{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3IVGWU2NUZGTVKQWFYML2OOQRQ","short_pith_number":"pith:3IVGWU2N","canonical_record":{"source":{"id":"2312.04736","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-07T22:33:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5fc33eed8d9a56e8088cce0c7f35cc276f5bc2dedf6adf751726d5eacad5ddce","abstract_canon_sha256":"eae3e4e83b825fdecd4d5c39a77946471a602a9ce4ec3cc37b27e30564fafd94"},"schema_version":"1.0"},"canonical_sha256":"da2a6b534da64d3aaa162e18bd39d08c2733402f4efffa796a45f0586347e9f8","source":{"kind":"arxiv","id":"2312.04736","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04736","created_at":"2026-07-05T07:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04736v1","created_at":"2026-07-05T07:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04736","created_at":"2026-07-05T07:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"3IVGWU2NUZGT","created_at":"2026-07-05T07:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"3IVGWU2NUZGTVKQW","created_at":"2026-07-05T07:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"3IVGWU2N","created_at":"2026-07-05T07:21:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3IVGWU2NUZGTVKQWFYML2OOQRQ","target":"record","payload":{"canonical_record":{"source":{"id":"2312.04736","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-07T22:33:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5fc33eed8d9a56e8088cce0c7f35cc276f5bc2dedf6adf751726d5eacad5ddce","abstract_canon_sha256":"eae3e4e83b825fdecd4d5c39a77946471a602a9ce4ec3cc37b27e30564fafd94"},"schema_version":"1.0"},"canonical_sha256":"da2a6b534da64d3aaa162e18bd39d08c2733402f4efffa796a45f0586347e9f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:50.563880Z","signature_b64":"XfdOjp/FKurGLkbwOS1zkKtazag000tt8MgOPTm8EBMGuPAQVhHoTuCY97OdIeypNDYIblLiYH5W5SBSo8R8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da2a6b534da64d3aaa162e18bd39d08c2733402f4efffa796a45f0586347e9f8","last_reissued_at":"2026-07-05T07:21:50.563459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:50.563459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.04736","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":"2026-07-05T07:21:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AlUvPMAkXPhVRz9p54oGPeQ/nwKeSvB3CVgKAMLEWlfwFm2dsxao7pZDmy6UcdclgAqrpdJyxS55J/VJygw+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:24:19.931834Z"},"content_sha256":"ce154732a87ffd7af59e6e5edc9283263239212196b89dcad1f760bae9033ca7","schema_version":"1.0","event_id":"sha256:ce154732a87ffd7af59e6e5edc9283263239212196b89dcad1f760bae9033ca7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3IVGWU2NUZGTVKQWFYML2OOQRQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Feedback All You Need? Leveraging Natural Language Feedback in Goal-Conditioned Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alessandro Suglia, Max Taylor-Davies, Sabrina McCallum, Stefano V. Albrecht","submitted_at":"2023-12-07T22:33:34Z","abstract_excerpt":"Despite numerous successes, the field of reinforcement learning (RL) remains far from matching the impressive generalisation power of human behaviour learning. One possible way to help bridge this gap be to provide RL agents with richer, more human-like feedback expressed in natural language. To investigate this idea, we first extend BabyAI to automatically generate language feedback from the environment dynamics and goal condition success. Then, we modify the Decision Transformer architecture to take advantage of this additional signal. We find that training with language feedback either in p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04736","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/2312.04736/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":"2026-07-05T07:21:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kCTIDN61tAbTcwjq7dXvCnGaWbibIjfMIhY7A/+JVzKY3WWTpQyTrALIChAgfDMLovxph3f+iV2HXO7sX/CTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:24:19.932329Z"},"content_sha256":"90cb9ef873baa9d30fab623dbd1a584e3d348809dbbea70c4d16748a77b21390","schema_version":"1.0","event_id":"sha256:90cb9ef873baa9d30fab623dbd1a584e3d348809dbbea70c4d16748a77b21390"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3IVGWU2NUZGTVKQWFYML2OOQRQ/bundle.json","state_url":"https://pith.