{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:K7F3HP77UODCN6A3QTLZ7AYHI2","short_pith_number":"pith:K7F3HP77","canonical_record":{"source":{"id":"2202.09452","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-18T22:17:22Z","cross_cats_sorted":[],"title_canon_sha256":"2e142d1d3d04744a626b4e4476ebda6509324d65e2d6769f5394f07746810ddd","abstract_canon_sha256":"ad4bc27bdc7fa53a40c68df8b788ca85f76f2e97d2f9de4b159ffbe93118e37c"},"schema_version":"1.0"},"canonical_sha256":"57cbb3bfffa38626f81b84d79f83074693923fe7624c61efaca67b4e4fe91e73","source":{"kind":"arxiv","id":"2202.09452","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.09452","created_at":"2026-07-05T03:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"2202.09452v1","created_at":"2026-07-05T03:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09452","created_at":"2026-07-05T03:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"K7F3HP77UODC","created_at":"2026-07-05T03:58:22Z"},{"alias_kind":"pith_short_16","alias_value":"K7F3HP77UODCN6A3","created_at":"2026-07-05T03:58:22Z"},{"alias_kind":"pith_short_8","alias_value":"K7F3HP77","created_at":"2026-07-05T03:58:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:K7F3HP77UODCN6A3QTLZ7AYHI2","target":"record","payload":{"canonical_record":{"source":{"id":"2202.09452","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-18T22:17:22Z","cross_cats_sorted":[],"title_canon_sha256":"2e142d1d3d04744a626b4e4476ebda6509324d65e2d6769f5394f07746810ddd","abstract_canon_sha256":"ad4bc27bdc7fa53a40c68df8b788ca85f76f2e97d2f9de4b159ffbe93118e37c"},"schema_version":"1.0"},"canonical_sha256":"57cbb3bfffa38626f81b84d79f83074693923fe7624c61efaca67b4e4fe91e73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:22.435020Z","signature_b64":"/np12QC+q3xeJrGBmCXMAy/lXk67+v9VULVbiOhoicg9dHgO06/EGx6w3kzgVHd7ST7ncq0FJPzpeI2I5DGfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57cbb3bfffa38626f81b84d79f83074693923fe7624c61efaca67b4e4fe91e73","last_reissued_at":"2026-07-05T03:58:22.434571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:22.434571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.09452","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":"2026-07-05T03:58:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z1e55lMG5JRtLc8Qf61B9ukezNfDdBrUng+tCT1staWDDHV5rAnm4PPeU87jfVdrg4/ZzJXplvz0ti97YSL9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T21:17:22.623458Z"},"content_sha256":"162d35b135fad73d12ff9b2dc4ab525e1d297669df8e39df315016f9648f22f9","schema_version":"1.0","event_id":"sha256:162d35b135fad73d12ff9b2dc4ab525e1d297669df8e39df315016f9648f22f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:K7F3HP77UODCN6A3QTLZ7AYHI2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From FreEM to D'AlemBERT: a Large Corpus and a Language Model for Early Modern French","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandre Bartz, Alix Chagu\\'e, Beno\\^it Sagot, Pedro Ortiz Suarez, Philippe Gambette, Rachel Bawden, Simon Gabay","submitted_at":"2022-02-18T22:17:22Z","abstract_excerpt":"Language models for historical states of language are becoming increasingly important to allow the optimal digitisation and analysis of old textual sources. Because these historical states are at the same time more complex to process and more scarce in the corpora available, specific efforts are necessary to train natural language processing (NLP) tools adapted to the data. In this paper, we present our efforts to develop NLP tools for Early Modern French (historical French from the 16$^\\text{th}$ to the 18$^\\text{th}$ centuries). We present the $\\text{FreEM}_{\\text{max}}$ corpus of Early Mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09452","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/2202.09452/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":"2026-07-05T03:58:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d8vFUfjN/Co0p1tw0okobjIN2Gp9WaQ+7X9i7Yt7MdaDF9f0W4gA8o6anHkIqbLtPwdOMOxsuTONUk/hSIVgCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T21:17:22.623804Z"},"content_sha256":"d2529e8b4654a8b95247c098621eb7e80ba2df68ab79766e3abca1639bec8c76","schema_version":"1.0","event_id":"sha256:d2529e8b4654a8b95247c098621eb7e80ba2df68ab79766e3abca1639bec8c76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K7F3HP77UODCN6A3QTLZ7AYHI2/bundle.json","state_url":"https://pith.science