{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:H6Z7WWFEHBJUJHYSEHME5BZDVO","short_pith_number":"pith:H6Z7WWFE","canonical_record":{"source":{"id":"2501.17104","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T17:44:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c35215f69bfeaf81237bd49c4e0de7613c5ce87d1d1577d4e485756bd7831db6","abstract_canon_sha256":"81429f3f21b504058f910edc2b37d5a518a3898da0438c33749fa39cffa0882e"},"schema_version":"1.0"},"canonical_sha256":"3fb3fb58a43853449f1221d84e8723ab8379c0d65bd63ed67b586509272cb835","source":{"kind":"arxiv","id":"2501.17104","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17104","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17104v1","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17104","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"pith_short_12","alias_value":"H6Z7WWFEHBJU","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"pith_short_16","alias_value":"H6Z7WWFEHBJUJHYS","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"pith_short_8","alias_value":"H6Z7WWFE","created_at":"2026-07-05T10:06:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:H6Z7WWFEHBJUJHYSEHME5BZDVO","target":"record","payload":{"canonical_record":{"source":{"id":"2501.17104","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T17:44:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c35215f69bfeaf81237bd49c4e0de7613c5ce87d1d1577d4e485756bd7831db6","abstract_canon_sha256":"81429f3f21b504058f910edc2b37d5a518a3898da0438c33749fa39cffa0882e"},"schema_version":"1.0"},"canonical_sha256":"3fb3fb58a43853449f1221d84e8723ab8379c0d65bd63ed67b586509272cb835","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:34.415716Z","signature_b64":"tK4oTjMHn/LYvudA501bVzvFSvzVgEInVvnfExfFUc/6zVRg2EG4qgn5I/M7pSIcGuP7a81B3GXSVw81L6FDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fb3fb58a43853449f1221d84e8723ab8379c0d65bd63ed67b586509272cb835","last_reissued_at":"2026-07-05T10:06:34.415256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:34.415256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.17104","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":"2026-07-05T10:06:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZBHqCWs+ser4U3vToZQi9hGuZFUdgBRSvYHLvMyWYGX7DiTUzK9k+G90uo7i892nUzErZJdk1n0ghREyo8koDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:03:22.425221Z"},"content_sha256":"185b20d9ad98997968ff6d137017b3d7bba1e8ba0e4555ed7ea412e3b2a16501","schema_version":"1.0","event_id":"sha256:185b20d9ad98997968ff6d137017b3d7bba1e8ba0e4555ed7ea412e3b2a16501"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:H6Z7WWFEHBJUJHYSEHME5BZDVO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"COS(M+O)S: Curiosity and RL-Enhanced MCTS for Exploring Story Space via Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Tobias Materzok","submitted_at":"2025-01-28T17:44:04Z","abstract_excerpt":"We present COS(M+O)S, a System 2-inspired framework for open-ended plot development that systematically explores the vast space of possible story expansions, enabling a 3B-parameter language model to approach the plot quality of a 70B model on select short-story tasks. The method accomplishes this by combining Monte Carlo Tree Search (MCTS), guided by a step-level value model that rewards moderate surprisal (curiosity) while penalizing incoherence, and Odds Ratio Preference Optimization (ORPO) to fine-tune the policy on high-value plot expansions. This iterative reinforcement learning loop sys"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17104","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/2501.17104/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":"2026-07-05T10:06:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Td6Cz7nn9WrZsjOQ2ObU3xSlu6igEBRdIujxv4PEOQko9g6xZ8x+2hrycL3+Jh1KLnQtFjKMJJLxY92VOIuqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:03:22.425716Z"},"content_sha256":"4abd08ac44461739ed602db0c0d083c48433f4339fff837fad6927c3791d348d","schema_version":"1.0","event_id":"sha256:4abd08ac44461739ed602db0c0d083c48433f4339fff837fad6927c3791d348d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H6Z7WWFEHBJUJHYSEHME5BZDVO/bundle.json","state_url":"https://