{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2010:LHGUEW6RJJZDSUW5EDSXOWX6ZS","short_pith_number":"pith:LHGUEW6R","canonical_record":{"source":{"id":"1012.2797","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.SD","submitted_at":"2010-12-13T16:44:46Z","cross_cats_sorted":[],"title_canon_sha256":"3d91a5b99f7697290aebf5ae4cfded716dc23f5ccf8e3dd53b3a5682818443cd","abstract_canon_sha256":"6a0e87d50d24217cfe8e14072eceaf2cb1c94846079a739f03e056965cceb833"},"schema_version":"1.0"},"canonical_sha256":"59cd425bd14a723952dd20e5775afecc9c3e2354f078f580300af98025bcc99e","source":{"kind":"arxiv","id":"1012.2797","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1012.2797","created_at":"2026-05-18T04:33:27Z"},{"alias_kind":"arxiv_version","alias_value":"1012.2797v1","created_at":"2026-05-18T04:33:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1012.2797","created_at":"2026-05-18T04:33:27Z"},{"alias_kind":"pith_short_12","alias_value":"LHGUEW6RJJZD","created_at":"2026-05-18T12:26:10Z"},{"alias_kind":"pith_short_16","alias_value":"LHGUEW6RJJZDSUW5","created_at":"2026-05-18T12:26:10Z"},{"alias_kind":"pith_short_8","alias_value":"LHGUEW6R","created_at":"2026-05-18T12:26:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2010:LHGUEW6RJJZDSUW5EDSXOWX6ZS","target":"record","payload":{"canonical_record":{"source":{"id":"1012.2797","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.SD","submitted_at":"2010-12-13T16:44:46Z","cross_cats_sorted":[],"title_canon_sha256":"3d91a5b99f7697290aebf5ae4cfded716dc23f5ccf8e3dd53b3a5682818443cd","abstract_canon_sha256":"6a0e87d50d24217cfe8e14072eceaf2cb1c94846079a739f03e056965cceb833"},"schema_version":"1.0"},"canonical_sha256":"59cd425bd14a723952dd20e5775afecc9c3e2354f078f580300af98025bcc99e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:33:27.741108Z","signature_b64":"lAAr5HpkuQ7kFEfLnYf9UiggyXyxmtMemHn/FPtD9PxDBNGD5x4GNm7ojB1yA5VP1UdMTHUepouSXklj4/dWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59cd425bd14a723952dd20e5775afecc9c3e2354f078f580300af98025bcc99e","last_reissued_at":"2026-05-18T04:33:27.740454Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:33:27.740454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1012.2797","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":"2026-05-18T04:33:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BdSqi0e6VMcygeBbrNXHplem/m9Fxjf+Y5XvIeQt9TpPl8zjfp1qYY4azsfrUdk34rO0X32oAKowWtf6bt+nAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T00:10:24.828192Z"},"content_sha256":"f52a1d7bd09f92317021683fdc954d447c0c2cfe8e02d477603bbee5b05395ce","schema_version":"1.0","event_id":"sha256:f52a1d7bd09f92317021683fdc954d447c0c2cfe8e02d477603bbee5b05395ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2010:LHGUEW6RJJZDSUW5EDSXOWX6ZS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Should Corpora be Big, Rich, or Dense?","license":"http://creativecommons.org/licenses/by/3.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Chilin Shih, Greg P. Kochanski, Ryan Shosted","submitted_at":"2010-12-13T16:44:46Z","abstract_excerpt":"In this paper, we ask what properties makes a large corpus more or less useful. We suggest that size, by itself, should not be the ultimate goal of building a corpus. Large-scale corpora are considered desirable because they offer statistical stability and rich variation. But this rich variation means more factors to control and evaluate, which can limit the advantages of size. We discuss the use of multi-channel data to complement large-scale speech corpora. Even though multi-channel data may limit the scale of a corpus (due to the complex and labor-intensive nature of data collection) they c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1012.2797","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":""},"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":"2026-05-18T04:33:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WiYhG2XBrju4osuek4peiYouZ3oj3zObVVDl5Fw3Wr0ZDtWH22FXMZNDn+d9HKU/Deh62GMSydxW7e4UZnGLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T00:10:24.828562Z"},"content_sha256":"0ec27e320a7503f0199ef6e4842ada1d59f95e75c91dcc51a51705b5a73cec5b","schema_version":"1.0","event_id":"sha256:0ec27e320a7503f0199ef6e4842ada1d59f95e75c91dcc51a51705b5a73cec5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LHGUEW6RJJZDSUW5EDSXOWX6ZS/bundle.json","state