{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VZO3XHF3ZM4BJGIIQVGWCOYOZY","short_pith_number":"pith:VZO3XHF3","canonical_record":{"source":{"id":"2111.09884","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-18T18:59:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b06a7e63f4748d06cbea8a38879e2d3ddd4ff611e990bb6c4bb3c1b9d7214091","abstract_canon_sha256":"2b660901e6b918df8edac55b30d80a16d32091f6c70984177f125cb53a4e47f5"},"schema_version":"1.0"},"canonical_sha256":"ae5dbb9cbbcb38149908854d613b0ece1fe547b78cb6e8130bc6383deb60e676","source":{"kind":"arxiv","id":"2111.09884","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09884","created_at":"2026-07-05T03:33:16Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09884v1","created_at":"2026-07-05T03:33:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09884","created_at":"2026-07-05T03:33:16Z"},{"alias_kind":"pith_short_12","alias_value":"VZO3XHF3ZM4B","created_at":"2026-07-05T03:33:16Z"},{"alias_kind":"pith_short_16","alias_value":"VZO3XHF3ZM4BJGII","created_at":"2026-07-05T03:33:16Z"},{"alias_kind":"pith_short_8","alias_value":"VZO3XHF3","created_at":"2026-07-05T03:33:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VZO3XHF3ZM4BJGIIQVGWCOYOZY","target":"record","payload":{"canonical_record":{"source":{"id":"2111.09884","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-18T18:59:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b06a7e63f4748d06cbea8a38879e2d3ddd4ff611e990bb6c4bb3c1b9d7214091","abstract_canon_sha256":"2b660901e6b918df8edac55b30d80a16d32091f6c70984177f125cb53a4e47f5"},"schema_version":"1.0"},"canonical_sha256":"ae5dbb9cbbcb38149908854d613b0ece1fe547b78cb6e8130bc6383deb60e676","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:16.791268Z","signature_b64":"38sgmO8GdmwDaBsQ964eC5xjSGXdKMht8VIaC4CTrrh7/WPtSnErUTehLf/lNw7OOAZ9Pqaj9Ny496LW8L4UBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae5dbb9cbbcb38149908854d613b0ece1fe547b78cb6e8130bc6383deb60e676","last_reissued_at":"2026-07-05T03:33:16.790778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:16.790778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.09884","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":"2026-07-05T03:33:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g6q+LGCGXL5xQ8HM6f5S8E54mU92suC1iYhHpm3nanz0/zK72FikZciTz1K/Jga11LoHmsfCYckdThVXklrJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:07:18.254497Z"},"content_sha256":"4b79fc2e66bbcecc1a3346a5e1720b7c02411872d4d99a455299b5701b88897c","schema_version":"1.0","event_id":"sha256:4b79fc2e66bbcecc1a3346a5e1720b7c02411872d4d99a455299b5701b88897c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VZO3XHF3ZM4BJGIIQVGWCOYOZY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Assisted Robust Reward Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Anca D. Dragan, Jerry Zhi-Yang He","submitted_at":"2021-11-18T18:59:33Z","abstract_excerpt":"Real-world robotic tasks require complex reward functions. When we define the problem the robot needs to solve, we pretend that a designer specifies this complex reward exactly, and it is set in stone from then on. In practice, however, reward design is an iterative process: the designer chooses a reward, eventually encounters an \"edge-case\" environment where the reward incentivizes the wrong behavior, revises the reward, and repeats. What would it mean to rethink robotics problems to formally account for this iterative nature of reward design? We propose that the robot not take the specified "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09884","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/2111.09884/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":"2026-07-05T03:33:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HGpd4s7fThTf0m/SzSqvct14/xj1GV+9Bw3DyzdpXLhlOcy0KUGXn/S7ouFWlwKKvqwSTdg8bufOsOCbvwAbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:07:18.254994Z"},"content_sha256":"f34dd35918f1fcf92fab989160277909076410bb9fd937215ef05cfa14cab17e","schema_version":"1.0","event_id":"sha256:f34dd35918f1fcf92fab989160277909076410bb9fd937215ef05cfa14cab17e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VZO3XHF3ZM4BJGIIQVGWCOYOZY/bundle.json","state_url":"https://pith.science