{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AEM6PWRSJFPDYVYFXNW2NB77IB","short_pith_number":"pith:AEM6PWRS","schema_version":"1.0","canonical_sha256":"0119e7da32495e3c5705bb6da687ff406578a62963d0011de3720ae18ddc572b","source":{"kind":"arxiv","id":"2607.24779","version":1},"attestation_state":"computed","paper":{"title":"HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jinan Pang, Ji Wu, Wentao Bai, Wenzheng Shu, Xialong Liu, Yanxiang Zeng, Yunke Bai, Yunshan Peng","submitted_at":"2026-06-17T15:00:34Z","abstract_excerpt":"Online advertising bidding systems typically deploy multiple offline-trained expert models (e.g., PID controllers, model predictive control, offline RL policies) but face two critical limitations: lack of online adaptability to non-stationary auction markets, and reliance on costly manual tuning of hyperparameters such as bid bounds and budget pacing constraints. We propose HOBA (Hierarchical On-policy Bidding Agents), a hierarchical reinforcement learning framework that decouples strategic reasoning, model selection, and bid execution across three time scales. At the high level, a large langu"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.24779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-17T15:00:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a891a246f4e15b712604da50c3ae6daa9a5d559e3b631cb00ab65d87a1f6feb2","abstract_canon_sha256":"0c787f5c810b2d3e68945a066c3ef94c9ada0fa4b80b7b05badabecc7809eabf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:43.614845Z","signature_b64":"KrHSGPwCcRqKMll39j7ceER0CWFKwpwMvi5sxn/uwIgKUft3dDKWaVPsmOISSOJaTOEz1jqj+LDuOGrr6qJSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0119e7da32495e3c5705bb6da687ff406578a62963d0011de3720ae18ddc572b","last_reissued_at":"2026-07-29T00:24:43.614024Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:43.614024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jinan Pang, Ji Wu, Wentao Bai, Wenzheng Shu, Xialong Liu, Yanxiang Zeng, Yunke Bai, Yunshan Peng","submitted_at":"2026-06-17T15:00:34Z","abstract_excerpt":"Online advertising bidding systems typically deploy multiple offline-trained expert models (e.g., PID controllers, model predictive control, offline RL policies) but face two critical limitations: lack of online adaptability to non-stationary auction markets, and reliance on costly manual tuning of hyperparameters such as bid bounds and budget pacing constraints. We propose HOBA (Hierarchical On-policy Bidding Agents), a hierarchical reinforcement learning framework that decouples strategic reasoning, model selection, and bid execution across three time scales. At the high level, a large langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24779","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/2607.24779/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.24779","created_at":"2026-07-29T00:24:43.614449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24779v1","created_at":"2026-07-29T00:24:43.614449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24779","created_at":"2026-07-29T00:24:43.614449+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEM6PWRSJFPD","created_at":"2026-07-29T00:24:43.614449+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEM6PWRSJFPDYVYF","created_at":"2026-07-29T00:24:43.614449+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEM6PWRS","created_at":"2026-07-29T00:24:43.614449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AEM6PWRSJFPDYVYFXNW2NB77IB","json":"https://pith.science/pith/AEM6PWRSJFPDYVYFXNW2NB77IB.json","graph_json":"https://pith.science/api/pith-number/AEM6PWRSJFPDYVYFXNW2NB77IB/graph.json","events_json":"https://pith.science/api/pith-number/AEM6PWRSJFPDYVYFXNW2NB77IB/events.json","paper":"https://pith.science/paper/AEM6PWRS"},"agent_actions":{"view_html":"https://pith.science/pith/AEM6PWRSJFPDYVYFXNW2NB77IB","download_json":"https://pith.science/pith/AEM6PWRSJFPDYVYFXNW2NB77IB.json","view_paper":"https://pith.science/paper/AEM6PWRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24779&json=true","fetch_graph":"https://pith.science/api/pith-number/AEM6PWRSJFPDYVYFXNW2NB77IB/graph.json","fetch_events":"https://pith.science/api/pith-number/AEM6PWRSJFPDYVYFXNW2NB77IB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEM6PWRSJFPDYVYFXNW2NB77IB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEM6PWRSJFPDYVYFXNW2NB77IB/action/storage_attestation","attest_author":"https://pith.science/pith/AEM6PWRSJFPDYVYFXNW2NB77IB/action/author_attestation","sign_citation":"https://pith.science/pith/AEM6PWRSJFPDYVYFXNW2NB77IB/action/citation_signature","submit_replication":"https://pith.science/pith/AEM6PWRSJFPDYVYFXNW2NB77IB/action/replication_record"}},"created_at":"2026-07-29T00:24:43.614449+00:00","updated_at":"2026-07-29T00:24:43.614449+00:00"}