{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:M6YQAMNWEPF3KC2QHSXB3SMFPQ","short_pith_number":"pith:M6YQAMNW","canonical_record":{"source":{"id":"2507.01470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T08:33:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3ada47454c0ac59ae1c450a725d0e7e8f47edd06ef3b4c6bd35f2cd4df131fa","abstract_canon_sha256":"ed7f6ac511f2ad069efa210bfa56f79a01b1056e07d9cd75dcbbdbd77f4f2999"},"schema_version":"1.0"},"canonical_sha256":"67b10031b623cbb50b503cae1dc9857c00d54d5fa37ad4815b13b87b81f6743f","source":{"kind":"arxiv","id":"2507.01470","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01470","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01470v1","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01470","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"pith_short_12","alias_value":"M6YQAMNWEPF3","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"pith_short_16","alias_value":"M6YQAMNWEPF3KC2Q","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"pith_short_8","alias_value":"M6YQAMNW","created_at":"2026-07-05T11:30:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:M6YQAMNWEPF3KC2QHSXB3SMFPQ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.01470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T08:33:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3ada47454c0ac59ae1c450a725d0e7e8f47edd06ef3b4c6bd35f2cd4df131fa","abstract_canon_sha256":"ed7f6ac511f2ad069efa210bfa56f79a01b1056e07d9cd75dcbbdbd77f4f2999"},"schema_version":"1.0"},"canonical_sha256":"67b10031b623cbb50b503cae1dc9857c00d54d5fa37ad4815b13b87b81f6743f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:49.469392Z","signature_b64":"zlMqg+OBep6x53KNcit3UEg+OuxCVUq5+24+GgapI4/fsO8kEbQRzuTt2whedSw4VYIFpEwFkZp8FYsEqFHnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67b10031b623cbb50b503cae1dc9857c00d54d5fa37ad4815b13b87b81f6743f","last_reissued_at":"2026-07-05T11:30:49.468877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:49.468877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.01470","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":"2026-07-05T11:30:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pQ9R/1VVaQ/Cotp6xIxlXfaE9bW72phjvbwOwz4oLHeqO2GaT0sYTdaH6ldfDYIbY/tTw4ZoHcWaPkkN3LflBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:52:52.117180Z"},"content_sha256":"696494efb3211f651f8f29d8660c437f26fc765d23d05ea394831e335b8f593d","schema_version":"1.0","event_id":"sha256:696494efb3211f651f8f29d8660c437f26fc765d23d05ea394831e335b8f593d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:M6YQAMNWEPF3KC2QHSXB3SMFPQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-Incentive Dynamics: a look at reward sparsity through the lens of unrewarded subgoals","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Tom Lenaerts, Yannick Molinghen","submitted_at":"2025-07-02T08:33:03Z","abstract_excerpt":"This work re-examines the commonly held assumption that the frequency of rewards is a reliable measure of task difficulty in reinforcement learning. We identify and formalize a structural challenge that undermines the effectiveness of current policy learning methods: when essential subgoals do not directly yield rewards. We characterize such settings as exhibiting zero-incentive dynamics, where transitions critical to success remain unrewarded. We show that state-of-the-art deep subgoal-based algorithms fail to leverage these dynamics and that learning performance is highly sensitive to the te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01470","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/2507.01470/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":"2026-07-05T11:30:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ae5njRTXvrfjRLdsY2UM/bWX4S5VZCMngKRdxkupzkel/AaWS1GD9kjFy36Zc5BxolKNMiFYVb9zLI+KVgzPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:52:52.117697Z"},"content_sha256":"2708b3ff09c1239f27f351b3ffe91ff59ca2257b33ca60ee3f146f0c73d29d61","schema_version":"1.0","event_id":"sha256:2708b3ff09c1239f27f351b3ffe91ff59ca2257b33ca60ee3f146f0c73d29d61"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M6YQAMNWEPF3KC2QHSXB3SMFPQ/bundle.json","state_url":"https://pith.science