{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZAC4YALAEW6XEX5POSEHCER4J7","short_pith_number":"pith:ZAC4YALA","canonical_record":{"source":{"id":"2411.18825","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-27T23:58:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d6173d8794c116ec96c10c4daafc434bd9959d73323de4e59471177c22b37dc2","abstract_canon_sha256":"809e27be7d77f845fefac57fe2c31fe49bdef147ff4e8442aab05ad1ca31d9f7"},"schema_version":"1.0"},"canonical_sha256":"c805cc016025bd725faf748871123c4fe548b39c1702f86d9e8d48fa946311e2","source":{"kind":"arxiv","id":"2411.18825","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18825","created_at":"2026-07-05T11:01:02Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18825v3","created_at":"2026-07-05T11:01:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18825","created_at":"2026-07-05T11:01:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZAC4YALAEW6X","created_at":"2026-07-05T11:01:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZAC4YALAEW6XEX5P","created_at":"2026-07-05T11:01:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZAC4YALA","created_at":"2026-07-05T11:01:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZAC4YALAEW6XEX5POSEHCER4J7","target":"record","payload":{"canonical_record":{"source":{"id":"2411.18825","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-27T23:58:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d6173d8794c116ec96c10c4daafc434bd9959d73323de4e59471177c22b37dc2","abstract_canon_sha256":"809e27be7d77f845fefac57fe2c31fe49bdef147ff4e8442aab05ad1ca31d9f7"},"schema_version":"1.0"},"canonical_sha256":"c805cc016025bd725faf748871123c4fe548b39c1702f86d9e8d48fa946311e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:02.596340Z","signature_b64":"UmP9wgZ3Rs+lovX8Af8SrBLER3cOKS4JBvd48DP/PpaztkJU23owWeevQrbVXjE78/OEtOQqRcPKkQBCsv8wCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c805cc016025bd725faf748871123c4fe548b39c1702f86d9e8d48fa946311e2","last_reissued_at":"2026-07-05T11:01:02.595825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:02.595825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.18825","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/+WlodEEU8po/cRsa3nadCtoquDFfcI8h8jzlc1dIaqWwJRB4WWAWUupTXmjSbxyembMdb/a97AAGNRYRAPMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:53:39.603002Z"},"content_sha256":"86c7724393ee2bbeffeb2a5c9ad4ee45aea40b003d3869fec55bb3a4cc7707ca","schema_version":"1.0","event_id":"sha256:86c7724393ee2bbeffeb2a5c9ad4ee45aea40b003d3869fec55bb3a4cc7707ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZAC4YALAEW6XEX5POSEHCER4J7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Letian Chen, Matthew Gombolay, Nina Moorman","submitted_at":"2024-11-27T23:58:32Z","abstract_excerpt":"Reinforcement learning (RL) has demonstrated compelling performance in robotic tasks, but its success often hinges on the design of complex, ad hoc reward functions. Researchers have explored how Large Language Models (LLMs) could enable non-expert users to specify reward functions more easily. However, LLMs struggle to balance the importance of different features, generalize poorly to out-of-distribution robotic tasks, and cannot represent the problem properly with only text-based descriptions. To address these challenges, we propose ELEMENTAL (intEractive LEarning froM dEmoNstraTion And Lang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18825","kind":"arxiv","version":3},"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/2411.18825/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":"2026-07-05T11:01:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ieUK5kQ37CE0SIvPyyA+QWZctg2j2kKpT1AdvoJXsU+z/k/dKrxESTjU9k1b87tP7yIaPhwTJZn6Bjv+HRK+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:53:39.603564Z"},"content_sha256":"011e6de85a3c9f0216da3c0a1d9b03bf64438b266d0ea4f980d9e1eeb46fa716","schema_version":"1.0","event_id":"sha256:011e6de85a3c9f0216da3c0a1d9b03bf64438b266d0ea4f980d9e1eeb46fa716"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZAC4YALAEW6XEX5POSEHCER4J7/bundle.json","state_url":"https://pith.science/pith/ZAC4YALAEW6XEX5POSEHCER4J7