{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RJBPQGWF4VEO26NIKZMGHWMWRK","short_pith_number":"pith:RJBPQGWF","canonical_record":{"source":{"id":"1802.09756","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-27T07:52:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2bcc0eea1539f0a47bac43fd3740ade8d34575f176e6fd917155377c385b8130","abstract_canon_sha256":"07da064496c2b22582505e3e861df0365a41865bf69d23ecee1b468d3d865d97"},"schema_version":"1.0"},"canonical_sha256":"8a42f81ac5e548ed79a8565863d9968a8737d4d0e151d1ddf9ba4db337685d56","source":{"kind":"arxiv","id":"1802.09756","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09756","created_at":"2026-05-18T00:01:49Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09756v2","created_at":"2026-05-18T00:01:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09756","created_at":"2026-05-18T00:01:49Z"},{"alias_kind":"pith_short_12","alias_value":"RJBPQGWF4VEO","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RJBPQGWF4VEO26NI","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RJBPQGWF","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RJBPQGWF4VEO26NIKZMGHWMWRK","target":"record","payload":{"canonical_record":{"source":{"id":"1802.09756","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-27T07:52:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2bcc0eea1539f0a47bac43fd3740ade8d34575f176e6fd917155377c385b8130","abstract_canon_sha256":"07da064496c2b22582505e3e861df0365a41865bf69d23ecee1b468d3d865d97"},"schema_version":"1.0"},"canonical_sha256":"8a42f81ac5e548ed79a8565863d9968a8737d4d0e151d1ddf9ba4db337685d56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:49.035451Z","signature_b64":"fwHkrrKJ0MOcclLFoPH5kzRyGAkTSiBsefEKmW0SOl3rpVRpXTNtGfX4W17p7XUls4Y4MquCauEoDpEot/NVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a42f81ac5e548ed79a8565863d9968a8737d4d0e151d1ddf9ba4db337685d56","last_reissued_at":"2026-05-18T00:01:49.034922Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:49.034922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.09756","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":"2026-05-18T00:01:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ox/EkMMyS4YTFSZzlPwyGP+/VkPUM2pGF6rpycB52OA1cFJp3qOho1wpFouyGdmi1kiymWbwLKDA82/w0g/8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:29:40.480855Z"},"content_sha256":"69ff6d124c456cbe6e4bbec11bb82094e6239910a0208382d48492681b2403d0","schema_version":"1.0","event_id":"sha256:69ff6d124c456cbe6e4bbec11bb82094e6239910a0208382d48492681b2403d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RJBPQGWF4VEO26NIKZMGHWMWRK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Chengru Song, Han Li, Junqi Jin, Jun Wang, Kun Gai, Weinan Zhang","submitted_at":"2018-02-27T07:52:35Z","abstract_excerpt":"Real-time advertising allows advertisers to bid for each impression for a visiting user. To optimize specific goals such as maximizing revenue and return on investment (ROI) led by ad placements, advertisers not only need to estimate the relevance between the ads and user's interests, but most importantly require a strategic response with respect to other advertisers bidding in the market. In this paper, we formulate bidding optimization with multi-agent reinforcement learning. To deal with a large number of advertisers, we propose a clustering method and assign each cluster with a strategic b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09756","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":""},"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":"2026-05-18T00:01:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LFLGq+rUCxdIl3A6UyfAjIqO4+NnIWd7AJ4s0gvj6VzM4faIl+RGFG1mr2VlmOtfQGWxaP5QdBPDR9QaPCfwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:29:40.481585Z"},"content_sha256":"c741c749498df64d6f3921ad3bf672d059e243be934c142506d16cacf35434f0","schema_version":"1.0","event_id":"sha256:c741c749498df64d6f3921ad3bf672d059e243be934c142506d16cacf35434f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJBPQGWF4VEO26NIKZMGHWMWRK/bundle.json","state_url":"https://pith.science/pith/RJBPQGWF4VEO26NIKZMGHWMWRK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJBPQGWF4VEO26NIKZMGHWMWRK/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":"2026-05-30T17:29:40Z","links":{"resolver":"https://pith.science/pith/RJBPQGWF4VEO26NIKZMGHWMWRK","bundle":"https://pith.science/pith/RJBPQGWF4VEO26NIKZMGHWMWRK/bundle.json","state":"https://pith.science/pith/RJBPQGWF4VEO26NIKZMGHWMWRK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJBPQGWF4VEO26NIKZMGHWMWRK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RJBPQGWF4VEO26NIKZMGHWMWRK","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":"07da064496c2b22582505e3e861df0365a41865bf69d23ecee1b468d3d865d97","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-27T07:52:35Z","title_canon_sha256":"2bcc0eea1539f0a47bac43fd3740ade8d34575f176e6fd917155377c385b8130"},"schema_version":"1.0","source":{"id":"1802.09756","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09756","created_at":"2026-05-18T00:01:49Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09756v2","created_at":"2026-05-18T00:01:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09756","created_at":"2026-05-18T00:01:49Z"},{"alias_kind":"pith_short_12","alias_value":"RJBPQGWF4VEO","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RJBPQGWF4VEO26NI","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RJBPQGWF","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:c741c749498df64d6f3921ad3bf672d059e243be934c142506d16cacf35434f0","target":"graph","created_at":"2026-05-18T00:01:49Z","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"},"paper":{"abstract_excerpt":"Real-time advertising allows advertisers to bid for each impression for a visiting user. To optimize specific goals such as maximizing revenue and return on investment (ROI) led by ad placements, advertisers not only need to estimate the relevance between the ads and user's interests, but most importantly require a strategic response with respect to other advertisers bidding in the market. In this paper, we formulate bidding optimization with multi-agent reinforcement learning. To deal with a large number of advertisers, we propose a clustering method and assign each cluster with a strategic b","authors_text":"Chengru Song, Han Li, Junqi Jin, Jun Wang, Kun Gai, Weinan Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-27T07:52:35Z","title":"Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09756","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":"sha256:69ff6d124c456cbe6e4bbec11bb82094e6239910a0208382d48492681b2403d0","target":"record","created_at":"2026-05-18T00:01:49Z","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":"07da064496c2b22582505e3e861df0365a41865bf69d23ecee1b468d3d865d97","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-27T07:52:35Z","title_canon_sha256":"2bcc0eea1539f0a47bac43fd3740ade8d34575f176e6fd917155377c385b8130"},"schema_version":"1.0","source":{"id":"1802.09756","kind":"arxiv","version":2}},"canonical_sha256":"8a42f81ac5e548ed79a8565863d9968a8737d4d0e151d1ddf9ba4db337685d56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a42f81ac5e548ed79a8565863d9968a8737d4d0e151d1ddf9ba4db337685d56","first_computed_at":"2026-05-18T00:01:49.034922Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:49.034922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fwHkrrKJ0MOcclLFoPH5kzRyGAkTSiBsefEKmW0SOl3rpVRpXTNtGfX4W17p7XUls4Y4MquCauEoDpEot/NVCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:49.035451Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.09756","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69ff6d124c456cbe6e4bbec11bb82094e6239910a0208382d48492681b2403d0","sha256:c741c749498df64d6f3921ad3bf672d059e243be934c142506d16cacf35434f0"],"state_sha256":"5349ef22da0e74841f65728b8475361c9ab35e2b949edeee28ca996532899a1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rLQknSSN/ieEPvfrcFAUvre5fBubGrw4Kga94PKcTmnHi10W9U4jfs9jI7O8C/tp3mvH/NTpbbxnITdsPpGlCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T17:29:40.485074Z","bundle_sha256":"ba98f4cde5eaa2a2ac3210dd1105530ccd2576f71c0e7ddb1aafbbcd02294a5d"}}