/pith/M6YQAMNWEPF3KC2QHSXB3SMFPQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M6YQAMNWEPF3KC2QHSXB3SMFPQ/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":"2026-08-08T23:52:52Z","links":{"resolver":"https://pith.science/pith/M6YQAMNWEPF3KC2QHSXB3SMFPQ","bundle":"https://pith.science/pith/M6YQAMNWEPF3KC2QHSXB3SMFPQ/bundle.json","state":"https://pith.science/pith/M6YQAMNWEPF3KC2QHSXB3SMFPQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M6YQAMNWEPF3KC2QHSXB3SMFPQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M6YQAMNWEPF3KC2QHSXB3SMFPQ","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":"ed7f6ac511f2ad069efa210bfa56f79a01b1056e07d9cd75dcbbdbd77f4f2999","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T08:33:03Z","title_canon_sha256":"b3ada47454c0ac59ae1c450a725d0e7e8f47edd06ef3b4c6bd35f2cd4df131fa"},"schema_version":"1.0","source":{"id":"2507.01470","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01470","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01470v1","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01470","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"pith_short_12","alias_value":"M6YQAMNWEPF3","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"pith_short_16","alias_value":"M6YQAMNWEPF3KC2Q","created_at":"2026-07-05T11:30:49Z"},{"alias_kind":"pith_short_8","alias_value":"M6YQAMNW","created_at":"2026-07-05T11:30:49Z"}],"graph_snapshots":[{"event_id":"sha256:2708b3ff09c1239f27f351b3ffe91ff59ca2257b33ca60ee3f146f0c73d29d61","target":"graph","created_at":"2026-07-05T11:30:49Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.01470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work re-examines the commonly held assumption that the frequency of rewards is a reliable measure of task difficulty in reinforcement learning. We identify and formalize a structural challenge that undermines the effectiveness of current policy learning methods: when essential subgoals do not directly yield rewards. We characterize such settings as exhibiting zero-incentive dynamics, where transitions critical to success remain unrewarded. We show that state-of-the-art deep subgoal-based algorithms fail to leverage these dynamics and that learning performance is highly sensitive to the te","authors_text":"Tom Lenaerts, Yannick Molinghen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T08:33:03Z","title":"Zero-Incentive Dynamics: a look at reward sparsity through the lens of unrewarded subgoals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01470","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":"sha256:696494efb3211f651f8f29d8660c437f26fc765d23d05ea394831e335b8f593d","target":"record","created_at":"2026-07-05T11:30:49Z","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":"ed7f6ac511f2ad069efa210bfa56f79a01b1056e07d9cd75dcbbdbd77f4f2999","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T08:33:03Z","title_canon_sha256":"b3ada47454c0ac59ae1c450a725d0e7e8f47edd06ef3b4c6bd35f2cd4df131fa"},"schema_version":"1.0","source":{"id":"2507.01470","kind":"arxiv","version":1}},"canonical_sha256":"67b10031b623cbb50b503cae1dc9857c00d54d5fa37ad4815b13b87b81f6743f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67b10031b623cbb50b503cae1dc9857c00d54d5fa37ad4815b13b87b81f6743f","first_computed_at":"2026-07-05T11:30:49.468877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:49.468877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zlMqg+OBep6x53KNcit3UEg+OuxCVUq5+24+GgapI4/fsO8kEbQRzuTt2whedSw4VYIFpEwFkZp8FYsEqFHnAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:49.469392Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01470","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:696494efb3211f651f8f29d8660c437f26fc765d23d05ea394831e335b8f593d","sha256:2708b3ff09c1239f27f351b3ffe91ff59ca2257b33ca60ee3f146f0c73d29d61"],"state_sha256":"4330cbbc9b19abccf5f8099d7d44f7ae0247fee19b21b613b747a339bb4e848b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xLQVhHbpWiWKYKOBCb6zHvV7JDx9Q+847i/M88TTG7q0MhJhU/vLR/tO52HYnrU0ouIgh89dhc9tu8d8GPwICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:52:52.123638Z","bundle_sha256":"0f129646d6fe0a6d88753df66b0eeb8926547bea12fe44204b7a0ce4f950e3a8"}}