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZAC4YALAEW6XEX5POSEHCER4J7/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":"2026-08-08T17:53:39Z","links":{"resolver":"https://pith.science/pith/ZAC4YALAEW6XEX5POSEHCER4J7","bundle":"https://pith.science/pith/ZAC4YALAEW6XEX5POSEHCER4J7/bundle.json","state":"https://pith.science/pith/ZAC4YALAEW6XEX5POSEHCER4J7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZAC4YALAEW6XEX5POSEHCER4J7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZAC4YALAEW6XEX5POSEHCER4J7","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":"809e27be7d77f845fefac57fe2c31fe49bdef147ff4e8442aab05ad1ca31d9f7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-27T23:58:32Z","title_canon_sha256":"d6173d8794c116ec96c10c4daafc434bd9959d73323de4e59471177c22b37dc2"},"schema_version":"1.0","source":{"id":"2411.18825","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18825","created_at":"2026-07-05T11:01:02Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18825v3","created_at":"2026-07-05T11:01:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18825","created_at":"2026-07-05T11:01:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZAC4YALAEW6X","created_at":"2026-07-05T11:01:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZAC4YALAEW6XEX5P","created_at":"2026-07-05T11:01:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZAC4YALA","created_at":"2026-07-05T11:01:02Z"}],"graph_snapshots":[{"event_id":"sha256:011e6de85a3c9f0216da3c0a1d9b03bf64438b266d0ea4f980d9e1eeb46fa716","target":"graph","created_at":"2026-07-05T11:01:02Z","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/2411.18825/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has demonstrated compelling performance in robotic tasks, but its success often hinges on the design of complex, ad hoc reward functions. Researchers have explored how Large Language Models (LLMs) could enable non-expert users to specify reward functions more easily. However, LLMs struggle to balance the importance of different features, generalize poorly to out-of-distribution robotic tasks, and cannot represent the problem properly with only text-based descriptions. To address these challenges, we propose ELEMENTAL (intEractive LEarning froM dEmoNstraTion And Lang","authors_text":"Letian Chen, Matthew Gombolay, Nina Moorman","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-27T23:58:32Z","title":"ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18825","kind":"arxiv","version":3},"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":"sha256:86c7724393ee2bbeffeb2a5c9ad4ee45aea40b003d3869fec55bb3a4cc7707ca","target":"record","created_at":"2026-07-05T11:01:02Z","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":"809e27be7d77f845fefac57fe2c31fe49bdef147ff4e8442aab05ad1ca31d9f7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-27T23:58:32Z","title_canon_sha256":"d6173d8794c116ec96c10c4daafc434bd9959d73323de4e59471177c22b37dc2"},"schema_version":"1.0","source":{"id":"2411.18825","kind":"arxiv","version":3}},"canonical_sha256":"c805cc016025bd725faf748871123c4fe548b39c1702f86d9e8d48fa946311e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c805cc016025bd725faf748871123c4fe548b39c1702f86d9e8d48fa946311e2","first_computed_at":"2026-07-05T11:01:02.595825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:02.595825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UmP9wgZ3Rs+lovX8Af8SrBLER3cOKS4JBvd48DP/PpaztkJU23owWeevQrbVXjE78/OEtOQqRcPKkQBCsv8wCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:02.596340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18825","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86c7724393ee2bbeffeb2a5c9ad4ee45aea40b003d3869fec55bb3a4cc7707ca","sha256:011e6de85a3c9f0216da3c0a1d9b03bf64438b266d0ea4f980d9e1eeb46fa716"],"state_sha256":"2a4b30eaa62aad1d6a5ab262aee59036e5a47bbad2d622f328ee8041e4555fd3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hEb57/L/eGgFBD7+a6rH2jwYBO0T/NHZzh507qBGnyqTuSSq8YM+4oOdNbu/0zeGNgRtdlk4+9QqTlthbWEtCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:53:39.608432Z","bundle_sha256":"9ace16ce0b6de57db2339c40455a610a2f6b21c185a8f50ecf5a5c8130e21c08"}}