{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:24FB2JDI7UWGTMOLI5KQRO4VQM","short_pith_number":"pith:24FB2JDI","canonical_record":{"source":{"id":"2607.29419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T13:41:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d754c31c19e38db182427f0ba726a8700b60ca139d30264d0d22084159e3e3e2","abstract_canon_sha256":"1fc543cf01f6d24ae49dc92dc4ad0b5a4d4cf6fc18c21311bc4a2697f12f029e"},"schema_version":"1.0"},"canonical_sha256":"d70a1d2468fd2c69b1cb475508bb95832952161ac4dc8e6f290ff81ca218bb71","source":{"kind":"arxiv","id":"2607.29419","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.29419","created_at":"2026-08-03T01:34:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.29419v1","created_at":"2026-08-03T01:34:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29419","created_at":"2026-08-03T01:34:13Z"},{"alias_kind":"pith_short_12","alias_value":"24FB2JDI7UWG","created_at":"2026-08-03T01:34:13Z"},{"alias_kind":"pith_short_16","alias_value":"24FB2JDI7UWGTMOL","created_at":"2026-08-03T01:34:13Z"},{"alias_kind":"pith_short_8","alias_value":"24FB2JDI","created_at":"2026-08-03T01:34:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:24FB2JDI7UWGTMOLI5KQRO4VQM","target":"record","payload":{"canonical_record":{"source":{"id":"2607.29419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T13:41:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d754c31c19e38db182427f0ba726a8700b60ca139d30264d0d22084159e3e3e2","abstract_canon_sha256":"1fc543cf01f6d24ae49dc92dc4ad0b5a4d4cf6fc18c21311bc4a2697f12f029e"},"schema_version":"1.0"},"canonical_sha256":"d70a1d2468fd2c69b1cb475508bb95832952161ac4dc8e6f290ff81ca218bb71","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:34:13.596480Z","signature_b64":"ixyKzmWRU04HUzkZmH0B5ydHQ17lmmoln1eI8WyX+hDroIKiAuEU2LsHFyYRTdQ+9DnSXcRJSx/8hRH1iiVaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d70a1d2468fd2c69b1cb475508bb95832952161ac4dc8e6f290ff81ca218bb71","last_reissued_at":"2026-08-03T01:34:13.594964Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:34:13.594964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.29419","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":"2026-08-03T01:34:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GAEJyNn3xdWBoBOTyCBZx0LtqT8pYz9gAQm0vsxGKFcZejnPjmqVs6RThTEJGzdt7ZgKW3VrkiPH7BdROE1tBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:32:56.529266Z"},"content_sha256":"71098d51e47738da469d6ff1e6a685022d4e0bfe23e1f09f2c144729f109292e","schema_version":"1.0","event_id":"sha256:71098d51e47738da469d6ff1e6a685022d4e0bfe23e1f09f2c144729f109292e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:24FB2JDI7UWGTMOLI5KQRO4VQM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explore Beyond the Boundary Using Entropic Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bumgeun Park, Donghwan Lee","submitted_at":"2026-07-31T13:41:51Z","abstract_excerpt":"In reinforcement learning, exploration with sparse and delayed rewards presents a significant challenge due to the limited feedback available for guiding the learning process. Addressing this issue requires extensive exploration in the state space to discover valuable reward signals. In this paper, we propose Entropic Information for Exploration (ENTINEX), a novel method that enhances exploration by incentivizing agents to explore beyond the boundaries of the state distribution. ENTINEX achieves this by assigning intrinsic rewards to these boundaries, leveraging entropic information to identif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29419","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/2607.29419/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":"2026-08-03T01:34:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mzltl70AjKCFfUojYtWe0J9Qb2+aUVzEzP/Pq1l5llL17NG3QSjFNKsDIvzFKgk1TZLnxAD1hsqmR0sKJBe3CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:32:56.529767Z"},"content_sha256":"84526746eeb8360e0330f700379800aad13ecd8c4a14e278fbd2870256b9d34c","schema_version":"1.0","event_id":"sha256:84526746eeb8360e0330f700379800aad13ecd8c4a14e278fbd2870256b9d34c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/24FB2JDI7UWGTMOLI5KQRO4VQM/bundle.json","state_url":"https://