{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PEZFCSQW7JTWMVO2BNSIOTIYVX","short_pith_number":"pith:PEZFCSQW","canonical_record":{"source":{"id":"2411.11260","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T03:29:48Z","cross_cats_sorted":[],"title_canon_sha256":"5853b8b7ca4b0c37dc0f8f1d2a143d618fa725462935755b1fd4ee4b834ccefe","abstract_canon_sha256":"46b16ca4f1f29172ae15b155a39bfa28f37e5d4bbe4a272a8b7893e10d98e902"},"schema_version":"1.0"},"canonical_sha256":"7932514a16fa676655da0b64874d18adc009593e3ccf1a7e17544b5dcabb4fc3","source":{"kind":"arxiv","id":"2411.11260","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11260","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11260v2","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11260","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"pith_short_12","alias_value":"PEZFCSQW7JTW","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"pith_short_16","alias_value":"PEZFCSQW7JTWMVO2","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"pith_short_8","alias_value":"PEZFCSQW","created_at":"2026-07-05T10:46:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PEZFCSQW7JTWMVO2BNSIOTIYVX","target":"record","payload":{"canonical_record":{"source":{"id":"2411.11260","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T03:29:48Z","cross_cats_sorted":[],"title_canon_sha256":"5853b8b7ca4b0c37dc0f8f1d2a143d618fa725462935755b1fd4ee4b834ccefe","abstract_canon_sha256":"46b16ca4f1f29172ae15b155a39bfa28f37e5d4bbe4a272a8b7893e10d98e902"},"schema_version":"1.0"},"canonical_sha256":"7932514a16fa676655da0b64874d18adc009593e3ccf1a7e17544b5dcabb4fc3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:58.587474Z","signature_b64":"TIpPX1lkoFHN+yKXMw/vxGtbCwNVs5ytvvC2sXEZV6cZhjgmZ+ZMh+2eo9bhcM5sGKSHsHCc2aFZ+dwv4xZ2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7932514a16fa676655da0b64874d18adc009593e3ccf1a7e17544b5dcabb4fc3","last_reissued_at":"2026-07-05T10:46:58.586858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:58.586858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.11260","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:46:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DWGCcpzGlmB85gf4iloDRn3QLiG6IbAjFpb3jdY24JN3DaDarZvYAPCZoDhxELnvac6jNpFF9TOt9RayMWvWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:06:32.457461Z"},"content_sha256":"7d7ecc12819bc9fa4f7405376968b40f04c4ebdbc76ea42195b4f84ef97b9d76","schema_version":"1.0","event_id":"sha256:7d7ecc12819bc9fa4f7405376968b40f04c4ebdbc76ea42195b4f84ef97b9d76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PEZFCSQW7JTWMVO2BNSIOTIYVX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large corpora and large language models: a replicable method for automating grammatical annotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cameron Morin, Matti Marttinen Larsson","submitted_at":"2024-11-18T03:29:48Z","abstract_excerpt":"Much linguistic research relies on annotated datasets of features extracted from text corpora, but the rapid quantitative growth of these corpora has created practical difficulties for linguists to manually annotate large data samples. In this paper, we present a replicable, supervised method that leverages large language models for assisting the linguist in grammatical annotation through prompt engineering, training, and evaluation. We introduce a methodological pipeline applied to the case study of formal variation in the English evaluative verb construction 'consider X (as) (to be) Y', base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11260","kind":"arxiv","version":2},"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/2411.11260/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":"2026-07-05T10:46:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JlneyS14HO0dscxoIxMT/A8BtyBB6O8BMBV9wV4qs1gEZNyn1/7GEH8pJ6vBcxKOZo8NRddtq1m9Q8osgiybCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:06:32.457778Z"},"content_sha256":"6910dc60b8683dd448ede5e93f4d56c05b95ee1f59f2ae2eac30dbbe2141630e","schema_version":"1.0","event_id":"sha256:6910dc60b8683dd448ede5e93f4d56c05b95ee1f59f2ae2eac30dbbe2141630e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PEZFCSQW7JTWMVO2BNSIOTIYVX/bundle.json","state_url":"https://pith.science/pith/PEZFCSQW7JTWMVO2BNSIOTIYVX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PEZFCSQW7JTWMVO2BNSIOTIYVX/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":"2026-08-14T09:06:32Z","links":{"resolver":"https://pith.science/pith/PEZFCSQW7JTWMVO2BNSIOTIYVX","bundle":"https://pith.science/pith/PEZFCSQW7JTWMVO2BNSIOTIYVX/bundle.json","state":"https://pith.science/pith/PEZFCSQW7JTWMVO2BNSIOTIYVX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PEZFCSQW7JTWMVO2BNSIOTIYVX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PEZFCSQW7JTWMVO2BNSIOTIYVX","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":"46b16ca4f1f29172ae15b155a39bfa28f37e5d4bbe4a272a8b7893e10d98e902","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T03:29:48Z","title_canon_sha256":"5853b8b7ca4b0c37dc0f8f1d2a143d618fa725462935755b1fd4ee4b834ccefe"},"schema_version":"1.0","source":{"id":"2411.11260","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11260","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11260v2","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11260","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"pith_short_12","alias_value":"PEZFCSQW7JTW","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"pith_short_16","alias_value":"PEZFCSQW7JTWMVO2","created_at":"2026-07-05T10:46:58Z"},{"alias_kind":"pith_short_8","alias_value":"PEZFCSQW","created_at":"2026-07-05T10:46:58Z"}],"graph_snapshots":[{"event_id":"sha256:6910dc60b8683dd448ede5e93f4d56c05b95ee1f59f2ae2eac30dbbe2141630e","target":"graph","created_at":"2026-07-05T10:46:58Z","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/2411.11260/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Much linguistic research relies on annotated datasets of features extracted from text corpora, but the rapid quantitative growth of these corpora has created practical difficulties for linguists to manually annotate large data samples. In this paper, we present a replicable, supervised method that leverages large language models for assisting the linguist in grammatical annotation through prompt engineering, training, and evaluation. We introduce a methodological pipeline applied to the case study of formal variation in the English evaluative verb construction 'consider X (as) (to be) Y', base","authors_text":"Cameron Morin, Matti Marttinen Larsson","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T03:29:48Z","title":"Large corpora and large language models: a replicable method for automating grammatical annotation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11260","kind":"arxiv","version":2},"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":"sha256:7d7ecc12819bc9fa4f7405376968b40f04c4ebdbc76ea42195b4f84ef97b9d76","target":"record","created_at":"2026-07-05T10:46:58Z","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":"46b16ca4f1f29172ae15b155a39bfa28f37e5d4bbe4a272a8b7893e10d98e902","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T03:29:48Z","title_canon_sha256":"5853b8b7ca4b0c37dc0f8f1d2a143d618fa725462935755b1fd4ee4b834ccefe"},"schema_version":"1.0","source":{"id":"2411.11260","kind":"arxiv","version":2}},"canonical_sha256":"7932514a16fa676655da0b64874d18adc009593e3ccf1a7e17544b5dcabb4fc3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7932514a16fa676655da0b64874d18adc009593e3ccf1a7e17544b5dcabb4fc3","first_computed_at":"2026-07-05T10:46:58.586858Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:58.586858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TIpPX1lkoFHN+yKXMw/vxGtbCwNVs5ytvvC2sXEZV6cZhjgmZ+ZMh+2eo9bhcM5sGKSHsHCc2aFZ+dwv4xZ2AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:58.587474Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.11260","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d7ecc12819bc9fa4f7405376968b40f04c4ebdbc76ea42195b4f84ef97b9d76","sha256:6910dc60b8683dd448ede5e93f4d56c05b95ee1f59f2ae2eac30dbbe2141630e"],"state_sha256":"4357baca5e8b3489ed44292b992b01077878575e3b9cc1bdc03173fdfa1abb07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3y5UQYtmsHCfyWY51YFwIcBhzb4BBP3Crrva/jpvQTNYbj0W483N9TgZ17EkUVpAeXm3W0Rr71mOg/53KnJiBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T09:06:32.459954Z","bundle_sha256":"3ab51864e123d9da759f914d2cf08d22a32e6d5eabb9a742a3e6d7bb0da468c8"}}