{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RUSJGXEMIR76PF3UVJ5NUH4J36","short_pith_number":"pith:RUSJGXEM","canonical_record":{"source":{"id":"2501.08003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T10:47:33Z","cross_cats_sorted":[],"title_canon_sha256":"fd8f259c3804577c3d24611db2d5f93f08cd659a0c5cc182e58d63035521900f","abstract_canon_sha256":"98126a5e12282d1e8043046baa41e79d6279c76e9bc02936d53efec18263fd07"},"schema_version":"1.0"},"canonical_sha256":"8d24935c8c447fe79774aa7ada1f89dfa87ffb489648db27786006c0906bddb1","source":{"kind":"arxiv","id":"2501.08003","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08003","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08003v1","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08003","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_12","alias_value":"RUSJGXEMIR76","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_16","alias_value":"RUSJGXEMIR76PF3U","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_8","alias_value":"RUSJGXEM","created_at":"2026-07-05T10:00:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RUSJGXEMIR76PF3UVJ5NUH4J36","target":"record","payload":{"canonical_record":{"source":{"id":"2501.08003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T10:47:33Z","cross_cats_sorted":[],"title_canon_sha256":"fd8f259c3804577c3d24611db2d5f93f08cd659a0c5cc182e58d63035521900f","abstract_canon_sha256":"98126a5e12282d1e8043046baa41e79d6279c76e9bc02936d53efec18263fd07"},"schema_version":"1.0"},"canonical_sha256":"8d24935c8c447fe79774aa7ada1f89dfa87ffb489648db27786006c0906bddb1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:53.719684Z","signature_b64":"/lxqUotzqPgHwewOx4arYS/N1SBNujcwXx9xXY1HjRt2BH/eiAbLRbzk+F2l58w5EQlTfjIjhmA9vO9hQ7EiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d24935c8c447fe79774aa7ada1f89dfa87ffb489648db27786006c0906bddb1","last_reissued_at":"2026-07-05T10:00:53.719222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:53.719222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.08003","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":"2026-07-05T10:00:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6itACy0j9kYien0BMqfvxTLZBHMSTcCIpPtkreOfpbJxR9i2dtbizxpPsatWoQOUp635z//g/F/C3vo3F69VDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T09:44:37.198383Z"},"content_sha256":"1abe4b34fe7e157c30c29dc1bba33e7df82df8cf51218428565a61011560bcd2","schema_version":"1.0","event_id":"sha256:1abe4b34fe7e157c30c29dc1bba33e7df82df8cf51218428565a61011560bcd2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RUSJGXEMIR76PF3UVJ5NUH4J36","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Formalising lexical and syntactic diversity for data sampling in French","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Agata Savary, Louis Est\\`eve, Manon Scholivet","submitted_at":"2025-01-14T10:47:33Z","abstract_excerpt":"Diversity is an important property of datasets and sampling data for diversity is useful in dataset creation. Finding the optimally diverse sample is expensive, we therefore present a heuristic significantly increasing diversity relative to random sampling. We also explore whether different kinds of diversity -- lexical and syntactic -- correlate, with the purpose of sampling for expensive syntactic diversity through inexpensive lexical diversity. We find that correlations fluctuate with different datasets and versions of diversity measures. This shows that an arbitrarily chosen measure may fa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08003","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/2501.08003/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":"2026-07-05T10:00:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vtnLpJ9uQVG0iiiWwDRzxYv2EG9hyCxkD3EbdnvMpE2rgxK1k+84hZUGYdVuz7sl/7L3ScGHIs31J740VMf+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T09:44:37.199271Z"},"content_sha256":"2fbbd4b1ae888dc1805f296de621019b4d5e37d85b5c7065bad28adac4d85070","schema_version":"1.0","event_id":"sha256:2fbbd4b1ae888dc1805f296de621019b4d5e37d85b5c7065bad28adac4d85070"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RUSJGXEMIR76PF3UVJ5NUH4J36/bundle.json","state_url":"https://pith