{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WN3OJVYUNCQ4ZMFJU2O5JDVMNE","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":"bb06b236f4ea109c56564851b6f252044495c23862571f29a77cfb6fa21f4bf2","cross_cats_sorted":["cs.SC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-11T10:38:22Z","title_canon_sha256":"f925f3060eebb4cb53dcfbcb96b49696c7789c5e4f55348628d64d0623291756"},"schema_version":"1.0","source":{"id":"2401.05821","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.05821","created_at":"2026-07-05T09:27:20Z"},{"alias_kind":"arxiv_version","alias_value":"2401.05821v4","created_at":"2026-07-05T09:27:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05821","created_at":"2026-07-05T09:27:20Z"},{"alias_kind":"pith_short_12","alias_value":"WN3OJVYUNCQ4","created_at":"2026-07-05T09:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"WN3OJVYUNCQ4ZMFJ","created_at":"2026-07-05T09:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"WN3OJVYU","created_at":"2026-07-05T09:27:20Z"}],"graph_snapshots":[{"event_id":"sha256:ad9574ec99303629769fd47699c339be4bb9b54c1cbe7acba9dab5b5ac76050d","target":"graph","created_at":"2026-07-05T09:27:20Z","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/2401.05821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Goal misalignment, reward sparsity and difficult credit assignment are only a few of the many issues that make it difficult for deep reinforcement learning (RL) agents to learn optimal policies. Unfortunately, the black-box nature of deep neural networks impedes the inclusion of domain experts for inspecting the model and revising suboptimal policies. To this end, we introduce *Successive Concept Bottleneck Agents* (SCoBots), that integrate consecutive concept bottleneck (CB) layers. In contrast to current CB models, SCoBots do not just represent concepts as properties of individual objects, b","authors_text":"Kristian Kersting, Mark Rothermel, Quentin Delfosse, Sebastian Sztwiertnia, Wolfgang Stammer","cross_cats":["cs.SC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-11T10:38:22Z","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05821","kind":"arxiv","version":4},"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":"sha256:06db462ecdf8048d58ed41af51b3624c105a5b69689c131435d0a0579778effc","target":"record","created_at":"2026-07-05T09:27:20Z","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":"bb06b236f4ea109c56564851b6f252044495c23862571f29a77cfb6fa21f4bf2","cross_cats_sorted":["cs.SC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-11T10:38:22Z","title_canon_sha256":"f925f3060eebb4cb53dcfbcb96b49696c7789c5e4f55348628d64d0623291756"},"schema_version":"1.0","source":{"id":"2401.05821","kind":"arxiv","version":4}},"canonical_sha256":"b376e4d71468a1ccb0a9a69dd48eac690f9d8814f31621ba08325edff3502b27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b376e4d71468a1ccb0a9a69dd48eac690f9d8814f31621ba08325edff3502b27","first_computed_at":"2026-07-05T09:27:20.094868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:20.094868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"laujqbDYW19HSkSyhcAB6eL5nQsrd+K5Ugz2pHWWpj9IjukYUkaGsLMzBB06zsvUl9lW/T34QNPmTkZt5VZhBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:20.095268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.05821","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06db462ecdf8048d58ed41af51b3624c105a5b69689c131435d0a0579778effc","sha256:ad9574ec99303629769fd47699c339be4bb9b54c1cbe7acba9dab5b5ac76050d"],"state_sha256":"fe7c34d42443b88d91e5b7f60d6bcd2b0f187b6b46782a8d8d8748a6e8ca366a"}