{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G43MBH4XHA4ZUYTICBGGRQXCCE","short_pith_number":"pith:G43MBH4X","schema_version":"1.0","canonical_sha256":"3736c09f9738399a6268104c68c2e2111ac2725976b63ad131dbbbd6f7be50e6","source":{"kind":"arxiv","id":"2605.30896","version":1},"attestation_state":"computed","paper":{"title":"Zero Collapse: A Failure Mode of Policy Gradient Methods in Discontinuous Reward Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amy Greenwald, Enrique Areyan Viqueira, Nishant Kumar","submitted_at":"2026-05-29T06:29:26Z","abstract_excerpt":"Bidding in repeated auctions is a central challenge for reinforcement learning (RL), combining continuous control with the strategic complexities of digital advertising. While policy gradient and value-based methods seem well-suited for these settings, they often struggle with the discontinuous, \"cliff-like\" nature of auction reward landscapes. In a first-price auction, for example, a bidder receives zero reward until they cross a specific threshold, after which the reward decreases as the bid increases. This creates a landscape of flat, zero-reward regions separated by sharp boundaries.\n  We "},"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":"2605.30896","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T06:29:26Z","cross_cats_sorted":[],"title_canon_sha256":"e50bfd96d5dfafdd4d0972fc436c83ba6f0bce78583f068520620246b2259627","abstract_canon_sha256":"89e189e55c86e261f5ce19e61e6393eb2dd20a440b5cbc47ac93a711b023bb50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:23.833341Z","signature_b64":"/Ap2x9twnB0M+AgAsrUxiRng0Gc5BERhlQuZy7wtexeCUc5ZSqvnp3zP2Fb/F/JLMM3r8oQtfKUZMmbi8FvlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3736c09f9738399a6268104c68c2e2111ac2725976b63ad131dbbbd6f7be50e6","last_reissued_at":"2026-06-01T01:03:23.832569Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:23.832569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero Collapse: A Failure Mode of Policy Gradient Methods in Discontinuous Reward Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amy Greenwald, Enrique Areyan Viqueira, Nishant Kumar","submitted_at":"2026-05-29T06:29:26Z","abstract_excerpt":"Bidding in repeated auctions is a central challenge for reinforcement learning (RL), combining continuous control with the strategic complexities of digital advertising. While policy gradient and value-based methods seem well-suited for these settings, they often struggle with the discontinuous, \"cliff-like\" nature of auction reward landscapes. In a first-price auction, for example, a bidder receives zero reward until they cross a specific threshold, after which the reward decreases as the bid increases. This creates a landscape of flat, zero-reward regions separated by sharp boundaries.\n  We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30896","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/2605.30896/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":"2605.30896","created_at":"2026-06-01T01:03:23.832675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30896v1","created_at":"2026-06-01T01:03:23.832675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30896","created_at":"2026-06-01T01:03:23.832675+00:00"},{"alias_kind":"pith_short_12","alias_value":"G43MBH4XHA4Z","created_at":"2026-06-01T01:03:23.832675+00:00"},{"alias_kind":"pith_short_16","alias_value":"G43MBH4XHA4ZUYTI","created_at":"2026-06-01T01:03:23.832675+00:00"},{"alias_kind":"pith_short_8","alias_value":"G43MBH4X","created_at":"2026-06-01T01:03:23.832675+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/G43MBH4XHA4ZUYTICBGGRQXCCE","json":"https://pith.science/pith/G43MBH4XHA4ZUYTICBGGRQXCCE.json","graph_json":"https://pith.science/api/pith-number/G43MBH4XHA4ZUYTICBGGRQXCCE/graph.json","events_json":"https://pith.science/api/pith-number/G43MBH4XHA4ZUYTICBGGRQXCCE/events.json","paper":"https://pith.science/paper/G43MBH4X"},"agent_actions":{"view_html":"https://pith.science/pith/G43MBH4XHA4ZUYTICBGGRQXCCE","download_json":"https://pith.science/pith/G43MBH4XHA4ZUYTICBGGRQXCCE.json","view_paper":"https://pith.science/paper/G43MBH4X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30896&json=true","fetch_graph":"https://pith.science/api/pith-number/G43MBH4XHA4ZUYTICBGGRQXCCE/graph.json","fetch_events":"https://pith.science/api/pith-number/G43MBH4XHA4ZUYTICBGGRQXCCE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G43MBH4XHA4ZUYTICBGGRQXCCE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G43MBH4XHA4ZUYTICBGGRQXCCE/action/storage_attestation","attest_author":"https://pith.science/pith/G43MBH4XHA4ZUYTICBGGRQXCCE/action/author_attestation","sign_citation":"https://pith.science/pith/G43MBH4XHA4ZUYTICBGGRQXCCE/action/citation_signature","submit_replication":"https://pith.science/pith/G43MBH4XHA4ZUYTICBGGRQXCCE/action/replication_record"}},"created_at":"2026-06-01T01:03:23.832675+00:00","updated_at":"2026-06-01T01:03:23.832675+00:00"}