{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Y266ADNHDF3HL2Z7NWFRWACMBL","short_pith_number":"pith:Y266ADNH","canonical_record":{"source":{"id":"2301.10107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-01-24T16:19:09Z","cross_cats_sorted":["cs.GT","cs.HC"],"title_canon_sha256":"ce4ffa9236820c41b4f6af9df83b48a3113c8626e86efa70c8876fe9bb4a3cf3","abstract_canon_sha256":"94faac8f7c6487c49354cb648ae242e495695a054385e036440c1b64a2ae446a"},"schema_version":"1.0"},"canonical_sha256":"c6bde00da7197675eb3f6d8b1b004c0ade15757d21e30532894447c1fafaf5f6","source":{"kind":"arxiv","id":"2301.10107","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.10107","created_at":"2026-07-05T05:35:38Z"},{"alias_kind":"arxiv_version","alias_value":"2301.10107v1","created_at":"2026-07-05T05:35:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10107","created_at":"2026-07-05T05:35:38Z"},{"alias_kind":"pith_short_12","alias_value":"Y266ADNHDF3H","created_at":"2026-07-05T05:35:38Z"},{"alias_kind":"pith_short_16","alias_value":"Y266ADNHDF3HL2Z7","created_at":"2026-07-05T05:35:38Z"},{"alias_kind":"pith_short_8","alias_value":"Y266ADNH","created_at":"2026-07-05T05:35:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Y266ADNHDF3HL2Z7NWFRWACMBL","target":"record","payload":{"canonical_record":{"source":{"id":"2301.10107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-01-24T16:19:09Z","cross_cats_sorted":["cs.GT","cs.HC"],"title_canon_sha256":"ce4ffa9236820c41b4f6af9df83b48a3113c8626e86efa70c8876fe9bb4a3cf3","abstract_canon_sha256":"94faac8f7c6487c49354cb648ae242e495695a054385e036440c1b64a2ae446a"},"schema_version":"1.0"},"canonical_sha256":"c6bde00da7197675eb3f6d8b1b004c0ade15757d21e30532894447c1fafaf5f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:35:38.041589Z","signature_b64":"dNtU2Lly4PKlvK+mIqsv2giJ+oqxhZS2y6bVDpO/ItpMLsca/gkJg18BFG7AFX3M4MOFw5AVmexFUUc9twQMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6bde00da7197675eb3f6d8b1b004c0ade15757d21e30532894447c1fafaf5f6","last_reissued_at":"2026-07-05T05:35:38.041142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:35:38.041142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.10107","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":"2026-07-05T05:35:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zR+xdp0euZGowOOCU3qx0SaUSpBGESjU9mexE2FJrsbTGcSzqXE2jyErzMI1Es9UZ4Uf/eyaSwV4+CpwU00eCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:43:29.760719Z"},"content_sha256":"e2e3c47c376d0dd6d549d4aab6800f0d54840a41dd47dc377767b02470548755","schema_version":"1.0","event_id":"sha256:e2e3c47c376d0dd6d549d4aab6800f0d54840a41dd47dc377767b02470548755"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Y266ADNHDF3HL2Z7NWFRWACMBL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Story Shaping: Teaching Agents Human-like Behavior with Stories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.HC"],"primary_cat":"cs.AI","authors_text":"Christopher Cui, Mark Riedl, Renee Jia, Wei Zhou, Xiangyu Peng","submitted_at":"2023-01-24T16:19:09Z","abstract_excerpt":"Reward design for reinforcement learning agents can be difficult in situations where one not only wants the agent to achieve some effect in the world but where one also cares about how that effect is achieved. For example, we might wish for an agent to adhere to a tacit understanding of commonsense, align itself to a preference for how to behave for purposes of safety, or taking on a particular role in an interactive game. Storytelling is a mode for communicating tacit procedural knowledge. We introduce a technique, Story Shaping, in which a reinforcement learning agent infers tacit knowledge "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10107","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/2301.10107/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":"2026-07-05T05:35:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E8DiQ0GokPg+p2o0pi28oBOtt6eq6s5Rpuk0ghaUYi0Yv9J3RuQ6pi/42O3IKZEsqnrVRIC7iYQqg+OqMu/wBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:43:29.761349Z"},"content_sha256":"b92edd1ee10a5cf63a194eeaa9c2589585d3c7b71e1c85efdde7673bc6c5bea7","schema_version":"1.0","event_id":"sha256:b92edd1ee10a5cf63a194eeaa9c2589585d3c7b71e1c85efdde7673bc6c5bea7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y266ADNHDF3HL2Z7NWFRWACMBL/bundle.json","state_url":"https://pith.science