{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KL52XIKDKBRVSMF76334B77FH5","short_pith_number":"pith:KL52XIKD","canonical_record":{"source":{"id":"2605.20878","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T08:15:57Z","cross_cats_sorted":[],"title_canon_sha256":"232ccef1837e2001d7ea20690ab935242cb1c9790848d19239d1cd0f32844e4e","abstract_canon_sha256":"346e74853fce6cf65896d8e3b139bf6fa844c4c28485ac9fcf837a7b510e2e63"},"schema_version":"1.0"},"canonical_sha256":"52fbaba14350635930bff6f7c0ffe53f4a9d9450fd402e394fde29a75d9e93f5","source":{"kind":"arxiv","id":"2605.20878","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20878","created_at":"2026-05-21T01:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20878v1","created_at":"2026-05-21T01:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20878","created_at":"2026-05-21T01:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"KL52XIKDKBRV","created_at":"2026-05-21T01:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"KL52XIKDKBRVSMF7","created_at":"2026-05-21T01:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"KL52XIKD","created_at":"2026-05-21T01:05:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KL52XIKDKBRVSMF76334B77FH5","target":"record","payload":{"canonical_record":{"source":{"id":"2605.20878","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T08:15:57Z","cross_cats_sorted":[],"title_canon_sha256":"232ccef1837e2001d7ea20690ab935242cb1c9790848d19239d1cd0f32844e4e","abstract_canon_sha256":"346e74853fce6cf65896d8e3b139bf6fa844c4c28485ac9fcf837a7b510e2e63"},"schema_version":"1.0"},"canonical_sha256":"52fbaba14350635930bff6f7c0ffe53f4a9d9450fd402e394fde29a75d9e93f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:26.033042Z","signature_b64":"qBmb2MgXxGusU9EvIg63Mv65Oi9xbV6mHNU8lAfCRR9OJDvYZolmPnBKVT6wd/vpojSiZVn/jfFmz+kV218JAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52fbaba14350635930bff6f7c0ffe53f4a9d9450fd402e394fde29a75d9e93f5","last_reissued_at":"2026-05-21T01:05:26.032264Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:26.032264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.20878","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":"2026-05-21T01:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZW4/pqc3ervpcRmMKZpFptmwnj9LPQrY+/QuEuCZ1wIpfqaPsWkxM04WBSsPy1r29jxGXlJ69hOlbZ4dy7zvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:35:36.118948Z"},"content_sha256":"5e422246742299d42248cc6feb5c26b2997905115eb85a9379c2926f30eaf79b","schema_version":"1.0","event_id":"sha256:5e422246742299d42248cc6feb5c26b2997905115eb85a9379c2926f30eaf79b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KL52XIKDKBRVSMF76334B77FH5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CIG: Exploration via Conditional Information Gain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"J. Marius Z\\\"ollner, Karam Daaboul, Marcus Fechner, Philipp Stegmaier, Tim Joseph","submitted_at":"2026-05-20T08:15:57Z","abstract_excerpt":"Intrinsic rewards for exploration in reinforcement learning condition on different contexts: lifelong rewards score each transition against accumulated experience but ignore within-rollout redundancy; episodic rewards penalize intra-trajectory repetition but discard lifetime progress. Hybrid methods combine both signals through heuristic weights or require Gaussian-process dynamics that do not scale beyond low-dimensional state spaces. Trajectory-level information gain decomposes into per-step terms that condition on the replay buffer and rollout prefix simultaneously, but remains intractable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20878","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/2605.20878/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":"2026-05-21T01:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wORtc4WPm6pu4vSElMijJ806vePUAcShm0LHOPehlmNeivteCynLjKyHLUZK1xQWLNBcI/Qve+JisHgS3SBIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:35:36.119687Z"},"content_sha256":"de2a1977373e6198241261430644546a3d551f751ef5bf437eb127bef5c92c2d","schema_version":"1.0","event_id":"sha256:de2a1977373e6198241261430644546a3d551f751ef5bf437eb127bef5c92c2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KL52XIKDKBRVSMF76334B77FH5/bundle.json","state_url":"https://pith.science/pith/KL52XIKDKBRVSMF76334B77FH5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KL52XIKDKBRVSMF76334B77FH5/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":"2026-05-26T07:35:36Z","links":{"resolver":"https://pith.science/pith/KL52XIKDKBRVSMF76334B77FH5","bundle":"https://pith.science/pith/KL52XIKDKBRVSMF76334B77FH5/bundle.json","state":"https://pith.science/pith/KL52XIKDKBRVSMF76334B77FH5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KL52XIKDKBRVSMF76334B77FH5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KL52XIKDKBRVSMF76334B77FH5","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":"346e74853fce6cf65896d8e3b139bf6fa844c4c28485ac9fcf837a7b510e2e63","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T08:15:57Z","title_canon_sha256":"232ccef1837e2001d7ea20690ab935242cb1c9790848d19239d1cd0f32844e4e"},"schema_version":"1.0","source":{"id":"2605.20878","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20878","created_at":"2026-05-21T01:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20878v1","created_at":"2026-05-21T01:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20878","created_at":"2026-05-21T01:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"KL52XIKDKBRV","created_at":"2026-05-21T01:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"KL52XIKDKBRVSMF7","created_at":"2026-05-21T01:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"KL52XIKD","created_at":"2026-05-21T01:05:26Z"}],"graph_snapshots":[{"event_id":"sha256:de2a1977373e6198241261430644546a3d551f751ef5bf437eb127bef5c92c2d","target":"graph","created_at":"2026-05-21T01:05:26Z","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/2605.20878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Intrinsic rewards for exploration in reinforcement learning condition on different contexts: lifelong rewards score each transition against accumulated experience but ignore within-rollout redundancy; episodic rewards penalize intra-trajectory repetition but discard lifetime progress. Hybrid methods combine both signals through heuristic weights or require Gaussian-process dynamics that do not scale beyond low-dimensional state spaces. Trajectory-level information gain decomposes into per-step terms that condition on the replay buffer and rollout prefix simultaneously, but remains intractable ","authors_text":"J. Marius Z\\\"ollner, Karam Daaboul, Marcus Fechner, Philipp Stegmaier, Tim Joseph","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T08:15:57Z","title":"CIG: Exploration via Conditional Information Gain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20878","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":"sha256:5e422246742299d42248cc6feb5c26b2997905115eb85a9379c2926f30eaf79b","target":"record","created_at":"2026-05-21T01:05:26Z","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":"346e74853fce6cf65896d8e3b139bf6fa844c4c28485ac9fcf837a7b510e2e63","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T08:15:57Z","title_canon_sha256":"232ccef1837e2001d7ea20690ab935242cb1c9790848d19239d1cd0f32844e4e"},"schema_version":"1.0","source":{"id":"2605.20878","kind":"arxiv","version":1}},"canonical_sha256":"52fbaba14350635930bff6f7c0ffe53f4a9d9450fd402e394fde29a75d9e93f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52fbaba14350635930bff6f7c0ffe53f4a9d9450fd402e394fde29a75d9e93f5","first_computed_at":"2026-05-21T01:05:26.032264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:26.032264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qBmb2MgXxGusU9EvIg63Mv65Oi9xbV6mHNU8lAfCRR9OJDvYZolmPnBKVT6wd/vpojSiZVn/jfFmz+kV218JAg==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:26.033042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20878","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e422246742299d42248cc6feb5c26b2997905115eb85a9379c2926f30eaf79b","sha256:de2a1977373e6198241261430644546a3d551f751ef5bf437eb127bef5c92c2d"],"state_sha256":"5c8ab3af968695fe25156cdc8158ef1feec7ce09e5fb3b30bc2c3e3acd878985"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qvcSmtMy59lWDY4pt4RZuSfKjjTgH7CQ/o4mGcz8Y4wLGQxNVoy7Enodedd/2CTRxcmS0m3j9t431PswZRaXAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T07:35:36.123123Z","bundle_sha256":"b6b0afa427597f1bb8d1d4f702d8f3a0505f0ac4c92fe0596e11c69958cb5f25"}}