pith.science/pith/24FB2JDI7UWGTMOLI5KQRO4VQM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/24FB2JDI7UWGTMOLI5KQRO4VQM/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":"2026-08-19T10:32:56Z","links":{"resolver":"https://pith.science/pith/24FB2JDI7UWGTMOLI5KQRO4VQM","bundle":"https://pith.science/pith/24FB2JDI7UWGTMOLI5KQRO4VQM/bundle.json","state":"https://pith.science/pith/24FB2JDI7UWGTMOLI5KQRO4VQM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/24FB2JDI7UWGTMOLI5KQRO4VQM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:24FB2JDI7UWGTMOLI5KQRO4VQM","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":"1fc543cf01f6d24ae49dc92dc4ad0b5a4d4cf6fc18c21311bc4a2697f12f029e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T13:41:51Z","title_canon_sha256":"d754c31c19e38db182427f0ba726a8700b60ca139d30264d0d22084159e3e3e2"},"schema_version":"1.0","source":{"id":"2607.29419","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.29419","created_at":"2026-08-03T01:34:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.29419v1","created_at":"2026-08-03T01:34:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29419","created_at":"2026-08-03T01:34:13Z"},{"alias_kind":"pith_short_12","alias_value":"24FB2JDI7UWG","created_at":"2026-08-03T01:34:13Z"},{"alias_kind":"pith_short_16","alias_value":"24FB2JDI7UWGTMOL","created_at":"2026-08-03T01:34:13Z"},{"alias_kind":"pith_short_8","alias_value":"24FB2JDI","created_at":"2026-08-03T01:34:13Z"}],"graph_snapshots":[{"event_id":"sha256:84526746eeb8360e0330f700379800aad13ecd8c4a14e278fbd2870256b9d34c","target":"graph","created_at":"2026-08-03T01:34:13Z","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/2607.29419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning, exploration with sparse and delayed rewards presents a significant challenge due to the limited feedback available for guiding the learning process. Addressing this issue requires extensive exploration in the state space to discover valuable reward signals. In this paper, we propose Entropic Information for Exploration (ENTINEX), a novel method that enhances exploration by incentivizing agents to explore beyond the boundaries of the state distribution. ENTINEX achieves this by assigning intrinsic rewards to these boundaries, leveraging entropic information to identif","authors_text":"Bumgeun Park, Donghwan Lee","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T13:41:51Z","title":"Explore Beyond the Boundary Using Entropic Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29419","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":"sha256:71098d51e47738da469d6ff1e6a685022d4e0bfe23e1f09f2c144729f109292e","target":"record","created_at":"2026-08-03T01:34:13Z","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":"1fc543cf01f6d24ae49dc92dc4ad0b5a4d4cf6fc18c21311bc4a2697f12f029e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T13:41:51Z","title_canon_sha256":"d754c31c19e38db182427f0ba726a8700b60ca139d30264d0d22084159e3e3e2"},"schema_version":"1.0","source":{"id":"2607.29419","kind":"arxiv","version":1}},"canonical_sha256":"d70a1d2468fd2c69b1cb475508bb95832952161ac4dc8e6f290ff81ca218bb71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d70a1d2468fd2c69b1cb475508bb95832952161ac4dc8e6f290ff81ca218bb71","first_computed_at":"2026-08-03T01:34:13.594964Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:34:13.594964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ixyKzmWRU04HUzkZmH0B5ydHQ17lmmoln1eI8WyX+hDroIKiAuEU2LsHFyYRTdQ+9DnSXcRJSx/8hRH1iiVaAA==","signature_status":"signed_v1","signed_at":"2026-08-03T01:34:13.596480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.29419","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71098d51e47738da469d6ff1e6a685022d4e0bfe23e1f09f2c144729f109292e","sha256:84526746eeb8360e0330f700379800aad13ecd8c4a14e278fbd2870256b9d34c"],"state_sha256":"b3cc3afe29bef9b44fd51f33ecaecef9d3c2467a37c7188af39992a3d6db6c5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pVYBs+OjZWO8FLf3IVgNJwVbseKcqDqZ3ZZzuRvW7uHxzpNjENUB0+u8ltjYHBvqjSdNXEpNmOBG0nfj7Nv9Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T10:32:56.535039Z","bundle_sha256":"e0755ccfe04d7becf949f9a94268f9cd731110b462c1ca320993232571b84448"}}