{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:U37Y6OAZI6FCWD5S5JQYBTFKN2","short_pith_number":"pith:U37Y6OAZ","canonical_record":{"source":{"id":"2204.02268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-05T15:02:28Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"c94e785b0d8d1acbfa382fa6f83688bc7ec974a36be4434b40715958fc761fc3","abstract_canon_sha256":"6062f6f27cf4241be5408799011bbfd627df625ebdd0b29d535a018b3bd2a0b9"},"schema_version":"1.0"},"canonical_sha256":"a6ff8f3819478a2b0fb2ea6180ccaa6e90d87948deb818c61c5558593ed97f53","source":{"kind":"arxiv","id":"2204.02268","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.02268","created_at":"2026-07-05T04:11:38Z"},{"alias_kind":"arxiv_version","alias_value":"2204.02268v1","created_at":"2026-07-05T04:11:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02268","created_at":"2026-07-05T04:11:38Z"},{"alias_kind":"pith_short_12","alias_value":"U37Y6OAZI6FC","created_at":"2026-07-05T04:11:38Z"},{"alias_kind":"pith_short_16","alias_value":"U37Y6OAZI6FCWD5S","created_at":"2026-07-05T04:11:38Z"},{"alias_kind":"pith_short_8","alias_value":"U37Y6OAZ","created_at":"2026-07-05T04:11:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:U37Y6OAZI6FCWD5S5JQYBTFKN2","target":"record","payload":{"canonical_record":{"source":{"id":"2204.02268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-05T15:02:28Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"c94e785b0d8d1acbfa382fa6f83688bc7ec974a36be4434b40715958fc761fc3","abstract_canon_sha256":"6062f6f27cf4241be5408799011bbfd627df625ebdd0b29d535a018b3bd2a0b9"},"schema_version":"1.0"},"canonical_sha256":"a6ff8f3819478a2b0fb2ea6180ccaa6e90d87948deb818c61c5558593ed97f53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:38.068705Z","signature_b64":"ouVUNVtTbOCHCkXPLYWWtkxCUT4ogZ3q7zhxuNa4IYDt2/wtvb1NdHjezdMZZuv5hgWc7D1v+uhlbuvzDsxuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6ff8f3819478a2b0fb2ea6180ccaa6e90d87948deb818c61c5558593ed97f53","last_reissued_at":"2026-07-05T04:11:38.068330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:38.068330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.02268","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":"2026-07-05T04:11:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QFywMUXNYSMs57bWAqwpq7RgrPTzxiMaahb6GCNhoN2szHhUChM1FZOtrkbWAjebcfg7wCoJhBmALmiAuSNJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:08:16.470632Z"},"content_sha256":"22fca5cd1c968ebf5379b562a3d2dcb4a3dca96d92e6bf2b13f406c02ac09dce","schema_version":"1.0","event_id":"sha256:22fca5cd1c968ebf5379b562a3d2dcb4a3dca96d92e6bf2b13f406c02ac09dce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:U37Y6OAZI6FCWD5S5JQYBTFKN2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Bid Long-Term: Multi-Agent Reinforcement Learning with Long-Term and Sparse Reward in Repeated Auction Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Holger Karl, Jing Tan, Ramin Khalili","submitted_at":"2022-04-05T15:02:28Z","abstract_excerpt":"We propose a multi-agent distributed reinforcement learning algorithm that balances between potentially conflicting short-term reward and sparse, delayed long-term reward, and learns with partial information in a dynamic environment. We compare different long-term rewards to incentivize the algorithm to maximize individual payoff and overall social welfare. We test the algorithm in two simulated auction games, and demonstrate that 1) our algorithm outperforms two benchmark algorithms in a direct competition, with cost to social welfare, and 2) our algorithm's aggressive competitive behavior ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02268","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/2204.02268/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":"2026-07-05T04:11:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EGLoH/jUqGkd3YCg6we4rX4IeXgRJYuAdJ49oY05Nu12f7dSSVPxiu2+ZaibmEpA092BqwbYae8wftUsH6kUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:08:16.471133Z"},"content_sha256":"4789ee7e3dda188d8d99b2da2a64d673c2f2c3eaacfa29707250b2d187351bf1","schema_version":"1.0","event_id":"sha256:4789ee7e3dda188d8d99b2da2a64d673c2f2c3eaacfa29707250b2d187351bf1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U37Y6OAZI6FCWD5S5JQYBTFKN2/bundle.json","state_url":"https://pith.science/pith/U37Y