{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4PXFFPPL633D3R64DDWGG5J5MK","short_pith_number":"pith:4PXFFPPL","canonical_record":{"source":{"id":"2303.06710","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-12T17:22:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"28463f3ea58bd1255c1c7b203ba67944031368b6a8142c8e69e6f50637e85d71","abstract_canon_sha256":"b9038cea2f58197997ba95788233460f4613f14f42e4b256083f05636e6d77b3"},"schema_version":"1.0"},"canonical_sha256":"e3ee52bdebf6f63dc7dc18ec63753d629ccb32ef03829baa99523bcdc8ca19cf","source":{"kind":"arxiv","id":"2303.06710","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.06710","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"arxiv_version","alias_value":"2303.06710v2","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06710","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"pith_short_12","alias_value":"4PXFFPPL633D","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"pith_short_16","alias_value":"4PXFFPPL633D3R64","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"pith_short_8","alias_value":"4PXFFPPL","created_at":"2026-07-05T05:51:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4PXFFPPL633D3R64DDWGG5J5MK","target":"record","payload":{"canonical_record":{"source":{"id":"2303.06710","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-12T17:22:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"28463f3ea58bd1255c1c7b203ba67944031368b6a8142c8e69e6f50637e85d71","abstract_canon_sha256":"b9038cea2f58197997ba95788233460f4613f14f42e4b256083f05636e6d77b3"},"schema_version":"1.0"},"canonical_sha256":"e3ee52bdebf6f63dc7dc18ec63753d629ccb32ef03829baa99523bcdc8ca19cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:04.771447Z","signature_b64":"h/pCfzBT4UQiO5ZzI+pk9VgCjfb+fuh+xSHOSBItgxFrUERKG1y7s6ezDe3h43E1JaAUbQrRijfRE3plBT1iBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3ee52bdebf6f63dc7dc18ec63753d629ccb32ef03829baa99523bcdc8ca19cf","last_reissued_at":"2026-07-05T05:51:04.771059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:04.771059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.06710","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:51:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b8OLZWqbJhsiD+FfO8NTshMxzWRWmOxfSX25nuKSBhbWt68SFI9O5VZI49eOWi5clGj6DED/3ahEDO/1j8bsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T05:43:56.633681Z"},"content_sha256":"aebd25142b2fbed5d92c7b14def7825099c68d7b9b417f2314200fa65600e63c","schema_version":"1.0","event_id":"sha256:aebd25142b2fbed5d92c7b14def7825099c68d7b9b417f2314200fa65600e63c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4PXFFPPL633D3R64DDWGG5J5MK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decision Making for Human-in-the-loop Robotic Agents via Uncertainty-Aware Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alvin Pan, Gunnar A. Sigurdsson, Matei Ciocarlie, Robinson Piramuthu, Sandip Patel, Shuran Song, Siddharth Singi, Zhanpeng He","submitted_at":"2023-03-12T17:22:54Z","abstract_excerpt":"In a Human-in-the-Loop paradigm, a robotic agent is able to act mostly autonomously in solving a task, but can request help from an external expert when needed. However, knowing when to request such assistance is critical: too few requests can lead to the robot making mistakes, but too many requests can overload the expert. In this paper, we present a Reinforcement Learning based approach to this problem, where a semi-autonomous agent asks for external assistance when it has low confidence in the eventual success of the task. The confidence level is computed by estimating the variance of the r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06710","kind":"arxiv","version":2},"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/2303.06710/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":"2026-07-05T05:51:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"msai+YysjJC6EW0Vv8Jb15VYQAtw4Pnz1EtnB80fDI7mm60L6vrBrLRTbikIuEQ9oqvILxjn3yjBZX+L7qaUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T05:43:56.634060Z"},"content_sha256":"2bd7c672d114b660440e1e590e7f68b5aaad9e938f08f29869c21116c94058ed","schema_version":"1.0","event_id":"sha256:2bd7c672d114b660440e1e590e7f68b5aaad9e938f08f29869c21116c94058ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4PXFFPPL633D3R64DDWGG5J5MK/bundle.json","state_url":"https://pith.science