/pith/VZO3XHF3ZM4BJGIIQVGWCOYOZY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VZO3XHF3ZM4BJGIIQVGWCOYOZY/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":"2026-08-22T07:07:18Z","links":{"resolver":"https://pith.science/pith/VZO3XHF3ZM4BJGIIQVGWCOYOZY","bundle":"https://pith.science/pith/VZO3XHF3ZM4BJGIIQVGWCOYOZY/bundle.json","state":"https://pith.science/pith/VZO3XHF3ZM4BJGIIQVGWCOYOZY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VZO3XHF3ZM4BJGIIQVGWCOYOZY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VZO3XHF3ZM4BJGIIQVGWCOYOZY","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":"2b660901e6b918df8edac55b30d80a16d32091f6c70984177f125cb53a4e47f5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-18T18:59:33Z","title_canon_sha256":"b06a7e63f4748d06cbea8a38879e2d3ddd4ff611e990bb6c4bb3c1b9d7214091"},"schema_version":"1.0","source":{"id":"2111.09884","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09884","created_at":"2026-07-05T03:33:16Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09884v1","created_at":"2026-07-05T03:33:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09884","created_at":"2026-07-05T03:33:16Z"},{"alias_kind":"pith_short_12","alias_value":"VZO3XHF3ZM4B","created_at":"2026-07-05T03:33:16Z"},{"alias_kind":"pith_short_16","alias_value":"VZO3XHF3ZM4BJGII","created_at":"2026-07-05T03:33:16Z"},{"alias_kind":"pith_short_8","alias_value":"VZO3XHF3","created_at":"2026-07-05T03:33:16Z"}],"graph_snapshots":[{"event_id":"sha256:f34dd35918f1fcf92fab989160277909076410bb9fd937215ef05cfa14cab17e","target":"graph","created_at":"2026-07-05T03:33:16Z","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/2111.09884/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world robotic tasks require complex reward functions. When we define the problem the robot needs to solve, we pretend that a designer specifies this complex reward exactly, and it is set in stone from then on. In practice, however, reward design is an iterative process: the designer chooses a reward, eventually encounters an \"edge-case\" environment where the reward incentivizes the wrong behavior, revises the reward, and repeats. What would it mean to rethink robotics problems to formally account for this iterative nature of reward design? We propose that the robot not take the specified ","authors_text":"Anca D. Dragan, Jerry Zhi-Yang He","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-18T18:59:33Z","title":"Assisted Robust Reward Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09884","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":"sha256:4b79fc2e66bbcecc1a3346a5e1720b7c02411872d4d99a455299b5701b88897c","target":"record","created_at":"2026-07-05T03:33:16Z","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":"2b660901e6b918df8edac55b30d80a16d32091f6c70984177f125cb53a4e47f5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-18T18:59:33Z","title_canon_sha256":"b06a7e63f4748d06cbea8a38879e2d3ddd4ff611e990bb6c4bb3c1b9d7214091"},"schema_version":"1.0","source":{"id":"2111.09884","kind":"arxiv","version":1}},"canonical_sha256":"ae5dbb9cbbcb38149908854d613b0ece1fe547b78cb6e8130bc6383deb60e676","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae5dbb9cbbcb38149908854d613b0ece1fe547b78cb6e8130bc6383deb60e676","first_computed_at":"2026-07-05T03:33:16.790778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:33:16.790778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"38sgmO8GdmwDaBsQ964eC5xjSGXdKMht8VIaC4CTrrh7/WPtSnErUTehLf/lNw7OOAZ9Pqaj9Ny496LW8L4UBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:33:16.791268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.09884","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b79fc2e66bbcecc1a3346a5e1720b7c02411872d4d99a455299b5701b88897c","sha256:f34dd35918f1fcf92fab989160277909076410bb9fd937215ef05cfa14cab17e"],"state_sha256":"4d352233d85909059b60f5186801cd87b02e183453eca88d7c948278ad3dec36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JdVlH86pWcZaH3JXA2KfTwieM/959E9ofuWVVcIGC+8XtyxDf+17cz9sW8np5wdtVleJUpWgf4p7nkyWHwZKCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T07:07:18.259108Z","bundle_sha256":"cc9cf83513ad268169d206317e6a1b5f80ada67596a413f1e51947805db8bd6e"}}