science/pith/3IVGWU2NUZGTVKQWFYML2OOQRQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3IVGWU2NUZGTVKQWFYML2OOQRQ/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":"2026-08-10T23:24:19Z","links":{"resolver":"https://pith.science/pith/3IVGWU2NUZGTVKQWFYML2OOQRQ","bundle":"https://pith.science/pith/3IVGWU2NUZGTVKQWFYML2OOQRQ/bundle.json","state":"https://pith.science/pith/3IVGWU2NUZGTVKQWFYML2OOQRQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3IVGWU2NUZGTVKQWFYML2OOQRQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3IVGWU2NUZGTVKQWFYML2OOQRQ","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":"eae3e4e83b825fdecd4d5c39a77946471a602a9ce4ec3cc37b27e30564fafd94","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-07T22:33:34Z","title_canon_sha256":"5fc33eed8d9a56e8088cce0c7f35cc276f5bc2dedf6adf751726d5eacad5ddce"},"schema_version":"1.0","source":{"id":"2312.04736","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04736","created_at":"2026-07-05T07:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04736v1","created_at":"2026-07-05T07:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04736","created_at":"2026-07-05T07:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"3IVGWU2NUZGT","created_at":"2026-07-05T07:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"3IVGWU2NUZGTVKQW","created_at":"2026-07-05T07:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"3IVGWU2N","created_at":"2026-07-05T07:21:50Z"}],"graph_snapshots":[{"event_id":"sha256:90cb9ef873baa9d30fab623dbd1a584e3d348809dbbea70c4d16748a77b21390","target":"graph","created_at":"2026-07-05T07:21:50Z","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/2312.04736/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite numerous successes, the field of reinforcement learning (RL) remains far from matching the impressive generalisation power of human behaviour learning. One possible way to help bridge this gap be to provide RL agents with richer, more human-like feedback expressed in natural language. To investigate this idea, we first extend BabyAI to automatically generate language feedback from the environment dynamics and goal condition success. Then, we modify the Decision Transformer architecture to take advantage of this additional signal. We find that training with language feedback either in p","authors_text":"Alessandro Suglia, Max Taylor-Davies, Sabrina McCallum, Stefano V. Albrecht","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-07T22:33:34Z","title":"Is Feedback All You Need? Leveraging Natural Language Feedback in Goal-Conditioned Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04736","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:ce154732a87ffd7af59e6e5edc9283263239212196b89dcad1f760bae9033ca7","target":"record","created_at":"2026-07-05T07:21:50Z","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":"eae3e4e83b825fdecd4d5c39a77946471a602a9ce4ec3cc37b27e30564fafd94","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-07T22:33:34Z","title_canon_sha256":"5fc33eed8d9a56e8088cce0c7f35cc276f5bc2dedf6adf751726d5eacad5ddce"},"schema_version":"1.0","source":{"id":"2312.04736","kind":"arxiv","version":1}},"canonical_sha256":"da2a6b534da64d3aaa162e18bd39d08c2733402f4efffa796a45f0586347e9f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da2a6b534da64d3aaa162e18bd39d08c2733402f4efffa796a45f0586347e9f8","first_computed_at":"2026-07-05T07:21:50.563459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:21:50.563459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XfdOjp/FKurGLkbwOS1zkKtazag000tt8MgOPTm8EBMGuPAQVhHoTuCY97OdIeypNDYIblLiYH5W5SBSo8R8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:21:50.563880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.04736","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce154732a87ffd7af59e6e5edc9283263239212196b89dcad1f760bae9033ca7","sha256:90cb9ef873baa9d30fab623dbd1a584e3d348809dbbea70c4d16748a77b21390"],"state_sha256":"20a62eb1225263c955505331079ad70ccbead5f5a921280e59f4479fd0104d82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/3txuiXfSsOezOSABtOqzLjoJrwZPwWbcBblNRvJjICTXf1IL64ARuQSr7IPUVcwl0g3fprqYp///OnRCopIAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:24:19.937130Z","bundle_sha256":"77342c06c546e879e27b712ae32269e8cbb67f40dd72d56c3732e9880480b44e"}}