/pith/4PXFFPPL633D3R64DDWGG5J5MK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4PXFFPPL633D3R64DDWGG5J5MK/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":"2026-07-24T05:43:56Z","links":{"resolver":"https://pith.science/pith/4PXFFPPL633D3R64DDWGG5J5MK","bundle":"https://pith.science/pith/4PXFFPPL633D3R64DDWGG5J5MK/bundle.json","state":"https://pith.science/pith/4PXFFPPL633D3R64DDWGG5J5MK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4PXFFPPL633D3R64DDWGG5J5MK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4PXFFPPL633D3R64DDWGG5J5MK","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":"b9038cea2f58197997ba95788233460f4613f14f42e4b256083f05636e6d77b3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-12T17:22:54Z","title_canon_sha256":"28463f3ea58bd1255c1c7b203ba67944031368b6a8142c8e69e6f50637e85d71"},"schema_version":"1.0","source":{"id":"2303.06710","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.06710","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"arxiv_version","alias_value":"2303.06710v2","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06710","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"pith_short_12","alias_value":"4PXFFPPL633D","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"pith_short_16","alias_value":"4PXFFPPL633D3R64","created_at":"2026-07-05T05:51:04Z"},{"alias_kind":"pith_short_8","alias_value":"4PXFFPPL","created_at":"2026-07-05T05:51:04Z"}],"graph_snapshots":[{"event_id":"sha256:2bd7c672d114b660440e1e590e7f68b5aaad9e938f08f29869c21116c94058ed","target":"graph","created_at":"2026-07-05T05:51:04Z","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/2303.06710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In a Human-in-the-Loop paradigm, a robotic agent is able to act mostly autonomously in solving a task, but can request help from an external expert when needed. However, knowing when to request such assistance is critical: too few requests can lead to the robot making mistakes, but too many requests can overload the expert. In this paper, we present a Reinforcement Learning based approach to this problem, where a semi-autonomous agent asks for external assistance when it has low confidence in the eventual success of the task. The confidence level is computed by estimating the variance of the r","authors_text":"Alvin Pan, Gunnar A. Sigurdsson, Matei Ciocarlie, Robinson Piramuthu, Sandip Patel, Shuran Song, Siddharth Singi, Zhanpeng He","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-12T17:22:54Z","title":"Decision Making for Human-in-the-loop Robotic Agents via Uncertainty-Aware Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06710","kind":"arxiv","version":2},"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:aebd25142b2fbed5d92c7b14def7825099c68d7b9b417f2314200fa65600e63c","target":"record","created_at":"2026-07-05T05:51:04Z","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":"b9038cea2f58197997ba95788233460f4613f14f42e4b256083f05636e6d77b3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-12T17:22:54Z","title_canon_sha256":"28463f3ea58bd1255c1c7b203ba67944031368b6a8142c8e69e6f50637e85d71"},"schema_version":"1.0","source":{"id":"2303.06710","kind":"arxiv","version":2}},"canonical_sha256":"e3ee52bdebf6f63dc7dc18ec63753d629ccb32ef03829baa99523bcdc8ca19cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3ee52bdebf6f63dc7dc18ec63753d629ccb32ef03829baa99523bcdc8ca19cf","first_computed_at":"2026-07-05T05:51:04.771059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:51:04.771059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h/pCfzBT4UQiO5ZzI+pk9VgCjfb+fuh+xSHOSBItgxFrUERKG1y7s6ezDe3h43E1JaAUbQrRijfRE3plBT1iBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:51:04.771447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.06710","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aebd25142b2fbed5d92c7b14def7825099c68d7b9b417f2314200fa65600e63c","sha256:2bd7c672d114b660440e1e590e7f68b5aaad9e938f08f29869c21116c94058ed"],"state_sha256":"84f01bc6667dd912efe35859e72d95b0750b3f68066e24a1697c358f2c353251"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XfUSMgKh0qWSXOpQUe4T5slPfKbTJnwh1dTAAu2f2/8WOuZ93sEchonP9omb37d4TzJzXshYYRDp/LdEdfL/DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T05:43:56.636650Z","bundle_sha256":"b4efc22e6f2afaa13da47e2f033db518e82fde53e892ab9938526c671680e4ab"}}