{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:G43MBH4XHA4ZUYTICBGGRQXCCE","short_pith_number":"pith:G43MBH4X","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"},"canonical_sha256":"3736c09f9738399a6268104c68c2e2111ac2725976b63ad131dbbbd6f7be50e6","source":{"kind":"arxiv","id":"2605.30896","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30896","created_at":"2026-06-01T01:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30896v1","created_at":"2026-06-01T01:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30896","created_at":"2026-06-01T01:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"G43MBH4XHA4Z","created_at":"2026-06-01T01:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"G43MBH4XHA4ZUYTI","created_at":"2026-06-01T01:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"G43MBH4X","created_at":"2026-06-01T01:03:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:G43MBH4XHA4ZUYTICBGGRQXCCE","target":"record","payload":{"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"},"canonical_sha256":"3736c09f9738399a6268104c68c2e2111ac2725976b63ad131dbbbd6f7be50e6","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"},"source_kind":"arxiv","source_id":"2605.30896","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":"2026-06-01T01:03:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uHFDXukAVmm1rSyyh8WvHzasFeaqeD1YJqaagwvFcjR7VhZnW2HMbwq+yh6tXJyaCyPc620NhUHeMMFvNba2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:48:58.713702Z"},"content_sha256":"e49cca02eb381b7b300029d2ca72d15abfcd1dfc57ec9f85d0fc976422111c46","schema_version":"1.0","event_id":"sha256:e49cca02eb381b7b300029d2ca72d15abfcd1dfc57ec9f85d0fc976422111c46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:G43MBH4XHA4ZUYTICBGGRQXCCE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:03:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GcxMxCurFOyGrZz/0QxHnofg0x2fO6K9I3vlKv6t5gerdYOPtQ7sYhDAHpgByftaRSTkI1GMGiKKS45fPAqrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:48:58.714512Z"},"content_sha256":"dbf9c0f2e4c34ac2137b2c3fae3e690927fbbd51c5fafeec8d560601a87010cf","schema_version":"1.0","event_id":"sha256:dbf9c0f2e4c34ac2137b2c3fae3e690927fbbd51c5fafeec8d560601a87010cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G43MBH4XHA4ZUYTICBGGRQXCCE/bundle.json","state_url":"https://pith.science/pith/G43MBH4XHA4ZUYTICBGGRQXCCE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G43MBH4XHA4ZUYTICBGGRQXCCE/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":"2026-06-05T00:48:58Z","links":{"resolver":"https://pith.science/pith/G43MBH4XHA4ZUYTICBGGRQXCCE","bundle":"https://pith.science/pith/G43MBH4XHA4ZUYTICBGGRQXCCE/bundle.json","state":"https://pith.science/pith/G43MBH4XHA4ZUYTICBGGRQXCCE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G43MBH4XHA4ZUYTICBGGRQXCCE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G43MBH4XHA4ZUYTICBGGRQXCCE","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":"89e189e55c86e261f5ce19e61e6393eb2dd20a440b5cbc47ac93a711b023bb50","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T06:29:26Z","title_canon_sha256":"e50bfd96d5dfafdd4d0972fc436c83ba6f0bce78583f068520620246b2259627"},"schema_version":"1.0","source":{"id":"2605.30896","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30896","created_at":"2026-06-01T01:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30896v1","created_at":"2026-06-01T01:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30896","created_at":"2026-06-01T01:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"G43MBH4XHA4Z","created_at":"2026-06-01T01:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"G43MBH4XHA4ZUYTI","created_at":"2026-06-01T01:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"G43MBH4X","created_at":"2026-06-01T01:03:23Z"}],"graph_snapshots":[{"event_id":"sha256:dbf9c0f2e4c34ac2137b2c3fae3e690927fbbd51c5fafeec8d560601a87010cf","target":"graph","created_at":"2026-06-01T01:03:23Z","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/2605.30896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Amy Greenwald, Enrique Areyan Viqueira, Nishant Kumar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T06:29:26Z","title":"Zero Collapse: A Failure Mode of Policy Gradient Methods in Discontinuous Reward Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30896","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:e49cca02eb381b7b300029d2ca72d15abfcd1dfc57ec9f85d0fc976422111c46","target":"record","created_at":"2026-06-01T01:03:23Z","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":"89e189e55c86e261f5ce19e61e6393eb2dd20a440b5cbc47ac93a711b023bb50","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T06:29:26Z","title_canon_sha256":"e50bfd96d5dfafdd4d0972fc436c83ba6f0bce78583f068520620246b2259627"},"schema_version":"1.0","source":{"id":"2605.30896","kind":"arxiv","version":1}},"canonical_sha256":"3736c09f9738399a6268104c68c2e2111ac2725976b63ad131dbbbd6f7be50e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3736c09f9738399a6268104c68c2e2111ac2725976b63ad131dbbbd6f7be50e6","first_computed_at":"2026-06-01T01:03:23.832569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:23.832569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Ap2x9twnB0M+AgAsrUxiRng0Gc5BERhlQuZy7wtexeCUc5ZSqvnp3zP2Fb/F/JLMM3r8oQtfKUZMmbi8FvlDQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:23.833341Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30896","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e49cca02eb381b7b300029d2ca72d15abfcd1dfc57ec9f85d0fc976422111c46","sha256:dbf9c0f2e4c34ac2137b2c3fae3e690927fbbd51c5fafeec8d560601a87010cf"],"state_sha256":"cb99d324432b028ac282e255a7dbcbfb01a3e08b73b8075068a1eaafbabfd5d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h3cuYIx8WkB1DdXpfEMibpUX3pFlX4LyNOR4fqwOXaLFgDK0qkzCb7MqPcxNq+/UnleOIwVLRJxJMUJGXK8dBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T00:48:58.718446Z","bundle_sha256":"128192ccd308d9b406a8431ba67dce44e419bc75f3cb68982933009d142bd05c"}}