{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OOZXSYOBLAUCF3QLEMOCJCGX6V","short_pith_number":"pith:OOZXSYOB","canonical_record":{"source":{"id":"2606.19468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T18:03:34Z","cross_cats_sorted":[],"title_canon_sha256":"aab36d5cfd0f9f0672c5cca83a8f4375da8fbe7b07e73be6c128745921304a5f","abstract_canon_sha256":"2f4c776d0559111c9c5a4c52ba2792c347a988607026a5eb9c3be44e93cb747a"},"schema_version":"1.0"},"canonical_sha256":"73b37961c1582822ee0b231c2488d7f5776a427a9cba0ce363d3dd67b895dfa0","source":{"kind":"arxiv","id":"2606.19468","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19468","created_at":"2026-06-19T16:12:26Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19468v1","created_at":"2026-06-19T16:12:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19468","created_at":"2026-06-19T16:12:26Z"},{"alias_kind":"pith_short_12","alias_value":"OOZXSYOBLAUC","created_at":"2026-06-19T16:12:26Z"},{"alias_kind":"pith_short_16","alias_value":"OOZXSYOBLAUCF3QL","created_at":"2026-06-19T16:12:26Z"},{"alias_kind":"pith_short_8","alias_value":"OOZXSYOB","created_at":"2026-06-19T16:12:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OOZXSYOBLAUCF3QLEMOCJCGX6V","target":"record","payload":{"canonical_record":{"source":{"id":"2606.19468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T18:03:34Z","cross_cats_sorted":[],"title_canon_sha256":"aab36d5cfd0f9f0672c5cca83a8f4375da8fbe7b07e73be6c128745921304a5f","abstract_canon_sha256":"2f4c776d0559111c9c5a4c52ba2792c347a988607026a5eb9c3be44e93cb747a"},"schema_version":"1.0"},"canonical_sha256":"73b37961c1582822ee0b231c2488d7f5776a427a9cba0ce363d3dd67b895dfa0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:26.558529Z","signature_b64":"I0tBiqeL8bH/j1Hl+PYiPtskdjjoQS7zjE/AXB6XuzMKycA0SL6xW1168xNo+TMztPkLifZ10Std3DrDSQhJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73b37961c1582822ee0b231c2488d7f5776a427a9cba0ce363d3dd67b895dfa0","last_reissued_at":"2026-06-19T16:12:26.558122Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:26.558122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.19468","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":"2026-06-19T16:12:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oLhC0mRhqOsAxpKAicehcf8lnMa6ad2AWf44Wlmup5Z62wJm/gMhql4DnLWGJFMUSE86WZ1zynXyuxz4I3fjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T02:45:39.267367Z"},"content_sha256":"64a20c29466af0a0ac5c40970830d599470c30111234f334d6a4212f91d23bb0","schema_version":"1.0","event_id":"sha256:64a20c29466af0a0ac5c40970830d599470c30111234f334d6a4212f91d23bb0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OOZXSYOBLAUCF3QLEMOCJCGX6V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Characterizing Narrative Content in Web-scale LLM Pretraining Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Piper, Elliott Ash, Maria Antoniak, Teagan Johnson","submitted_at":"2026-06-17T18:03:34Z","abstract_excerpt":"The narrative composition of web-scale LLM pretraining corpora remains largely unexplored even though narrative is a fundamental mode of human communication. We present the first fine-grained study of narrative features in Dolma, a 3-trillion-token open pretraining corpus. Drawing on narrative theory, we design a framework spanning three core narrative elements (agency, setting, and events) operationalized as 11 interpretable dimensions. After sampling and annotating a diverse set of 400 passages, we finetune and validate NarraBERT, a RoBERTa-based model for fine-grained narrative prediction. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19468","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/2606.19468/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":"2026-06-19T16:12:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DTgwAX64Fnk5du7g8OW8JFJsMVOjvGmcIkMK7FERdGuK76lbr72eGM1IzQcEeoLdC3AnOJZf02ODm8BdSErjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T02:45:39.267749Z"},"content_sha256":"5e58e79070276f7eab89b70321b93111d45c7e6fc9261092e971c28f634ce3a2","schema_version":"1.0","event_id":"sha256:5e58e79070276f7eab89b70321b93111d45c7e6fc9261092e971c28f634ce3a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OOZXSYOBLAUCF3QLEMOCJCGX6V/bundle.json","state_url":"https://pith.science/