{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Y2TYKMUUCE7YMBMI7PRP2OX5JN","short_pith_number":"pith:Y2TYKMUU","canonical_record":{"source":{"id":"2307.09668","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-18T22:37:30Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3723f65aa77a43d867f60b83ef8cb3d46a82d7d57387b1fb644efaaef7218736","abstract_canon_sha256":"24d8012872b7944265b62e5510de3d4148be227804c480e7a3582ca4a6a81043"},"schema_version":"1.0"},"canonical_sha256":"c6a7853294113f860588fbe2fd3afd4b706a95034827f83f682a0dbb7b2f8fa4","source":{"kind":"arxiv","id":"2307.09668","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.09668","created_at":"2026-07-05T06:32:44Z"},{"alias_kind":"arxiv_version","alias_value":"2307.09668v1","created_at":"2026-07-05T06:32:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09668","created_at":"2026-07-05T06:32:44Z"},{"alias_kind":"pith_short_12","alias_value":"Y2TYKMUUCE7Y","created_at":"2026-07-05T06:32:44Z"},{"alias_kind":"pith_short_16","alias_value":"Y2TYKMUUCE7YMBMI","created_at":"2026-07-05T06:32:44Z"},{"alias_kind":"pith_short_8","alias_value":"Y2TYKMUU","created_at":"2026-07-05T06:32:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Y2TYKMUUCE7YMBMI7PRP2OX5JN","target":"record","payload":{"canonical_record":{"source":{"id":"2307.09668","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-18T22:37:30Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3723f65aa77a43d867f60b83ef8cb3d46a82d7d57387b1fb644efaaef7218736","abstract_canon_sha256":"24d8012872b7944265b62e5510de3d4148be227804c480e7a3582ca4a6a81043"},"schema_version":"1.0"},"canonical_sha256":"c6a7853294113f860588fbe2fd3afd4b706a95034827f83f682a0dbb7b2f8fa4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:44.293260Z","signature_b64":"FbtcUQw6lS+jJgKtGJWpF0vTFlcAaQJllIGkUVxX4TbOHoZGvcf8vLfDEZ2smS0ZXyx8RR3wlEh15qKWI5SZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6a7853294113f860588fbe2fd3afd4b706a95034827f83f682a0dbb7b2f8fa4","last_reissued_at":"2026-07-05T06:32:44.292763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:44.292763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.09668","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":"2026-07-05T06:32:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bb56tNlKkWXZ6jy5AlPXYHKjQGAFS+vJYneNbX2gHhk92RX0sVNVseVuEgdmBuE2ZdTQuk68VkjNjVpl7KSjCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T23:48:31.289227Z"},"content_sha256":"4803d076d1c69fd7b71717a7756dfb33651c6f0bc5ee1ed31065b976b34f1e85","schema_version":"1.0","event_id":"sha256:4803d076d1c69fd7b71717a7756dfb33651c6f0bc5ee1ed31065b976b34f1e85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Y2TYKMUUCE7YMBMI7PRP2OX5JN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards A Unified Agent with Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Arunkumar Byravan, Leonard Hasenclever, Markus Wulfmeier, Martin Riedmiller, Nicolas Heess, Norman Di Palo","submitted_at":"2023-07-18T22:37:30Z","abstract_excerpt":"Language Models and Vision Language Models have recently demonstrated unprecedented capabilities in terms of understanding human intentions, reasoning, scene understanding, and planning-like behaviour, in text form, among many others. In this work, we investigate how to embed and leverage such abilities in Reinforcement Learning (RL) agents. We design a framework that uses language as the core reasoning tool, exploring how this enables an agent to tackle a series of fundamental RL challenges, such as efficient exploration, reusing experience data, scheduling skills, and learning from observati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09668","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/2307.09668/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":"2026-07-05T06:32:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qxbx8QXq7LWF8wpkigAt9JtK7RPpQ0Y7JwFRm9nN6lGYk7jw8rXq7L7FNDd0rTsWWpPmn19iBO0hPBc64hToBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T23:48:31.289617Z"},"content_sha256":"6dd97ef13171a08743ee9bac6e7429a43b19801f58e956f1aecabe37ef5dd476","schema_version":"1.0","event_id":"sha256:6dd97ef13171a08743ee9bac6e7429a43b19801f58e956f1aecabe37ef5dd476"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y2TYKMUUCE7YMBMI7PRP2OX5JN/bundle.json","state_url":"https://pith.science