{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WAZOF3EGUEM56GZTTTVJ5OFYPO","short_pith_number":"pith:WAZOF3EG","canonical_record":{"source":{"id":"2503.04280","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-06T10:08:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6c059e350e8c965c958be58ca3ed086fce96dfe9a0e8f25a971a5cfe6597162c","abstract_canon_sha256":"bc600b880cf2cb76cd3ac3ac2de95a1107ce75b4271b08f6a37047e4becf3c1e"},"schema_version":"1.0"},"canonical_sha256":"b032e2ec86a119df1b339cea9eb8b87b90b01c5a6c0bf6632f1ffe0b4d4f1d62","source":{"kind":"arxiv","id":"2503.04280","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04280","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04280v4","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04280","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"pith_short_12","alias_value":"WAZOF3EGUEM5","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"pith_short_16","alias_value":"WAZOF3EGUEM56GZT","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"pith_short_8","alias_value":"WAZOF3EG","created_at":"2026-07-05T11:19:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WAZOF3EGUEM56GZTTTVJ5OFYPO","target":"record","payload":{"canonical_record":{"source":{"id":"2503.04280","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-06T10:08:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6c059e350e8c965c958be58ca3ed086fce96dfe9a0e8f25a971a5cfe6597162c","abstract_canon_sha256":"bc600b880cf2cb76cd3ac3ac2de95a1107ce75b4271b08f6a37047e4becf3c1e"},"schema_version":"1.0"},"canonical_sha256":"b032e2ec86a119df1b339cea9eb8b87b90b01c5a6c0bf6632f1ffe0b4d4f1d62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:04.166251Z","signature_b64":"H4ZKAcvwdsuCb0mMytp3LFA1ofclYlIM3dMjyikwgo27QVUXcVhPmbFteEEHa6ISOf+FT1ipE6XTPtke1hhMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b032e2ec86a119df1b339cea9eb8b87b90b01c5a6c0bf6632f1ffe0b4d4f1d62","last_reissued_at":"2026-07-05T11:19:04.165802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:04.165802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.04280","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:19:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nTiW1cQ0fRRHKWIrV5Blhz1jgs7Tv3V1rXhScGNhgQ+8+lQHM7IbpQJSyvXX3USDaZKWUWfMh8+vg4Xad1lcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:10:01.230883Z"},"content_sha256":"6ea3ee2ab58e3b546ef5a2d2304fe1145737db48b0aaf11084e869dcefc5a3f6","schema_version":"1.0","event_id":"sha256:6ea3ee2ab58e3b546ef5a2d2304fe1145737db48b0aaf11084e869dcefc5a3f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WAZOF3EGUEM56GZTTTVJ5OFYPO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Autonomous Reinforcement Learning for Real-World Robotic Manipulation with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alberto Dalla Libera, Aris Synodinos, Matteo Iovino, Niccol\\`o Turcato, Pietro Falco, Ruggero Carli","submitted_at":"2025-03-06T10:08:44Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) and Visual Language Models (VLMs) have significantly impacted robotics, enabling high-level semantic motion planning applications. Reinforcement Learning (RL), a complementary paradigm, enables agents to autonomously optimize complex behaviors through interaction and reward signals. However, designing effective reward functions for RL remains challenging, especially in real-world tasks where sparse rewards are insufficient and dense rewards require elaborate design. In this work, we propose Autonomous Reinforcement learning for Complex Human-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04280","kind":"arxiv","version":4},"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/2503.04280/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":"2026-07-05T11:19:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fmr7e+X+oSltw+GKgMfF60zN39MYJR3fhCxGanv6wPEisnrRLIeOMWxjRfDnTH7j2DyzfqGI725e6fl7SZzxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:10:01.231258Z"},"content_sha256":"8a02a5384a02c48ea7f3be9ba286250d36137213db65188129fc6d77450142fb","schema_version":"1.0","event_id":"sha256:8a02a5384a02c48ea7f3be9ba286250d36137213db65188129fc6d77450142fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO/bundle.json","state_url":"https://pith.science/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO/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":"2026-07-06T15:10:01Z","links":{"resolver":"https://pith.science/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO","bundle":"https://pith.science/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO/bundle.json","state":"https://pith.science/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WAZOF3EGUEM56GZTTTVJ5OFYPO","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":"bc600b880cf2cb76cd3ac3ac2de95a1107ce75b4271b08f6a37047e4becf3c1e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-06T10:08:44Z","title_canon_sha256":"6c059e350e8c965c958be58ca3ed086fce96dfe9a0e8f25a971a5cfe6597162c"},"schema_version":"1.0","source":{"id":"2503.04280","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04280","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04280v4","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04280","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"pith_short_12","alias_value":"WAZOF3EGUEM5","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"pith_short_16","alias_value":"WAZOF3EGUEM56GZT","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"pith_short_8","alias_value":"WAZOF3EG","created_at":"2026-07-05T11:19:04Z"}],"graph_snapshots":[{"event_id":"sha256:8a02a5384a02c48ea7f3be9ba286250d36137213db65188129fc6d77450142fb","target":"graph","created_at":"2026-07-05T11:19:04Z","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/2503.04280/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Language Models (LLMs) and Visual Language Models (VLMs) have significantly impacted robotics, enabling high-level semantic motion planning applications. Reinforcement Learning (RL), a complementary paradigm, enables agents to autonomously optimize complex behaviors through interaction and reward signals. However, designing effective reward functions for RL remains challenging, especially in real-world tasks where sparse rewards are insufficient and dense rewards require elaborate design. In this work, we propose Autonomous Reinforcement learning for Complex Human-","authors_text":"Alberto Dalla Libera, Aris Synodinos, Matteo Iovino, Niccol\\`o Turcato, Pietro Falco, Ruggero Carli","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-06T10:08:44Z","title":"Towards Autonomous Reinforcement Learning for Real-World Robotic Manipulation with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04280","kind":"arxiv","version":4},"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":"sha256:6ea3ee2ab58e3b546ef5a2d2304fe1145737db48b0aaf11084e869dcefc5a3f6","target":"record","created_at":"2026-07-05T11:19:04Z","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":"bc600b880cf2cb76cd3ac3ac2de95a1107ce75b4271b08f6a37047e4becf3c1e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-06T10:08:44Z","title_canon_sha256":"6c059e350e8c965c958be58ca3ed086fce96dfe9a0e8f25a971a5cfe6597162c"},"schema_version":"1.0","source":{"id":"2503.04280","kind":"arxiv","version":4}},"canonical_sha256":"b032e2ec86a119df1b339cea9eb8b87b90b01c5a6c0bf6632f1ffe0b4d4f1d62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b032e2ec86a119df1b339cea9eb8b87b90b01c5a6c0bf6632f1ffe0b4d4f1d62","first_computed_at":"2026-07-05T11:19:04.165802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:04.165802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H4ZKAcvwdsuCb0mMytp3LFA1ofclYlIM3dMjyikwgo27QVUXcVhPmbFteEEHa6ISOf+FT1ipE6XTPtke1hhMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:04.166251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04280","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ea3ee2ab58e3b546ef5a2d2304fe1145737db48b0aaf11084e869dcefc5a3f6","sha256:8a02a5384a02c48ea7f3be9ba286250d36137213db65188129fc6d77450142fb"],"state_sha256":"9820644cb35ec6034f656993e1dafc148d75ced2e0e4f5e71cba80576b8fda78"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JbD4LJcAlkwT7w8bcoYoC0XDdzIKfB2B9dt434xh7ilJ7siu8SjTan2NgC1cq/5o57Ez1pBYeWXYwfJRoX/0AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:10:01.233353Z","bundle_sha256":"58c68dcf904009dba0623b494f56692687ebddeb98dea08d5c60d4692ed38692"}}