a3973baf4f4b1099ca1164","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:34.918454Z","signature_b64":"KHEZZYDEAhEPu5a3LuM1sAV6Qz5jMTMmhamjWGU3fK72QuU35wQcd0qIMQo9Bs6x3ovr1YcNbxJWMm/gBHMFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b22f5ecc3ac5aa4e68b0399767b9fe0d31e7350250a3973baf4f4b1099ca1164","last_reissued_at":"2026-07-05T12:08:34.917927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:34.917927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.08721","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":"2026-07-05T12:08:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jdrrAQThkvJVbulA3PuviWDHxOAWshdI2jNZvgcrMYFKVvo0BdGILUtoL+fjIrsjvitkZf9tg+X0WJGawIuDBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T01:22:00.838654Z"},"content_sha256":"7b7b1add360186ca5e5a2672dfc69bb0028c2568dc209dfe25cab97b06ecd65a","schema_version":"1.0","event_id":"sha256:7b7b1add360186ca5e5a2672dfc69bb0028c2568dc209dfe25cab97b06ecd65a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WIXV5TB2YWVE42FQHGLWPOP6BU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Austin Virts, Ben Fielding, Christopher Nies, Diogo Ortega, Edward Phillip Flores Nu\\~no, Gabriel Passamani Andrade, Harry Grieve, Jari Kolehmainen, Jeffrey Amico, John Donaghy, Matthew J. Wright, Semih Kara, Shikhar Rastogi, Tristin Forbus, Yihua Lou","submitted_at":"2025-09-10T16:14:20Z","abstract_excerpt":"Post-training language models (LMs) with reinforcement learning (RL) can enhance their complex reasoning capabilities without supervised fine-tuning, as demonstrated by DeepSeek-R1-Zero. However, effectively utilizing RL for LMs requires significant parallelization to scale-up inference, which introduces non-trivial technical challenges (e.g. latency, memory, and reliability) alongside ever-growing financial costs. We present Swarm sAmpling Policy Optimization (SAPO), a fully decentralized and asynchronous RL post-training algorithm. SAPO is designed for decentralized networks of heterogenous "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08721","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/2509.08721/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":"2026-07-05T12:08:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3wFxE7VMZVoTauUmdfljizGUVRT9CqWh5RdpwExWvDkJu3Mv8NPTOkgddfI97p4ZXcx1+rJMgWb5ctwW5ZmlDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T01:22:00.839278Z"},"content_sha256":"51136abd220808d4a712e719e8dccfb1dcaf27622bc946b99502722dfe96b689","schema_version":"1.0","event_id":"sha256:51136abd220808d4a712e719e8dccfb1dcaf27622bc946b99502722dfe96b689"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WIXV5TB2YWVE42FQHGLWPOP6BU/bundle.json","state_url":"https://pith.science/pith/WIXV5TB2YWVE42FQHGLWPOP6BU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WIXV5TB2YWVE42FQHGLWPOP6BU/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":"2026-08-17T01:22:00Z","links":{"resolver":"https://pith.science/pith/WIXV5TB2YWVE42FQHGLWPOP6BU","bundle":"https://pith.science/pith/WIXV5TB2YWVE42FQHGLWPOP6BU/bundle.json","state":"https://pith.science/pith/WIXV5TB2YWVE42FQHGLWPOP6BU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WIXV5TB2YWVE42FQHGLWPOP6BU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WIXV5TB2YWVE42FQHGLWPOP6BU","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":"5edc3c20b7b6f0db258a292f8bbd197c2a6dcd414fef6874a5bd19ecef9fd6c4","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T16:14:20Z","title_canon_sha256":"772544a6e7044ce0d99e7ed1c24ec4c90e5a281902e3429d646e14610af267e0"},"schema_version":"1.0","source":{"id":"2509.08721","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08721","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08721v1","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08721","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"pith_short_12","alias_value":"WIXV5TB2YWVE","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"pith_short_16","alias_value":"WIXV5TB2YWVE42FQ","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"pith_short_8","alias_value":"WIXV5TB2","created_at":"2026-07-05T12:08:34Z"}],"graph_snapshots":[{"event_id":"sha256:51136abd220808d4a712e719e8dccfb1dcaf27622bc946b99502722dfe96b689","target":"graph","created_at":"2026-07-05T12:08:34Z","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/2509.08721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training language models (LMs) with reinforcement learning (RL) can enhance their complex reasoning capabilities without supervised fine-tuning, as demonstrated by DeepSeek-R1-Zero. However, effectively utilizing RL for LMs requires significant parallelization to scale-up inference, which introduces non-trivial technical challenges (e.g. latency, memory, and reliability) alongside ever-growing financial costs. We present Swarm sAmpling Policy Optimization (SAPO), a fully decentralized and asynchronous RL post-training algorithm. SAPO is designed for decentralized networks of heterogenous ","authors_text":"Austin Virts, Ben Fielding, Christopher Nies, Diogo Ortega, Edward Phillip Flores Nu\\~no, Gabriel Passamani Andrade, Harry Grieve, Jari Kolehmainen, Jeffrey Amico, John Donaghy, Matthew J. Wright, Semih Kara, Shikhar Rastogi, Tristin Forbus, Yihua Lou","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T16:14:20Z","title":"Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08721","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":"sha256:7b7b1add360186ca5e5a2672dfc69bb0028c2568dc209dfe25cab97b06ecd65a","target":"record","created_at":"2026-07-05T12:08:34Z","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":"5edc3c20b7b6f0db258a292f8bbd197c2a6dcd414fef6874a5bd19ecef9fd6c4","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T16:14:20Z","title_canon_sha256":"772544a6e7044ce0d99e7ed1c24ec4c90e5a281902e3429d646e14610af267e0"},"schema_version":"1.0","source":{"id":"2509.08721","kind":"arxiv","version":1}},"canonical_sha256":"b22f5ecc3ac5aa4e68b0399767b9fe0d31e7350250a3973baf4f4b1099ca1164","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b22f5ecc3ac5aa4e68b0399767b9fe0d31e7350250a3973baf4f4b1099ca1164","first_computed_at":"2026-07-05T12:08:34.917927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:08:34.917927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KHEZZYDEAhEPu5a3LuM1sAV6Qz5jMTMmhamjWGU3fK72QuU35wQcd0qIMQo9Bs6x3ovr1YcNbxJWMm/gBHMFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:08:34.918454Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.08721","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b7b1add360186ca5e5a2672dfc69bb0028c2568dc209dfe25cab97b06ecd65a","sha256:51136abd220808d4a712e719e8dccfb1dcaf27622bc946b99502722dfe96b689"],"state_sha256":"7f4506712264ca5fc22e3c00094124898d7093edb71099ddf2279e761748fd2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y2RWtm6R1Woha1TSKJDMOMFXibXVgIhV7V0gOhzLjk+8aJVWfgzOEdaWW7ODdltC3FUzeObFf+8pz7jlz2NDCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T01:22:00.842582Z","bundle_sha256":"41d93ae67d284b86fcc310398a6f21bdace77b5c5888ebce7dff3c230f1dc148"}}