/pith/Y2TYKMUUCE7YMBMI7PRP2OX5JN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y2TYKMUUCE7YMBMI7PRP2OX5JN/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":"2026-07-24T23:48:31Z","links":{"resolver":"https://pith.science/pith/Y2TYKMUUCE7YMBMI7PRP2OX5JN","bundle":"https://pith.science/pith/Y2TYKMUUCE7YMBMI7PRP2OX5JN/bundle.json","state":"https://pith.science/pith/Y2TYKMUUCE7YMBMI7PRP2OX5JN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y2TYKMUUCE7YMBMI7PRP2OX5JN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Y2TYKMUUCE7YMBMI7PRP2OX5JN","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":"24d8012872b7944265b62e5510de3d4148be227804c480e7a3582ca4a6a81043","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-18T22:37:30Z","title_canon_sha256":"3723f65aa77a43d867f60b83ef8cb3d46a82d7d57387b1fb644efaaef7218736"},"schema_version":"1.0","source":{"id":"2307.09668","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.09668","created_at":"2026-07-05T06:32:44Z"},{"alias_kind":"arxiv_version","alias_value":"2307.09668v1","created_at":"2026-07-05T06:32:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09668","created_at":"2026-07-05T06:32:44Z"},{"alias_kind":"pith_short_12","alias_value":"Y2TYKMUUCE7Y","created_at":"2026-07-05T06:32:44Z"},{"alias_kind":"pith_short_16","alias_value":"Y2TYKMUUCE7YMBMI","created_at":"2026-07-05T06:32:44Z"},{"alias_kind":"pith_short_8","alias_value":"Y2TYKMUU","created_at":"2026-07-05T06:32:44Z"}],"graph_snapshots":[{"event_id":"sha256:6dd97ef13171a08743ee9bac6e7429a43b19801f58e956f1aecabe37ef5dd476","target":"graph","created_at":"2026-07-05T06:32:44Z","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/2307.09668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language Models and Vision Language Models have recently demonstrated unprecedented capabilities in terms of understanding human intentions, reasoning, scene understanding, and planning-like behaviour, in text form, among many others. In this work, we investigate how to embed and leverage such abilities in Reinforcement Learning (RL) agents. We design a framework that uses language as the core reasoning tool, exploring how this enables an agent to tackle a series of fundamental RL challenges, such as efficient exploration, reusing experience data, scheduling skills, and learning from observati","authors_text":"Arunkumar Byravan, Leonard Hasenclever, Markus Wulfmeier, Martin Riedmiller, Nicolas Heess, Norman Di Palo","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-18T22:37:30Z","title":"Towards A Unified Agent with Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09668","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":"sha256:4803d076d1c69fd7b71717a7756dfb33651c6f0bc5ee1ed31065b976b34f1e85","target":"record","created_at":"2026-07-05T06:32:44Z","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":"24d8012872b7944265b62e5510de3d4148be227804c480e7a3582ca4a6a81043","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-18T22:37:30Z","title_canon_sha256":"3723f65aa77a43d867f60b83ef8cb3d46a82d7d57387b1fb644efaaef7218736"},"schema_version":"1.0","source":{"id":"2307.09668","kind":"arxiv","version":1}},"canonical_sha256":"c6a7853294113f860588fbe2fd3afd4b706a95034827f83f682a0dbb7b2f8fa4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6a7853294113f860588fbe2fd3afd4b706a95034827f83f682a0dbb7b2f8fa4","first_computed_at":"2026-07-05T06:32:44.292763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:32:44.292763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FbtcUQw6lS+jJgKtGJWpF0vTFlcAaQJllIGkUVxX4TbOHoZGvcf8vLfDEZ2smS0ZXyx8RR3wlEh15qKWI5SZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:32:44.293260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.09668","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4803d076d1c69fd7b71717a7756dfb33651c6f0bc5ee1ed31065b976b34f1e85","sha256:6dd97ef13171a08743ee9bac6e7429a43b19801f58e956f1aecabe37ef5dd476"],"state_sha256":"350a69c4adad7f8214d4e6d5f7fa6ea431c67d698de19b3843f7e6e342ad510e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"riNMQXnSaRIaIl+6TnW7tM0wIoTEcsIxtvsqpnFrRHa89NzHsKvapyQMWIF/W3TxxBU1+fRPmnsBCqyaaTA+CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T23:48:31.291770Z","bundle_sha256":"3bfa106a957af74f07c3701c4dc496cd6975be88e8c8517bc65167ecbfa50e8c"}}