{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:W6N7XAY2FMXSH7QJIEGBO5VKWR","short_pith_number":"pith:W6N7XAY2","canonical_record":{"source":{"id":"2508.01287","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-02T09:42:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c0a66bdc459098bf779cb6da473540da6a96492a9c07fc8665c7256f78366ecc","abstract_canon_sha256":"c50ed86ac6929942903153936c6f1852563c20640a7fb4239e939b63a27c045d"},"schema_version":"1.0"},"canonical_sha256":"b79bfb831a2b2f23fe09410c1776aab45fa35cbec2ba3d009dd998455014b7cb","source":{"kind":"arxiv","id":"2508.01287","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01287","created_at":"2026-07-05T11:47:36Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01287v1","created_at":"2026-07-05T11:47:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01287","created_at":"2026-07-05T11:47:36Z"},{"alias_kind":"pith_short_12","alias_value":"W6N7XAY2FMXS","created_at":"2026-07-05T11:47:36Z"},{"alias_kind":"pith_short_16","alias_value":"W6N7XAY2FMXSH7QJ","created_at":"2026-07-05T11:47:36Z"},{"alias_kind":"pith_short_8","alias_value":"W6N7XAY2","created_at":"2026-07-05T11:47:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:W6N7XAY2FMXSH7QJIEGBO5VKWR","target":"record","payload":{"canonical_record":{"source":{"id":"2508.01287","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-02T09:42:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c0a66bdc459098bf779cb6da473540da6a96492a9c07fc8665c7256f78366ecc","abstract_canon_sha256":"c50ed86ac6929942903153936c6f1852563c20640a7fb4239e939b63a27c045d"},"schema_version":"1.0"},"canonical_sha256":"b79bfb831a2b2f23fe09410c1776aab45fa35cbec2ba3d009dd998455014b7cb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:36.737150Z","signature_b64":"kDMYQxSIm6DMtcQCzTgBfW40wKefYRF7kVzCurPXwXPCWdEI8EacQsxMn7TDj3J9adT7OovE8D4Li7T2utRCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b79bfb831a2b2f23fe09410c1776aab45fa35cbec2ba3d009dd998455014b7cb","last_reissued_at":"2026-07-05T11:47:36.736601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:36.736601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.01287","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":"2026-07-05T11:47:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cMacZJXj6oS9Sy1GZTOkDOmyFu+TDQwzBZiwXBGQXYwYpkY/55bHCe0IeohaFkunb3jAkpfePQpXaZ1p1ExSAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T16:32:14.474274Z"},"content_sha256":"383a52c8c5b9eea30a3c5e09a2e7962b2de58ea5b285d485ab11d2eb9343ab54","schema_version":"1.0","event_id":"sha256:383a52c8c5b9eea30a3c5e09a2e7962b2de58ea5b285d485ab11d2eb9343ab54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:W6N7XAY2FMXSH7QJIEGBO5VKWR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploitation Is All You Need... for Exploration","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jesse Roberts, Micah Rentschler","submitted_at":"2025-08-02T09:42:59Z","abstract_excerpt":"Ensuring sufficient exploration is a central challenge when training meta-reinforcement learning (meta-RL) agents to solve novel environments. Conventional solutions to the exploration-exploitation dilemma inject explicit incentives such as randomization, uncertainty bonuses, or intrinsic rewards to encourage exploration. In this work, we hypothesize that an agent trained solely to maximize a greedy (exploitation-only) objective can nonetheless exhibit emergent exploratory behavior, provided three conditions are met: (1) Recurring Environmental Structure, where the environment features repeata"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01287","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/2508.01287/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":"2026-07-05T11:47:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C/1NzHiZNxqLg9T0tsTS+aovSI6NbDfUTj4byOgI9n1uVJhSl8JSidRE7PomhnsmhPoSQZGMlI+W5juR4X5uAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T16:32:14.475024Z"},"content_sha256":"7983ca178947bff046ca756c04b2827242edd3f634925ec0a635153b414b23eb","schema_version":"1.0","event_id":"sha256:7983ca178947bff046ca756c04b2827242edd3f634925ec0a635153b414b23eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W6N7XAY2FMXSH7QJIEGBO5VKWR/bundle.json","state_url":"https