{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VUITO54QI7V6YCGWD2EEKY353N","short_pith_number":"pith:VUITO54Q","canonical_record":{"source":{"id":"2112.08593","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T03:34:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"48baabc2abfda1a2853f3e70217a82acdbca9271a99a3b3297bf92a4320a78e9","abstract_canon_sha256":"a479bddfa51996c3429e89b2821b18cef0f22d66addb10bcf02f0aa0700e5caf"},"schema_version":"1.0"},"canonical_sha256":"ad1137779047ebec08d61e8845637ddb4760d40aff7eedf122b5f7370aa9af80","source":{"kind":"arxiv","id":"2112.08593","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08593","created_at":"2026-07-05T03:41:30Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08593v1","created_at":"2026-07-05T03:41:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08593","created_at":"2026-07-05T03:41:30Z"},{"alias_kind":"pith_short_12","alias_value":"VUITO54QI7V6","created_at":"2026-07-05T03:41:30Z"},{"alias_kind":"pith_short_16","alias_value":"VUITO54QI7V6YCGW","created_at":"2026-07-05T03:41:30Z"},{"alias_kind":"pith_short_8","alias_value":"VUITO54Q","created_at":"2026-07-05T03:41:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VUITO54QI7V6YCGWD2EEKY353N","target":"record","payload":{"canonical_record":{"source":{"id":"2112.08593","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T03:34:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"48baabc2abfda1a2853f3e70217a82acdbca9271a99a3b3297bf92a4320a78e9","abstract_canon_sha256":"a479bddfa51996c3429e89b2821b18cef0f22d66addb10bcf02f0aa0700e5caf"},"schema_version":"1.0"},"canonical_sha256":"ad1137779047ebec08d61e8845637ddb4760d40aff7eedf122b5f7370aa9af80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:30.867358Z","signature_b64":"AjYuX3IH4+SCVwxbNptdxSl1qPO0w1q6x3u0AcX5eW9wtsmczzzayx0I/rSTYcktYjbaW6P0GND1bk+beJz3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad1137779047ebec08d61e8845637ddb4760d40aff7eedf122b5f7370aa9af80","last_reissued_at":"2026-07-05T03:41:30.866889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:30.866889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.08593","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":"2026-07-05T03:41:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bml07lca2LcY6piAY4SlcsjfCcDdrwn2SNiYTeU+CZTNmGwKIiBt8HyTyOCb/hNhr1D5+EWbr/7bQZWi6aZ2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:36:11.878263Z"},"content_sha256":"f9b0f3c8600ba3ed530510ec4d14e1530a702ed50006c8f4dbdca4af331c2fbd","schema_version":"1.0","event_id":"sha256:f9b0f3c8600ba3ed530510ec4d14e1530a702ed50006c8f4dbdca4af331c2fbd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VUITO54QI7V6YCGWD2EEKY353N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amal Alabdulkarim, Lara J. Martin, Mark O. Riedl, Winston Li","submitted_at":"2021-12-16T03:34:14Z","abstract_excerpt":"The advent of large pre-trained generative language models has provided a common framework for AI story generation via sampling the model to create sequences that continue the story. However, sampling alone is insufficient for story generation. In particular, it is hard to direct a language model to create stories to reach a specific goal event. We present two automated techniques grounded in deep reinforcement learning and reward shaping to control the plot of computer-generated stories. The first utilizes proximal policy optimization to fine-tune an existing transformer-based language model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08593","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/2112.08593/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":"2026-07-05T03:41:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W/JUCP95sIyF5unDOWk3iVGTW2V1E6HKmROugIvuc2q6zHnOCqPo0EvqTHqubsFXlyVS0/IOkdLF4kaZdy4SCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:36:11.879230Z"},"content_sha256":"ca1a05377a5e33eec31a3c541c0f2cc1cf80c26cd85f8d5ca8c4590b61097909","schema_version":"1.0","event_id":"sha256:ca1a05377a5e33eec31a3c541c0f2cc1cf80c26cd85f8d5ca8c4590b61097909"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VUITO54QI7V6YCGWD2EEKY353N/bundle.json","state_url":"https://pith.science/pith/