_url":"https://pith.science/pith/LHGUEW6RJJZDSUW5EDSXOWX6ZS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LHGUEW6RJJZDSUW5EDSXOWX6ZS/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":"2026-06-03T00:10:24Z","links":{"resolver":"https://pith.science/pith/LHGUEW6RJJZDSUW5EDSXOWX6ZS","bundle":"https://pith.science/pith/LHGUEW6RJJZDSUW5EDSXOWX6ZS/bundle.json","state":"https://pith.science/pith/LHGUEW6RJJZDSUW5EDSXOWX6ZS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LHGUEW6RJJZDSUW5EDSXOWX6ZS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2010:LHGUEW6RJJZDSUW5EDSXOWX6ZS","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":"6a0e87d50d24217cfe8e14072eceaf2cb1c94846079a739f03e056965cceb833","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.SD","submitted_at":"2010-12-13T16:44:46Z","title_canon_sha256":"3d91a5b99f7697290aebf5ae4cfded716dc23f5ccf8e3dd53b3a5682818443cd"},"schema_version":"1.0","source":{"id":"1012.2797","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1012.2797","created_at":"2026-05-18T04:33:27Z"},{"alias_kind":"arxiv_version","alias_value":"1012.2797v1","created_at":"2026-05-18T04:33:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1012.2797","created_at":"2026-05-18T04:33:27Z"},{"alias_kind":"pith_short_12","alias_value":"LHGUEW6RJJZD","created_at":"2026-05-18T12:26:10Z"},{"alias_kind":"pith_short_16","alias_value":"LHGUEW6RJJZDSUW5","created_at":"2026-05-18T12:26:10Z"},{"alias_kind":"pith_short_8","alias_value":"LHGUEW6R","created_at":"2026-05-18T12:26:10Z"}],"graph_snapshots":[{"event_id":"sha256:0ec27e320a7503f0199ef6e4842ada1d59f95e75c91dcc51a51705b5a73cec5b","target":"graph","created_at":"2026-05-18T04:33:27Z","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"},"paper":{"abstract_excerpt":"In this paper, we ask what properties makes a large corpus more or less useful. We suggest that size, by itself, should not be the ultimate goal of building a corpus. Large-scale corpora are considered desirable because they offer statistical stability and rich variation. But this rich variation means more factors to control and evaluate, which can limit the advantages of size. We discuss the use of multi-channel data to complement large-scale speech corpora. Even though multi-channel data may limit the scale of a corpus (due to the complex and labor-intensive nature of data collection) they c","authors_text":"Chilin Shih, Greg P. Kochanski, Ryan Shosted","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.SD","submitted_at":"2010-12-13T16:44:46Z","title":"Should Corpora be Big, Rich, or Dense?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1012.2797","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:f52a1d7bd09f92317021683fdc954d447c0c2cfe8e02d477603bbee5b05395ce","target":"record","created_at":"2026-05-18T04:33:27Z","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":"6a0e87d50d24217cfe8e14072eceaf2cb1c94846079a739f03e056965cceb833","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.SD","submitted_at":"2010-12-13T16:44:46Z","title_canon_sha256":"3d91a5b99f7697290aebf5ae4cfded716dc23f5ccf8e3dd53b3a5682818443cd"},"schema_version":"1.0","source":{"id":"1012.2797","kind":"arxiv","version":1}},"canonical_sha256":"59cd425bd14a723952dd20e5775afecc9c3e2354f078f580300af98025bcc99e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59cd425bd14a723952dd20e5775afecc9c3e2354f078f580300af98025bcc99e","first_computed_at":"2026-05-18T04:33:27.740454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:33:27.740454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lAAr5HpkuQ7kFEfLnYf9UiggyXyxmtMemHn/FPtD9PxDBNGD5x4GNm7ojB1yA5VP1UdMTHUepouSXklj4/dWDw==","signature_status":"signed_v1","signed_at":"2026-05-18T04:33:27.741108Z","signed_message":"canonical_sha256_bytes"},"source_id":"1012.2797","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f52a1d7bd09f92317021683fdc954d447c0c2cfe8e02d477603bbee5b05395ce","sha256:0ec27e320a7503f0199ef6e4842ada1d59f95e75c91dcc51a51705b5a73cec5b"],"state_sha256":"9205aca1762ccd5e149e27dcbad842ee78c03f987a785396b5aa174c1f73298d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KgyNQswuf5crWaymmpWeo0vBI2iQUFkwKFI2fk7rr2BJb7+bvAmOdzFifgL8ZCYaYWcxVvv8uKaP4yQenGx6DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T00:10:24.830483Z","bundle_sha256":"b906a0434f6d7e3443e82718ae92f77c8957a109f677b77e495da2e17107730e"}}