.science/pith/RUSJGXEMIR76PF3UVJ5NUH4J36/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RUSJGXEMIR76PF3UVJ5NUH4J36/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":"2026-08-11T09:44:37Z","links":{"resolver":"https://pith.science/pith/RUSJGXEMIR76PF3UVJ5NUH4J36","bundle":"https://pith.science/pith/RUSJGXEMIR76PF3UVJ5NUH4J36/bundle.json","state":"https://pith.science/pith/RUSJGXEMIR76PF3UVJ5NUH4J36/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RUSJGXEMIR76PF3UVJ5NUH4J36/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RUSJGXEMIR76PF3UVJ5NUH4J36","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":"98126a5e12282d1e8043046baa41e79d6279c76e9bc02936d53efec18263fd07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T10:47:33Z","title_canon_sha256":"fd8f259c3804577c3d24611db2d5f93f08cd659a0c5cc182e58d63035521900f"},"schema_version":"1.0","source":{"id":"2501.08003","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08003","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08003v1","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08003","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_12","alias_value":"RUSJGXEMIR76","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_16","alias_value":"RUSJGXEMIR76PF3U","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_8","alias_value":"RUSJGXEM","created_at":"2026-07-05T10:00:53Z"}],"graph_snapshots":[{"event_id":"sha256:2fbbd4b1ae888dc1805f296de621019b4d5e37d85b5c7065bad28adac4d85070","target":"graph","created_at":"2026-07-05T10:00:53Z","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/2501.08003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diversity is an important property of datasets and sampling data for diversity is useful in dataset creation. Finding the optimally diverse sample is expensive, we therefore present a heuristic significantly increasing diversity relative to random sampling. We also explore whether different kinds of diversity -- lexical and syntactic -- correlate, with the purpose of sampling for expensive syntactic diversity through inexpensive lexical diversity. We find that correlations fluctuate with different datasets and versions of diversity measures. This shows that an arbitrarily chosen measure may fa","authors_text":"Agata Savary, Louis Est\\`eve, Manon Scholivet","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T10:47:33Z","title":"Formalising lexical and syntactic diversity for data sampling in French"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08003","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":"sha256:1abe4b34fe7e157c30c29dc1bba33e7df82df8cf51218428565a61011560bcd2","target":"record","created_at":"2026-07-05T10:00:53Z","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":"98126a5e12282d1e8043046baa41e79d6279c76e9bc02936d53efec18263fd07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T10:47:33Z","title_canon_sha256":"fd8f259c3804577c3d24611db2d5f93f08cd659a0c5cc182e58d63035521900f"},"schema_version":"1.0","source":{"id":"2501.08003","kind":"arxiv","version":1}},"canonical_sha256":"8d24935c8c447fe79774aa7ada1f89dfa87ffb489648db27786006c0906bddb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d24935c8c447fe79774aa7ada1f89dfa87ffb489648db27786006c0906bddb1","first_computed_at":"2026-07-05T10:00:53.719222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:53.719222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/lxqUotzqPgHwewOx4arYS/N1SBNujcwXx9xXY1HjRt2BH/eiAbLRbzk+F2l58w5EQlTfjIjhmA9vO9hQ7EiBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:53.719684Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08003","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1abe4b34fe7e157c30c29dc1bba33e7df82df8cf51218428565a61011560bcd2","sha256:2fbbd4b1ae888dc1805f296de621019b4d5e37d85b5c7065bad28adac4d85070"],"state_sha256":"cb196077ab24562aedd9b1a27e457d543814d980a85e80229b5f1fd13f2a43a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ugxJ12VsMXiXstTwJ32PTO0r5CuFh0Llg5FNndKzSCw+98pf0S9li12WL1d+y7GYkQkn7FuEYWSLh6O+NBQcAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T09:44:37.205760Z","bundle_sha256":"7bf068272dc0ddfded418a9a620cd3d1a0fbc1a0ae8f17e250261d78e5bde60c"}}