://pith.science/pith/W6N7XAY2FMXSH7QJIEGBO5VKWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W6N7XAY2FMXSH7QJIEGBO5VKWR/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":"2026-08-14T16:32:14Z","links":{"resolver":"https://pith.science/pith/W6N7XAY2FMXSH7QJIEGBO5VKWR","bundle":"https://pith.science/pith/W6N7XAY2FMXSH7QJIEGBO5VKWR/bundle.json","state":"https://pith.science/pith/W6N7XAY2FMXSH7QJIEGBO5VKWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W6N7XAY2FMXSH7QJIEGBO5VKWR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W6N7XAY2FMXSH7QJIEGBO5VKWR","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":"c50ed86ac6929942903153936c6f1852563c20640a7fb4239e939b63a27c045d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-02T09:42:59Z","title_canon_sha256":"c0a66bdc459098bf779cb6da473540da6a96492a9c07fc8665c7256f78366ecc"},"schema_version":"1.0","source":{"id":"2508.01287","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01287","created_at":"2026-07-05T11:47:36Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01287v1","created_at":"2026-07-05T11:47:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01287","created_at":"2026-07-05T11:47:36Z"},{"alias_kind":"pith_short_12","alias_value":"W6N7XAY2FMXS","created_at":"2026-07-05T11:47:36Z"},{"alias_kind":"pith_short_16","alias_value":"W6N7XAY2FMXSH7QJ","created_at":"2026-07-05T11:47:36Z"},{"alias_kind":"pith_short_8","alias_value":"W6N7XAY2","created_at":"2026-07-05T11:47:36Z"}],"graph_snapshots":[{"event_id":"sha256:7983ca178947bff046ca756c04b2827242edd3f634925ec0a635153b414b23eb","target":"graph","created_at":"2026-07-05T11:47:36Z","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/2508.01287/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensuring sufficient exploration is a central challenge when training meta-reinforcement learning (meta-RL) agents to solve novel environments. Conventional solutions to the exploration-exploitation dilemma inject explicit incentives such as randomization, uncertainty bonuses, or intrinsic rewards to encourage exploration. In this work, we hypothesize that an agent trained solely to maximize a greedy (exploitation-only) objective can nonetheless exhibit emergent exploratory behavior, provided three conditions are met: (1) Recurring Environmental Structure, where the environment features repeata","authors_text":"Jesse Roberts, Micah Rentschler","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-02T09:42:59Z","title":"Exploitation Is All You Need... for Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01287","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":"sha256:383a52c8c5b9eea30a3c5e09a2e7962b2de58ea5b285d485ab11d2eb9343ab54","target":"record","created_at":"2026-07-05T11:47:36Z","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":"c50ed86ac6929942903153936c6f1852563c20640a7fb4239e939b63a27c045d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-02T09:42:59Z","title_canon_sha256":"c0a66bdc459098bf779cb6da473540da6a96492a9c07fc8665c7256f78366ecc"},"schema_version":"1.0","source":{"id":"2508.01287","kind":"arxiv","version":1}},"canonical_sha256":"b79bfb831a2b2f23fe09410c1776aab45fa35cbec2ba3d009dd998455014b7cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b79bfb831a2b2f23fe09410c1776aab45fa35cbec2ba3d009dd998455014b7cb","first_computed_at":"2026-07-05T11:47:36.736601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:36.736601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kDMYQxSIm6DMtcQCzTgBfW40wKefYRF7kVzCurPXwXPCWdEI8EacQsxMn7TDj3J9adT7OovE8D4Li7T2utRCCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:36.737150Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.01287","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:383a52c8c5b9eea30a3c5e09a2e7962b2de58ea5b285d485ab11d2eb9343ab54","sha256:7983ca178947bff046ca756c04b2827242edd3f634925ec0a635153b414b23eb"],"state_sha256":"6ac31c6ceb2fa6d24e29c0254d6e85b92652a5575ac9e881342f93f174f5708f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IGcZM2x45S3XO2a8hL7pgx9ewomhsRfRXoLo8Fj821MGVOI54UM0rgM+xOCxJMEXSqJEbzcRd4DOPMrxwbJAAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T16:32:14.484978Z","bundle_sha256":"fbc99793070a999723bfb38e9e0202a90144c8fafc0bead4d5450e2b12eb9a17"}}