6OAZI6FCWD5S5JQYBTFKN2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U37Y6OAZI6FCWD5S5JQYBTFKN2/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":"2026-08-20T20:08:16Z","links":{"resolver":"https://pith.science/pith/U37Y6OAZI6FCWD5S5JQYBTFKN2","bundle":"https://pith.science/pith/U37Y6OAZI6FCWD5S5JQYBTFKN2/bundle.json","state":"https://pith.science/pith/U37Y6OAZI6FCWD5S5JQYBTFKN2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U37Y6OAZI6FCWD5S5JQYBTFKN2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:U37Y6OAZI6FCWD5S5JQYBTFKN2","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":"6062f6f27cf4241be5408799011bbfd627df625ebdd0b29d535a018b3bd2a0b9","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-05T15:02:28Z","title_canon_sha256":"c94e785b0d8d1acbfa382fa6f83688bc7ec974a36be4434b40715958fc761fc3"},"schema_version":"1.0","source":{"id":"2204.02268","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.02268","created_at":"2026-07-05T04:11:38Z"},{"alias_kind":"arxiv_version","alias_value":"2204.02268v1","created_at":"2026-07-05T04:11:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02268","created_at":"2026-07-05T04:11:38Z"},{"alias_kind":"pith_short_12","alias_value":"U37Y6OAZI6FC","created_at":"2026-07-05T04:11:38Z"},{"alias_kind":"pith_short_16","alias_value":"U37Y6OAZI6FCWD5S","created_at":"2026-07-05T04:11:38Z"},{"alias_kind":"pith_short_8","alias_value":"U37Y6OAZ","created_at":"2026-07-05T04:11:38Z"}],"graph_snapshots":[{"event_id":"sha256:4789ee7e3dda188d8d99b2da2a64d673c2f2c3eaacfa29707250b2d187351bf1","target":"graph","created_at":"2026-07-05T04:11:38Z","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/2204.02268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a multi-agent distributed reinforcement learning algorithm that balances between potentially conflicting short-term reward and sparse, delayed long-term reward, and learns with partial information in a dynamic environment. We compare different long-term rewards to incentivize the algorithm to maximize individual payoff and overall social welfare. We test the algorithm in two simulated auction games, and demonstrate that 1) our algorithm outperforms two benchmark algorithms in a direct competition, with cost to social welfare, and 2) our algorithm's aggressive competitive behavior ca","authors_text":"Holger Karl, Jing Tan, Ramin Khalili","cross_cats":["cs.GT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-05T15:02:28Z","title":"Learning to Bid Long-Term: Multi-Agent Reinforcement Learning with Long-Term and Sparse Reward in Repeated Auction Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02268","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":"sha256:22fca5cd1c968ebf5379b562a3d2dcb4a3dca96d92e6bf2b13f406c02ac09dce","target":"record","created_at":"2026-07-05T04:11:38Z","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":"6062f6f27cf4241be5408799011bbfd627df625ebdd0b29d535a018b3bd2a0b9","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-05T15:02:28Z","title_canon_sha256":"c94e785b0d8d1acbfa382fa6f83688bc7ec974a36be4434b40715958fc761fc3"},"schema_version":"1.0","source":{"id":"2204.02268","kind":"arxiv","version":1}},"canonical_sha256":"a6ff8f3819478a2b0fb2ea6180ccaa6e90d87948deb818c61c5558593ed97f53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6ff8f3819478a2b0fb2ea6180ccaa6e90d87948deb818c61c5558593ed97f53","first_computed_at":"2026-07-05T04:11:38.068330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:11:38.068330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ouVUNVtTbOCHCkXPLYWWtkxCUT4ogZ3q7zhxuNa4IYDt2/wtvb1NdHjezdMZZuv5hgWc7D1v+uhlbuvzDsxuAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:11:38.068705Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.02268","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22fca5cd1c968ebf5379b562a3d2dcb4a3dca96d92e6bf2b13f406c02ac09dce","sha256:4789ee7e3dda188d8d99b2da2a64d673c2f2c3eaacfa29707250b2d187351bf1"],"state_sha256":"9e57fe3a25261a4fe7572caf796d0aed1bf89fc607eee30357a1f1442f476cf4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rD2RjoGS3feEe0S0TAzuofiY0Oqj5TlDVbq6ZM8iY4cPSjvm2yh8AGGPDX+y6e0gCWRZPFqkQK4saZh0hTSfDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T20:08:16.476580Z","bundle_sha256":"cea40a9c9e98a461a5d58e75b239ba843d1b629faf93745a30fdfd536edd0256"}}