VUITO54QI7V6YCGWD2EEKY353N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VUITO54QI7V6YCGWD2EEKY353N/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":"2026-08-06T00:36:11Z","links":{"resolver":"https://pith.science/pith/VUITO54QI7V6YCGWD2EEKY353N","bundle":"https://pith.science/pith/VUITO54QI7V6YCGWD2EEKY353N/bundle.json","state":"https://pith.science/pith/VUITO54QI7V6YCGWD2EEKY353N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VUITO54QI7V6YCGWD2EEKY353N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VUITO54QI7V6YCGWD2EEKY353N","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":"a479bddfa51996c3429e89b2821b18cef0f22d66addb10bcf02f0aa0700e5caf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T03:34:14Z","title_canon_sha256":"48baabc2abfda1a2853f3e70217a82acdbca9271a99a3b3297bf92a4320a78e9"},"schema_version":"1.0","source":{"id":"2112.08593","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08593","created_at":"2026-07-05T03:41:30Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08593v1","created_at":"2026-07-05T03:41:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08593","created_at":"2026-07-05T03:41:30Z"},{"alias_kind":"pith_short_12","alias_value":"VUITO54QI7V6","created_at":"2026-07-05T03:41:30Z"},{"alias_kind":"pith_short_16","alias_value":"VUITO54QI7V6YCGW","created_at":"2026-07-05T03:41:30Z"},{"alias_kind":"pith_short_8","alias_value":"VUITO54Q","created_at":"2026-07-05T03:41:30Z"}],"graph_snapshots":[{"event_id":"sha256:ca1a05377a5e33eec31a3c541c0f2cc1cf80c26cd85f8d5ca8c4590b61097909","target":"graph","created_at":"2026-07-05T03:41:30Z","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/2112.08593/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of large pre-trained generative language models has provided a common framework for AI story generation via sampling the model to create sequences that continue the story. However, sampling alone is insufficient for story generation. In particular, it is hard to direct a language model to create stories to reach a specific goal event. We present two automated techniques grounded in deep reinforcement learning and reward shaping to control the plot of computer-generated stories. The first utilizes proximal policy optimization to fine-tune an existing transformer-based language model ","authors_text":"Amal Alabdulkarim, Lara J. Martin, Mark O. Riedl, Winston Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T03:34:14Z","title":"Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08593","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:f9b0f3c8600ba3ed530510ec4d14e1530a702ed50006c8f4dbdca4af331c2fbd","target":"record","created_at":"2026-07-05T03:41:30Z","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":"a479bddfa51996c3429e89b2821b18cef0f22d66addb10bcf02f0aa0700e5caf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T03:34:14Z","title_canon_sha256":"48baabc2abfda1a2853f3e70217a82acdbca9271a99a3b3297bf92a4320a78e9"},"schema_version":"1.0","source":{"id":"2112.08593","kind":"arxiv","version":1}},"canonical_sha256":"ad1137779047ebec08d61e8845637ddb4760d40aff7eedf122b5f7370aa9af80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad1137779047ebec08d61e8845637ddb4760d40aff7eedf122b5f7370aa9af80","first_computed_at":"2026-07-05T03:41:30.866889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:41:30.866889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AjYuX3IH4+SCVwxbNptdxSl1qPO0w1q6x3u0AcX5eW9wtsmczzzayx0I/rSTYcktYjbaW6P0GND1bk+beJz3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:41:30.867358Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08593","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9b0f3c8600ba3ed530510ec4d14e1530a702ed50006c8f4dbdca4af331c2fbd","sha256:ca1a05377a5e33eec31a3c541c0f2cc1cf80c26cd85f8d5ca8c4590b61097909"],"state_sha256":"9580b16d7d2235c070d3593984971aa8ffe5dc20cae4a82d30e7a088281f1cd2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t9z8apLjprK2JY1kAo/IqdfZ7ehD0wkRrgu2mgdz5bJUOQIx7RfTTlYVAFsBoMxuELC2uFRvqgumghkK2RYaAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:36:11.883887Z","bundle_sha256":"138f60bb94dca7c79343c691e1819ecb6a0f650350cf81d381f18f20ba0d736f"}}