{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KYASULWEYSJHUIKOYE4U4AVHXN","short_pith_number":"pith:KYASULWE","canonical_record":{"source":{"id":"2410.08632","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-11T08:54:45Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"3b615d0e231102502f984593a364daf9c42cebc49e14287d05e9db9b0030b80e","abstract_canon_sha256":"637f6d7e5f8aa3f1362ae585edf789ebca6d283177b0db79f02c485ba5677f84"},"schema_version":"1.0"},"canonical_sha256":"56012a2ec4c4927a214ec1394e02a7bb6635f7f55bda721e97ddcdf15855c637","source":{"kind":"arxiv","id":"2410.08632","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08632","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08632v1","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08632","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"KYASULWEYSJH","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"pith_short_16","alias_value":"KYASULWEYSJHUIKO","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"pith_short_8","alias_value":"KYASULWE","created_at":"2026-07-05T09:19:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KYASULWEYSJHUIKOYE4U4AVHXN","target":"record","payload":{"canonical_record":{"source":{"id":"2410.08632","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-11T08:54:45Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"3b615d0e231102502f984593a364daf9c42cebc49e14287d05e9db9b0030b80e","abstract_canon_sha256":"637f6d7e5f8aa3f1362ae585edf789ebca6d283177b0db79f02c485ba5677f84"},"schema_version":"1.0"},"canonical_sha256":"56012a2ec4c4927a214ec1394e02a7bb6635f7f55bda721e97ddcdf15855c637","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:15.422717Z","signature_b64":"gktDWQGZru98hM1B73E9HxtweXsI1uIi9/E3iYkOBG7ew/RyaFUho5o+EefFWMeWrN7UYP2S+ed2JqaCc+CpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56012a2ec4c4927a214ec1394e02a7bb6635f7f55bda721e97ddcdf15855c637","last_reissued_at":"2026-07-05T09:19:15.422240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:15.422240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.08632","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":"2026-07-05T09:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SYcsAdy1UF/eYsTBTAUUBcxCvlNR7AeqZCc9+KmSqFcmNlnA4LWq1aUFSJYcSoXkqMeK7yi92BQmDbCSFWrPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T23:30:04.056285Z"},"content_sha256":"c6261b769d4670926753b38bd581c94eb7662493951b254ff0cb4629ed6e68a8","schema_version":"1.0","event_id":"sha256:c6261b769d4670926753b38bd581c94eb7662493951b254ff0cb4629ed6e68a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KYASULWEYSJHUIKOYE4U4AVHXN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Words as Beacons: Guiding RL Agents with High-Level Language Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Alain Andres, Javier Del Ser, Pedro G.Bascoy, Unai Ruiz-Gonzalez","submitted_at":"2024-10-11T08:54:45Z","abstract_excerpt":"Sparse reward environments in reinforcement learning (RL) pose significant challenges for exploration, often leading to inefficient or incomplete learning processes. To tackle this issue, this work proposes a teacher-student RL framework that leverages Large Language Models (LLMs) as \"teachers\" to guide the agent's learning process by decomposing complex tasks into subgoals. Due to their inherent capability to understand RL environments based on a textual description of structure and purpose, LLMs can provide subgoals to accomplish the task defined for the environment in a similar fashion to h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08632","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/2410.08632/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":"2026-07-05T09:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xhbsuzO2U/iCTedXKn4t1qOyglIKLCT+e6lAAEznVDCeES/zmqEl8Md5zUBDQT9v1kU+wNih5Bl6ev+enVXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T23:30:04.057128Z"},"content_sha256":"f2681f9a43ec5a99f7e0f6fc5b93b2fbb1ebb6a928283074bc60122721651e9e","schema_version":"1.0","event_id":"sha256:f2681f9a43ec5a99f7e0f6fc5b93b2fbb1ebb6a928283074bc60122721651e9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KYASULWEYSJHUIKOYE4U4AVHXN/bundle.json","state_url":"https://pith.science/pith/KYASULWEYSJHUIKOYE4U4AVHXN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KYASULWEYSJHUIKOYE4U4AVHXN/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":"2026-08-13T23:30:04Z","links":{"resolver":"https://pith.science/pith/KYASULWEYSJHUIKOYE4U4AVHXN","bundle":"https://pith.science/pith/KYASULWEYSJHUIKOYE4U4AVHXN/bundle.json","state":"https://pith.science/pith/KYASULWEYSJHUIKOYE4U4AVHXN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KYASULWEYSJHUIKOYE4U4AVHXN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KYASULWEYSJHUIKOYE4U4AVHXN","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":"637f6d7e5f8aa3f1362ae585edf789ebca6d283177b0db79f02c485ba5677f84","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-11T08:54:45Z","title_canon_sha256":"3b615d0e231102502f984593a364daf9c42cebc49e14287d05e9db9b0030b80e"},"schema_version":"1.0","source":{"id":"2410.08632","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08632","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08632v1","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08632","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"KYASULWEYSJH","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"pith_short_16","alias_value":"KYASULWEYSJHUIKO","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"pith_short_8","alias_value":"KYASULWE","created_at":"2026-07-05T09:19:15Z"}],"graph_snapshots":[{"event_id":"sha256:f2681f9a43ec5a99f7e0f6fc5b93b2fbb1ebb6a928283074bc60122721651e9e","target":"graph","created_at":"2026-07-05T09:19:15Z","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/2410.08632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse reward environments in reinforcement learning (RL) pose significant challenges for exploration, often leading to inefficient or incomplete learning processes. To tackle this issue, this work proposes a teacher-student RL framework that leverages Large Language Models (LLMs) as \"teachers\" to guide the agent's learning process by decomposing complex tasks into subgoals. Due to their inherent capability to understand RL environments based on a textual description of structure and purpose, LLMs can provide subgoals to accomplish the task defined for the environment in a similar fashion to h","authors_text":"Alain Andres, Javier Del Ser, Pedro G.Bascoy, Unai Ruiz-Gonzalez","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-11T08:54:45Z","title":"Words as Beacons: Guiding RL Agents with High-Level Language Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08632","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:c6261b769d4670926753b38bd581c94eb7662493951b254ff0cb4629ed6e68a8","target":"record","created_at":"2026-07-05T09:19:15Z","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":"637f6d7e5f8aa3f1362ae585edf789ebca6d283177b0db79f02c485ba5677f84","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-11T08:54:45Z","title_canon_sha256":"3b615d0e231102502f984593a364daf9c42cebc49e14287d05e9db9b0030b80e"},"schema_version":"1.0","source":{"id":"2410.08632","kind":"arxiv","version":1}},"canonical_sha256":"56012a2ec4c4927a214ec1394e02a7bb6635f7f55bda721e97ddcdf15855c637","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56012a2ec4c4927a214ec1394e02a7bb6635f7f55bda721e97ddcdf15855c637","first_computed_at":"2026-07-05T09:19:15.422240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:15.422240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gktDWQGZru98hM1B73E9HxtweXsI1uIi9/E3iYkOBG7ew/RyaFUho5o+EefFWMeWrN7UYP2S+ed2JqaCc+CpCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:15.422717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08632","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6261b769d4670926753b38bd581c94eb7662493951b254ff0cb4629ed6e68a8","sha256:f2681f9a43ec5a99f7e0f6fc5b93b2fbb1ebb6a928283074bc60122721651e9e"],"state_sha256":"707e849cedd08694c2d9ac222a15a85dea1c11be437752325d8b295161742908"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lytUvaeXQ1a6Le2Gkut+2Cr+s+B8WyNyGTGc9rzj4dQFC/StE7mVWIuVyvNgvN0L9qaBrc7DAl+lLLwfl8DpDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T23:30:04.099011Z","bundle_sha256":"eb422f8487440ee6cb8557ecf198067d24125f323098f2b670c8640ad5b97024"}}