/pith/Y266ADNHDF3HL2Z7NWFRWACMBL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y266ADNHDF3HL2Z7NWFRWACMBL/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":"2026-07-09T05:43:29Z","links":{"resolver":"https://pith.science/pith/Y266ADNHDF3HL2Z7NWFRWACMBL","bundle":"https://pith.science/pith/Y266ADNHDF3HL2Z7NWFRWACMBL/bundle.json","state":"https://pith.science/pith/Y266ADNHDF3HL2Z7NWFRWACMBL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y266ADNHDF3HL2Z7NWFRWACMBL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Y266ADNHDF3HL2Z7NWFRWACMBL","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":"94faac8f7c6487c49354cb648ae242e495695a054385e036440c1b64a2ae446a","cross_cats_sorted":["cs.GT","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-01-24T16:19:09Z","title_canon_sha256":"ce4ffa9236820c41b4f6af9df83b48a3113c8626e86efa70c8876fe9bb4a3cf3"},"schema_version":"1.0","source":{"id":"2301.10107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.10107","created_at":"2026-07-05T05:35:38Z"},{"alias_kind":"arxiv_version","alias_value":"2301.10107v1","created_at":"2026-07-05T05:35:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10107","created_at":"2026-07-05T05:35:38Z"},{"alias_kind":"pith_short_12","alias_value":"Y266ADNHDF3H","created_at":"2026-07-05T05:35:38Z"},{"alias_kind":"pith_short_16","alias_value":"Y266ADNHDF3HL2Z7","created_at":"2026-07-05T05:35:38Z"},{"alias_kind":"pith_short_8","alias_value":"Y266ADNH","created_at":"2026-07-05T05:35:38Z"}],"graph_snapshots":[{"event_id":"sha256:b92edd1ee10a5cf63a194eeaa9c2589585d3c7b71e1c85efdde7673bc6c5bea7","target":"graph","created_at":"2026-07-05T05:35:38Z","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/2301.10107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward design for reinforcement learning agents can be difficult in situations where one not only wants the agent to achieve some effect in the world but where one also cares about how that effect is achieved. For example, we might wish for an agent to adhere to a tacit understanding of commonsense, align itself to a preference for how to behave for purposes of safety, or taking on a particular role in an interactive game. Storytelling is a mode for communicating tacit procedural knowledge. We introduce a technique, Story Shaping, in which a reinforcement learning agent infers tacit knowledge ","authors_text":"Christopher Cui, Mark Riedl, Renee Jia, Wei Zhou, Xiangyu Peng","cross_cats":["cs.GT","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-01-24T16:19:09Z","title":"Story Shaping: Teaching Agents Human-like Behavior with Stories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10107","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:e2e3c47c376d0dd6d549d4aab6800f0d54840a41dd47dc377767b02470548755","target":"record","created_at":"2026-07-05T05:35:38Z","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":"94faac8f7c6487c49354cb648ae242e495695a054385e036440c1b64a2ae446a","cross_cats_sorted":["cs.GT","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-01-24T16:19:09Z","title_canon_sha256":"ce4ffa9236820c41b4f6af9df83b48a3113c8626e86efa70c8876fe9bb4a3cf3"},"schema_version":"1.0","source":{"id":"2301.10107","kind":"arxiv","version":1}},"canonical_sha256":"c6bde00da7197675eb3f6d8b1b004c0ade15757d21e30532894447c1fafaf5f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6bde00da7197675eb3f6d8b1b004c0ade15757d21e30532894447c1fafaf5f6","first_computed_at":"2026-07-05T05:35:38.041142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:35:38.041142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dNtU2Lly4PKlvK+mIqsv2giJ+oqxhZS2y6bVDpO/ItpMLsca/gkJg18BFG7AFX3M4MOFw5AVmexFUUc9twQMBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:35:38.041589Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.10107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2e3c47c376d0dd6d549d4aab6800f0d54840a41dd47dc377767b02470548755","sha256:b92edd1ee10a5cf63a194eeaa9c2589585d3c7b71e1c85efdde7673bc6c5bea7"],"state_sha256":"3fd00a83f52e075c3d75730d8842437f7e340fbcf843afad510969d424f59828"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DaAEqOCTGQdZuKR341+RNOc62FXmXA1z5avEAF1myb5mWN8TzuHToiKyY85QR78mDe9i6bn/ocATizLMCOcaAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:43:29.764623Z","bundle_sha256":"4adea4b037fd683ff4dbfc60b3a3090b3536e310faa9e5ae70025f011549f23a"}}