{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:AHPFPTNVAPEU27A2C754G32EXD","short_pith_number":"pith:AHPFPTNV","canonical_record":{"source":{"id":"2112.05812","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-10T20:12:39Z","cross_cats_sorted":[],"title_canon_sha256":"4752463fde6fb7b8175c3c9111314c13ace3f8b942041eb4733b11b4a897ec24","abstract_canon_sha256":"3392ca06cc04eb21ac08452108b5f2d9086dffa1b6fd367af65e305b31a7fbf0"},"schema_version":"1.0"},"canonical_sha256":"01de57cdb503c94d7c1a17fbc36f44b8f6c0e25452f2f0cd79ba42b3bf0e3677","source":{"kind":"arxiv","id":"2112.05812","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.05812","created_at":"2026-07-05T04:47:25Z"},{"alias_kind":"arxiv_version","alias_value":"2112.05812v2","created_at":"2026-07-05T04:47:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05812","created_at":"2026-07-05T04:47:25Z"},{"alias_kind":"pith_short_12","alias_value":"AHPFPTNVAPEU","created_at":"2026-07-05T04:47:25Z"},{"alias_kind":"pith_short_16","alias_value":"AHPFPTNVAPEU27A2","created_at":"2026-07-05T04:47:25Z"},{"alias_kind":"pith_short_8","alias_value":"AHPFPTNV","created_at":"2026-07-05T04:47:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:AHPFPTNVAPEU27A2C754G32EXD","target":"record","payload":{"canonical_record":{"source":{"id":"2112.05812","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-10T20:12:39Z","cross_cats_sorted":[],"title_canon_sha256":"4752463fde6fb7b8175c3c9111314c13ace3f8b942041eb4733b11b4a897ec24","abstract_canon_sha256":"3392ca06cc04eb21ac08452108b5f2d9086dffa1b6fd367af65e305b31a7fbf0"},"schema_version":"1.0"},"canonical_sha256":"01de57cdb503c94d7c1a17fbc36f44b8f6c0e25452f2f0cd79ba42b3bf0e3677","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:47:25.949480Z","signature_b64":"e7YiecWQd5YbwDJ4CisTUwvMz3THgkkBX1je6YTl+4V3gihX0xmVGYb09/3dXNSX7LMfE5sT377LFSE7yxD8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01de57cdb503c94d7c1a17fbc36f44b8f6c0e25452f2f0cd79ba42b3bf0e3677","last_reissued_at":"2026-07-05T04:47:25.949097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:47:25.949097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.05812","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:47:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VDdwo1Yh6D3jvnPGhLqzwaezlBgzQMhvrj+ODrLKBbwrDK3oD7TikqVsStpzC64+6L+y4sF8ZfUDM/qrHCo8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T07:40:36.143057Z"},"content_sha256":"3e2b1039f5d9cd1c185f3a06246ef4da014f857c74804f23210e5cb5270269de","schema_version":"1.0","event_id":"sha256:3e2b1039f5d9cd1c185f3a06246ef4da014f857c74804f23210e5cb5270269de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:AHPFPTNVAPEU27A2C754G32EXD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Edge-Compatible Reinforcement Learning for Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Georgios Theocharous, James E. Kostas, Philip S. Thomas","submitted_at":"2021-12-10T20:12:39Z","abstract_excerpt":"Most reinforcement learning (RL) recommendation systems designed for edge computing must either synchronize during recommendation selection or depend on an unprincipled patchwork collection of algorithms. In this work, we build on asynchronous coagent policy gradient algorithms \\citep{kostas2020asynchronous} to propose a principled solution to this problem. The class of algorithms that we propose can be distributed over the internet and run asynchronously and in real-time. When a given edge fails to respond to a request for data with sufficient speed, this is not a problem; the algorithm is de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05812","kind":"arxiv","version":2},"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/2112.05812/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":"2026-07-05T04:47:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n5ZhNsqJ7VOyZ3JRyTxQU5hyy+NqTghk7uZdwsee8DNKs1bg1bhia9CmLE6SvZYD7cUmKym7G4Q2KGB8mfxoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T07:40:36.143426Z"},"content_sha256":"408dc3a48b27406fd9de7042687fbf5070d2c8b37a697586155dac493b4ff734","schema_version":"1.0","event_id":"sha256:408dc3a48b27406fd9de7042687fbf5070d2c8b37a697586155dac493b4ff734"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AHPFPTNVAPEU27A2C754G32EXD/bundle.json","state_url":"https://pith.science/pith/AHPFPTNVAPEU27A2C754G32EXD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AHPFPTNVAPEU27A2C754G32EXD/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":"2026-07-17T07:40:36Z","links":{"resolver":"https://pith.science/pith/AHPFPTNVAPEU27A2C754G32EXD","bundle":"https://pith.science/pith/AHPFPTNVAPEU27A2C754G32EXD/bundle.json","state":"https://pith.science/pith/AHPFPTNVAPEU27A2C754G32EXD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AHPFPTNVAPEU27A2C754G32EXD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AHPFPTNVAPEU27A2C754G32EXD","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":"3392ca06cc04eb21ac08452108b5f2d9086dffa1b6fd367af65e305b31a7fbf0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-10T20:12:39Z","title_canon_sha256":"4752463fde6fb7b8175c3c9111314c13ace3f8b942041eb4733b11b4a897ec24"},"schema_version":"1.0","source":{"id":"2112.05812","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.05812","created_at":"2026-07-05T04:47:25Z"},{"alias_kind":"arxiv_version","alias_value":"2112.05812v2","created_at":"2026-07-05T04:47:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05812","created_at":"2026-07-05T04:47:25Z"},{"alias_kind":"pith_short_12","alias_value":"AHPFPTNVAPEU","created_at":"2026-07-05T04:47:25Z"},{"alias_kind":"pith_short_16","alias_value":"AHPFPTNVAPEU27A2","created_at":"2026-07-05T04:47:25Z"},{"alias_kind":"pith_short_8","alias_value":"AHPFPTNV","created_at":"2026-07-05T04:47:25Z"}],"graph_snapshots":[{"event_id":"sha256:408dc3a48b27406fd9de7042687fbf5070d2c8b37a697586155dac493b4ff734","target":"graph","created_at":"2026-07-05T04:47:25Z","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/2112.05812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most reinforcement learning (RL) recommendation systems designed for edge computing must either synchronize during recommendation selection or depend on an unprincipled patchwork collection of algorithms. In this work, we build on asynchronous coagent policy gradient algorithms \\citep{kostas2020asynchronous} to propose a principled solution to this problem. The class of algorithms that we propose can be distributed over the internet and run asynchronously and in real-time. When a given edge fails to respond to a request for data with sufficient speed, this is not a problem; the algorithm is de","authors_text":"Georgios Theocharous, James E. Kostas, Philip S. Thomas","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-10T20:12:39Z","title":"Edge-Compatible Reinforcement Learning for Recommendations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05812","kind":"arxiv","version":2},"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":"sha256:3e2b1039f5d9cd1c185f3a06246ef4da014f857c74804f23210e5cb5270269de","target":"record","created_at":"2026-07-05T04:47:25Z","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":"3392ca06cc04eb21ac08452108b5f2d9086dffa1b6fd367af65e305b31a7fbf0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-10T20:12:39Z","title_canon_sha256":"4752463fde6fb7b8175c3c9111314c13ace3f8b942041eb4733b11b4a897ec24"},"schema_version":"1.0","source":{"id":"2112.05812","kind":"arxiv","version":2}},"canonical_sha256":"01de57cdb503c94d7c1a17fbc36f44b8f6c0e25452f2f0cd79ba42b3bf0e3677","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01de57cdb503c94d7c1a17fbc36f44b8f6c0e25452f2f0cd79ba42b3bf0e3677","first_computed_at":"2026-07-05T04:47:25.949097Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:47:25.949097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e7YiecWQd5YbwDJ4CisTUwvMz3THgkkBX1je6YTl+4V3gihX0xmVGYb09/3dXNSX7LMfE5sT377LFSE7yxD8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:47:25.949480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.05812","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e2b1039f5d9cd1c185f3a06246ef4da014f857c74804f23210e5cb5270269de","sha256:408dc3a48b27406fd9de7042687fbf5070d2c8b37a697586155dac493b4ff734"],"state_sha256":"a90899d706038dc35f20dc3b3fd27f2b363eb436702a409a1282d76982b98423"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hqvV4nyU/hh29QfrLmnaNPpUgDEr16rn90P3tk+dbXJuElEY2K+tk2ns2SRqRO98qesKdMxBfFEOUlqmE4OgDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T07:40:36.145511Z","bundle_sha256":"cfdb49b512a2ac5a60f61b766574b3ca954535752fcdf4bb6fa05d01d621ecde"}}