pith.science/pith/H6Z7WWFEHBJUJHYSEHME5BZDVO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H6Z7WWFEHBJUJHYSEHME5BZDVO/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":"2026-08-09T22:03:22Z","links":{"resolver":"https://pith.science/pith/H6Z7WWFEHBJUJHYSEHME5BZDVO","bundle":"https://pith.science/pith/H6Z7WWFEHBJUJHYSEHME5BZDVO/bundle.json","state":"https://pith.science/pith/H6Z7WWFEHBJUJHYSEHME5BZDVO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H6Z7WWFEHBJUJHYSEHME5BZDVO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H6Z7WWFEHBJUJHYSEHME5BZDVO","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":"81429f3f21b504058f910edc2b37d5a518a3898da0438c33749fa39cffa0882e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T17:44:04Z","title_canon_sha256":"c35215f69bfeaf81237bd49c4e0de7613c5ce87d1d1577d4e485756bd7831db6"},"schema_version":"1.0","source":{"id":"2501.17104","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17104","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17104v1","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17104","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"pith_short_12","alias_value":"H6Z7WWFEHBJU","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"pith_short_16","alias_value":"H6Z7WWFEHBJUJHYS","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"pith_short_8","alias_value":"H6Z7WWFE","created_at":"2026-07-05T10:06:34Z"}],"graph_snapshots":[{"event_id":"sha256:4abd08ac44461739ed602db0c0d083c48433f4339fff837fad6927c3791d348d","target":"graph","created_at":"2026-07-05T10:06:34Z","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/2501.17104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present COS(M+O)S, a System 2-inspired framework for open-ended plot development that systematically explores the vast space of possible story expansions, enabling a 3B-parameter language model to approach the plot quality of a 70B model on select short-story tasks. The method accomplishes this by combining Monte Carlo Tree Search (MCTS), guided by a step-level value model that rewards moderate surprisal (curiosity) while penalizing incoherence, and Odds Ratio Preference Optimization (ORPO) to fine-tune the policy on high-value plot expansions. This iterative reinforcement learning loop sys","authors_text":"Tobias Materzok","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T17:44:04Z","title":"COS(M+O)S: Curiosity and RL-Enhanced MCTS for Exploring Story Space via Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17104","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":"sha256:185b20d9ad98997968ff6d137017b3d7bba1e8ba0e4555ed7ea412e3b2a16501","target":"record","created_at":"2026-07-05T10:06:34Z","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":"81429f3f21b504058f910edc2b37d5a518a3898da0438c33749fa39cffa0882e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T17:44:04Z","title_canon_sha256":"c35215f69bfeaf81237bd49c4e0de7613c5ce87d1d1577d4e485756bd7831db6"},"schema_version":"1.0","source":{"id":"2501.17104","kind":"arxiv","version":1}},"canonical_sha256":"3fb3fb58a43853449f1221d84e8723ab8379c0d65bd63ed67b586509272cb835","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fb3fb58a43853449f1221d84e8723ab8379c0d65bd63ed67b586509272cb835","first_computed_at":"2026-07-05T10:06:34.415256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:34.415256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tK4oTjMHn/LYvudA501bVzvFSvzVgEInVvnfExfFUc/6zVRg2EG4qgn5I/M7pSIcGuP7a81B3GXSVw81L6FDAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:34.415716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.17104","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:185b20d9ad98997968ff6d137017b3d7bba1e8ba0e4555ed7ea412e3b2a16501","sha256:4abd08ac44461739ed602db0c0d083c48433f4339fff837fad6927c3791d348d"],"state_sha256":"6556838153d215ffb7b7a2f44cbd369d026a020cc10149ea4ef3ad4a17be90a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6e+fscpGLUzfwoFAtoysylOVJAXFjv1jhwGFmxmpqlYz/1bNmy64dyCEYJWDnyflOUjmpvDr7BeRi4niz47jCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:03:22.429379Z","bundle_sha256":"911eaaf3ef5cc8b8d245e002fcd88167cc702d6a6202b0afd50c9b0dd98bc6d0"}}