/pith/K7F3HP77UODCN6A3QTLZ7AYHI2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K7F3HP77UODCN6A3QTLZ7AYHI2/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":"2026-08-19T21:17:22Z","links":{"resolver":"https://pith.science/pith/K7F3HP77UODCN6A3QTLZ7AYHI2","bundle":"https://pith.science/pith/K7F3HP77UODCN6A3QTLZ7AYHI2/bundle.json","state":"https://pith.science/pith/K7F3HP77UODCN6A3QTLZ7AYHI2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K7F3HP77UODCN6A3QTLZ7AYHI2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:K7F3HP77UODCN6A3QTLZ7AYHI2","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":"ad4bc27bdc7fa53a40c68df8b788ca85f76f2e97d2f9de4b159ffbe93118e37c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-18T22:17:22Z","title_canon_sha256":"2e142d1d3d04744a626b4e4476ebda6509324d65e2d6769f5394f07746810ddd"},"schema_version":"1.0","source":{"id":"2202.09452","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.09452","created_at":"2026-07-05T03:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"2202.09452v1","created_at":"2026-07-05T03:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09452","created_at":"2026-07-05T03:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"K7F3HP77UODC","created_at":"2026-07-05T03:58:22Z"},{"alias_kind":"pith_short_16","alias_value":"K7F3HP77UODCN6A3","created_at":"2026-07-05T03:58:22Z"},{"alias_kind":"pith_short_8","alias_value":"K7F3HP77","created_at":"2026-07-05T03:58:22Z"}],"graph_snapshots":[{"event_id":"sha256:d2529e8b4654a8b95247c098621eb7e80ba2df68ab79766e3abca1639bec8c76","target":"graph","created_at":"2026-07-05T03:58:22Z","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/2202.09452/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models for historical states of language are becoming increasingly important to allow the optimal digitisation and analysis of old textual sources. Because these historical states are at the same time more complex to process and more scarce in the corpora available, specific efforts are necessary to train natural language processing (NLP) tools adapted to the data. In this paper, we present our efforts to develop NLP tools for Early Modern French (historical French from the 16$^\\text{th}$ to the 18$^\\text{th}$ centuries). We present the $\\text{FreEM}_{\\text{max}}$ corpus of Early Mode","authors_text":"Alexandre Bartz, Alix Chagu\\'e, Beno\\^it Sagot, Pedro Ortiz Suarez, Philippe Gambette, Rachel Bawden, Simon Gabay","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-18T22:17:22Z","title":"From FreEM to D'AlemBERT: a Large Corpus and a Language Model for Early Modern French"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09452","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":"sha256:162d35b135fad73d12ff9b2dc4ab525e1d297669df8e39df315016f9648f22f9","target":"record","created_at":"2026-07-05T03:58:22Z","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":"ad4bc27bdc7fa53a40c68df8b788ca85f76f2e97d2f9de4b159ffbe93118e37c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-18T22:17:22Z","title_canon_sha256":"2e142d1d3d04744a626b4e4476ebda6509324d65e2d6769f5394f07746810ddd"},"schema_version":"1.0","source":{"id":"2202.09452","kind":"arxiv","version":1}},"canonical_sha256":"57cbb3bfffa38626f81b84d79f83074693923fe7624c61efaca67b4e4fe91e73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57cbb3bfffa38626f81b84d79f83074693923fe7624c61efaca67b4e4fe91e73","first_computed_at":"2026-07-05T03:58:22.434571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:58:22.434571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/np12QC+q3xeJrGBmCXMAy/lXk67+v9VULVbiOhoicg9dHgO06/EGx6w3kzgVHd7ST7ncq0FJPzpeI2I5DGfDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:58:22.435020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.09452","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:162d35b135fad73d12ff9b2dc4ab525e1d297669df8e39df315016f9648f22f9","sha256:d2529e8b4654a8b95247c098621eb7e80ba2df68ab79766e3abca1639bec8c76"],"state_sha256":"b7714df0f22c215b1f505b633916d29adb75d0ba7c746e9a935b172044b8e6b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rhAKGENeTdmgKiBE0vBUbacIK6uJwj3KghLgu2eZY3IwZSEtEiKM3XPo5IY/195d+VVNAPW3M3U1keAsNTVnBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T21:17:22.627129Z","bundle_sha256":"c18451a75b89e7a78f6d80d758810ee7607ee44c15cd506c5a94be102f4a9380"}}