{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CJZXT6KREC4OLYMAAJSIVTFKSN","short_pith_number":"pith:CJZXT6KR","canonical_record":{"source":{"id":"2510.11686","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-13T17:49:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0cd4f5a32ac88cce740d8f87723e392506447276c421e83227f5068326149277","abstract_canon_sha256":"fa6a33030fe47672f6e0027c23953f2af9f4c5b4f420effd9143a319a55c0f07"},"schema_version":"1.0"},"canonical_sha256":"127379f95120b8e5e18002648accaa93594a2c2f9c71b63f59675cd8047635ee","source":{"kind":"arxiv","id":"2510.11686","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.11686","created_at":"2026-07-16T01:22:28Z"},{"alias_kind":"arxiv_version","alias_value":"2510.11686v2","created_at":"2026-07-16T01:22:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.11686","created_at":"2026-07-16T01:22:28Z"},{"alias_kind":"pith_short_12","alias_value":"CJZXT6KREC4O","created_at":"2026-07-16T01:22:28Z"},{"alias_kind":"pith_short_16","alias_value":"CJZXT6KREC4OLYMA","created_at":"2026-07-16T01:22:28Z"},{"alias_kind":"pith_short_8","alias_value":"CJZXT6KR","created_at":"2026-07-16T01:22:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CJZXT6KREC4OLYMAAJSIVTFKSN","target":"record","payload":{"canonical_record":{"source":{"id":"2510.11686","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-13T17:49:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0cd4f5a32ac88cce740d8f87723e392506447276c421e83227f5068326149277","abstract_canon_sha256":"fa6a33030fe47672f6e0027c23953f2af9f4c5b4f420effd9143a319a55c0f07"},"schema_version":"1.0"},"canonical_sha256":"127379f95120b8e5e18002648accaa93594a2c2f9c71b63f59675cd8047635ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:22:28.690884Z","signature_b64":"dzhUXbUJxKOds9qmMgr7CfcluZr5rq8xNtKbTX+HGMpiK+Xntpp5TAUE09G2nVlLp10xp9dHTeKc2F7IQ81LCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"127379f95120b8e5e18002648accaa93594a2c2f9c71b63f59675cd8047635ee","last_reissued_at":"2026-07-16T01:22:28.689992Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:22:28.689992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.11686","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-16T01:22:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XNT7Hthom9UeH2yC7uxms4bwU4WzuUik7N7RJ1XU7DoFo+JLYwVHN4uHAQZ2AAUla/Qn6O1wtwW6AEMYrYCoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T23:21:23.258152Z"},"content_sha256":"accec9abaeec05e6b5adf4a4d1324a630b4a19f6b959e5df9364088354047303","schema_version":"1.0","event_id":"sha256:accec9abaeec05e6b5adf4a4d1324a630b4a19f6b959e5df9364088354047303"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CJZXT6KREC4OLYMAAJSIVTFKSN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Dylan J. Foster, Jens Tuyls, Jordan T. Ash","submitted_at":"2025-10-13T17:49:05Z","abstract_excerpt":"Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model. In this paper, we investigate the value of deliberate exploration -- explicitly incentivizing the model to discover novel and diverse behaviors -- and aim to understand how the knowledge in pre-trained models can guide this search. Our main finding is that exploration with a simple, principled, representation-based bonus derived from the pre-trained language model's hid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.11686","kind":"arxiv","version":2},"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/2510.11686/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":"2026-07-16T01:22:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fQ36H9gDVWf03uael3c4O07FExzqIskFifhksHhaUvKLv3aouHNr3G9I7lhAgp+41qJrhrDg6IGgZr9FEgnIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T23:21:23.258691Z"},"content_sha256":"a083bdd9aa793756c332512a96cf67ae0de2a7b6f659e9010dbfc2a0d5608e4a","schema_version":"1.0","event_id":"sha256:a083bdd9aa793756c332512a96cf67ae0de2a7b6f659e9010dbfc2a0d5608e4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CJZXT6KREC4OLYMAAJSIVTFKSN/bundle.json","state_url":"https://pith.science/pith/CJZXT6KREC4OLYMAAJSIVTFKSN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CJZXT6KREC4OLYMAAJSIVTFKSN/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":"2026-08-13T23:21:23Z","links":{"resolver":"https://pith.science/pith/CJZXT6KREC4OLYMAAJSIVTFKSN","bundle":"https://pith.science/pith/CJZXT6KREC4OLYMAAJSIVTFKSN/bundle.json","state":"https://pith.science/pith/CJZXT6KREC4OLYMAAJSIVTFKSN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CJZXT6KREC4OLYMAAJSIVTFKSN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CJZXT6KREC4OLYMAAJSIVTFKSN","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":"fa6a33030fe47672f6e0027c23953f2af9f4c5b4f420effd9143a319a55c0f07","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-13T17:49:05Z","title_canon_sha256":"0cd4f5a32ac88cce740d8f87723e392506447276c421e83227f5068326149277"},"schema_version":"1.0","source":{"id":"2510.11686","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.11686","created_at":"2026-07-16T01:22:28Z"},{"alias_kind":"arxiv_version","alias_value":"2510.11686v2","created_at":"2026-07-16T01:22:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.11686","created_at":"2026-07-16T01:22:28Z"},{"alias_kind":"pith_short_12","alias_value":"CJZXT6KREC4O","created_at":"2026-07-16T01:22:28Z"},{"alias_kind":"pith_short_16","alias_value":"CJZXT6KREC4OLYMA","created_at":"2026-07-16T01:22:28Z"},{"alias_kind":"pith_short_8","alias_value":"CJZXT6KR","created_at":"2026-07-16T01:22:28Z"}],"graph_snapshots":[{"event_id":"sha256:a083bdd9aa793756c332512a96cf67ae0de2a7b6f659e9010dbfc2a0d5608e4a","target":"graph","created_at":"2026-07-16T01:22:28Z","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/2510.11686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model. In this paper, we investigate the value of deliberate exploration -- explicitly incentivizing the model to discover novel and diverse behaviors -- and aim to understand how the knowledge in pre-trained models can guide this search. Our main finding is that exploration with a simple, principled, representation-based bonus derived from the pre-trained language model's hid","authors_text":"Akshay Krishnamurthy, Dylan J. Foster, Jens Tuyls, Jordan T. Ash","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-13T17:49:05Z","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.11686","kind":"arxiv","version":2},"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:accec9abaeec05e6b5adf4a4d1324a630b4a19f6b959e5df9364088354047303","target":"record","created_at":"2026-07-16T01:22:28Z","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":"fa6a33030fe47672f6e0027c23953f2af9f4c5b4f420effd9143a319a55c0f07","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-13T17:49:05Z","title_canon_sha256":"0cd4f5a32ac88cce740d8f87723e392506447276c421e83227f5068326149277"},"schema_version":"1.0","source":{"id":"2510.11686","kind":"arxiv","version":2}},"canonical_sha256":"127379f95120b8e5e18002648accaa93594a2c2f9c71b63f59675cd8047635ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"127379f95120b8e5e18002648accaa93594a2c2f9c71b63f59675cd8047635ee","first_computed_at":"2026-07-16T01:22:28.689992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T01:22:28.689992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dzhUXbUJxKOds9qmMgr7CfcluZr5rq8xNtKbTX+HGMpiK+Xntpp5TAUE09G2nVlLp10xp9dHTeKc2F7IQ81LCw==","signature_status":"signed_v1","signed_at":"2026-07-16T01:22:28.690884Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.11686","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:accec9abaeec05e6b5adf4a4d1324a630b4a19f6b959e5df9364088354047303","sha256:a083bdd9aa793756c332512a96cf67ae0de2a7b6f659e9010dbfc2a0d5608e4a"],"state_sha256":"97e80fa847860468953512db3c7e0c1dabee97e4ce21c49e50740792c2fa393c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EBVzdggKXvVXt6NxqoFsIPuXN5mrXyo0z5b916uqYCxeY+h9zFr7Uum3yh55jNKOHsvNrUvQXDBJfJ1q/oz+CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T23:21:23.280774Z","bundle_sha256":"4ad6feb2b8f4656fd6500e1757ef0ecb2a2d01cf1a5189e20a77718013423d74"}}