pith/OOZXSYOBLAUCF3QLEMOCJCGX6V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OOZXSYOBLAUCF3QLEMOCJCGX6V/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":"2026-06-24T02:45:39Z","links":{"resolver":"https://pith.science/pith/OOZXSYOBLAUCF3QLEMOCJCGX6V","bundle":"https://pith.science/pith/OOZXSYOBLAUCF3QLEMOCJCGX6V/bundle.json","state":"https://pith.science/pith/OOZXSYOBLAUCF3QLEMOCJCGX6V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OOZXSYOBLAUCF3QLEMOCJCGX6V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OOZXSYOBLAUCF3QLEMOCJCGX6V","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":"2f4c776d0559111c9c5a4c52ba2792c347a988607026a5eb9c3be44e93cb747a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T18:03:34Z","title_canon_sha256":"aab36d5cfd0f9f0672c5cca83a8f4375da8fbe7b07e73be6c128745921304a5f"},"schema_version":"1.0","source":{"id":"2606.19468","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19468","created_at":"2026-06-19T16:12:26Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19468v1","created_at":"2026-06-19T16:12:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19468","created_at":"2026-06-19T16:12:26Z"},{"alias_kind":"pith_short_12","alias_value":"OOZXSYOBLAUC","created_at":"2026-06-19T16:12:26Z"},{"alias_kind":"pith_short_16","alias_value":"OOZXSYOBLAUCF3QL","created_at":"2026-06-19T16:12:26Z"},{"alias_kind":"pith_short_8","alias_value":"OOZXSYOB","created_at":"2026-06-19T16:12:26Z"}],"graph_snapshots":[{"event_id":"sha256:5e58e79070276f7eab89b70321b93111d45c7e6fc9261092e971c28f634ce3a2","target":"graph","created_at":"2026-06-19T16:12:26Z","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/2606.19468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The narrative composition of web-scale LLM pretraining corpora remains largely unexplored even though narrative is a fundamental mode of human communication. We present the first fine-grained study of narrative features in Dolma, a 3-trillion-token open pretraining corpus. Drawing on narrative theory, we design a framework spanning three core narrative elements (agency, setting, and events) operationalized as 11 interpretable dimensions. After sampling and annotating a diverse set of 400 passages, we finetune and validate NarraBERT, a RoBERTa-based model for fine-grained narrative prediction. ","authors_text":"Andrew Piper, Elliott Ash, Maria Antoniak, Teagan Johnson","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T18:03:34Z","title":"Characterizing Narrative Content in Web-scale LLM Pretraining Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19468","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":"sha256:64a20c29466af0a0ac5c40970830d599470c30111234f334d6a4212f91d23bb0","target":"record","created_at":"2026-06-19T16:12:26Z","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":"2f4c776d0559111c9c5a4c52ba2792c347a988607026a5eb9c3be44e93cb747a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T18:03:34Z","title_canon_sha256":"aab36d5cfd0f9f0672c5cca83a8f4375da8fbe7b07e73be6c128745921304a5f"},"schema_version":"1.0","source":{"id":"2606.19468","kind":"arxiv","version":1}},"canonical_sha256":"73b37961c1582822ee0b231c2488d7f5776a427a9cba0ce363d3dd67b895dfa0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73b37961c1582822ee0b231c2488d7f5776a427a9cba0ce363d3dd67b895dfa0","first_computed_at":"2026-06-19T16:12:26.558122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:26.558122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I0tBiqeL8bH/j1Hl+PYiPtskdjjoQS7zjE/AXB6XuzMKycA0SL6xW1168xNo+TMztPkLifZ10Std3DrDSQhJCA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:26.558529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19468","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64a20c29466af0a0ac5c40970830d599470c30111234f334d6a4212f91d23bb0","sha256:5e58e79070276f7eab89b70321b93111d45c7e6fc9261092e971c28f634ce3a2"],"state_sha256":"cf2ce7fd4d6e031936c098cbf4318f1c810c08375422707a097cba68840c0f66"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1KjDzZ/qR43Rc8oAc0XdbAqUuDEswdL5hO/KQPzqruTx0tfdanz9F27KvNuN1njkrARcoIsDN1FYLd/Or4qsDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T02:45:39.270617Z","bundle_sha256":"61aede68ee6aae49918a8e093b3859c22271c3a64e42101c6a187c1ef2122504"}}