{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A5DZBPPKWTA6ZEP4QOXA546NNQ","short_pith_number":"pith:A5DZBPPK","schema_version":"1.0","canonical_sha256":"074790bdeab4c1ec91fc83ae0ef3cd6c2bb91d0a36a332a0357dbdee8be0d74d","source":{"kind":"arxiv","id":"2504.14645","version":1},"attestation_state":"computed","paper":{"title":"Surrogate Fitness Metrics for Interpretable Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"C\\'eline Davignon, Claudia Linnhoff-Popien, Fabian Ritz, Maximilian Zorn, Philipp Altmann, Thomas Gabor","submitted_at":"2025-04-20T15:01:19Z","abstract_excerpt":"We employ an evolutionary optimization framework that perturbs initial states to generate informative and diverse policy demonstrations. A joint surrogate fitness function guides the optimization by combining local diversity, behavioral certainty, and global population diversity. To assess demonstration quality, we apply a set of evaluation metrics, including the reward-based optimality gap, fidelity interquartile means (IQMs), fitness composition analysis, and trajectory visualizations. Hyperparameter sensitivity is also examined to better understand the dynamics of trajectory optimization. O"},"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":"2504.14645","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T15:01:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"30082481f1d130b6c1293c95b75b67c60c3092080d353fd53fd47c8c8d624d03","abstract_canon_sha256":"f4929b871ec753b9b2b5bfa9bc6ac9afe6b6cf743564c60f8e02a2722b2d2f34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:48.104960Z","signature_b64":"kj/3sz0RKdcOjj9GvnsLS3rfTvBik9a1T85TpuBApL6nuHtXLAwnMNZgo54rBlD8mB4nf7lLIVMeERpvs/S5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"074790bdeab4c1ec91fc83ae0ef3cd6c2bb91d0a36a332a0357dbdee8be0d74d","last_reissued_at":"2026-07-05T10:51:48.104398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:48.104398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Surrogate Fitness Metrics for Interpretable Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"C\\'eline Davignon, Claudia Linnhoff-Popien, Fabian Ritz, Maximilian Zorn, Philipp Altmann, Thomas Gabor","submitted_at":"2025-04-20T15:01:19Z","abstract_excerpt":"We employ an evolutionary optimization framework that perturbs initial states to generate informative and diverse policy demonstrations. A joint surrogate fitness function guides the optimization by combining local diversity, behavioral certainty, and global population diversity. To assess demonstration quality, we apply a set of evaluation metrics, including the reward-based optimality gap, fidelity interquartile means (IQMs), fitness composition analysis, and trajectory visualizations. Hyperparameter sensitivity is also examined to better understand the dynamics of trajectory optimization. O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14645","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/2504.14645/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":"2504.14645","created_at":"2026-07-05T10:51:48.104466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14645v1","created_at":"2026-07-05T10:51:48.104466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14645","created_at":"2026-07-05T10:51:48.104466+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5DZBPPKWTA6","created_at":"2026-07-05T10:51:48.104466+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5DZBPPKWTA6ZEP4","created_at":"2026-07-05T10:51:48.104466+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5DZBPPK","created_at":"2026-07-05T10:51:48.104466+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/A5DZBPPKWTA6ZEP4QOXA546NNQ","json":"https://pith.science/pith/A5DZBPPKWTA6ZEP4QOXA546NNQ.json","graph_json":"https://pith.science/api/pith-number/A5DZBPPKWTA6ZEP4QOXA546NNQ/graph.json","events_json":"https://pith.science/api/pith-number/A5DZBPPKWTA6ZEP4QOXA546NNQ/events.json","paper":"https://pith.science/paper/A5DZBPPK"},"agent_actions":{"view_html":"https://pith.science/pith/A5DZBPPKWTA6ZEP4QOXA546NNQ","download_json":"https://pith.science/pith/A5DZBPPKWTA6ZEP4QOXA546NNQ.json","view_paper":"https://pith.science/paper/A5DZBPPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14645&json=true","fetch_graph":"https://pith.science/api/pith-number/A5DZBPPKWTA6ZEP4QOXA546NNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/A5DZBPPKWTA6ZEP4QOXA546NNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5DZBPPKWTA6ZEP4QOXA546NNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5DZBPPKWTA6ZEP4QOXA546NNQ/action/storage_attestation","attest_author":"https://pith.science/pith/A5DZBPPKWTA6ZEP4QOXA546NNQ/action/author_attestation","sign_citation":"https://pith.science/pith/A5DZBPPKWTA6ZEP4QOXA546NNQ/action/citation_signature","submit_replication":"https://pith.science/pith/A5DZBPPKWTA6ZEP4QOXA546NNQ/action/replication_record"}},"created_at":"2026-07-05T10:51:48.104466+00:00","updated_at":"2026-07-05T10:51:48.104466+00:00"}