{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:IJ7CZVNELXICUSNYQAVG2PN3KT","short_pith_number":"pith:IJ7CZVNE","canonical_record":{"source":{"id":"1707.03253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-11T13:04:15Z","cross_cats_sorted":[],"title_canon_sha256":"fb2cc12b0991f62edcf7198005cf7a2a3e99625bafcebd06f3850d0ec3b68d84","abstract_canon_sha256":"fc8aa06c1563746afeb7a091e8a9d0a4b01fe023133df538b25ecb213465c75b"},"schema_version":"1.0"},"canonical_sha256":"427e2cd5a45dd02a49b8802a6d3dbb54e380e0f690fc1501414a4f7c4351a869","source":{"kind":"arxiv","id":"1707.03253","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.03253","created_at":"2026-05-18T00:40:29Z"},{"alias_kind":"arxiv_version","alias_value":"1707.03253v1","created_at":"2026-05-18T00:40:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03253","created_at":"2026-05-18T00:40:29Z"},{"alias_kind":"pith_short_12","alias_value":"IJ7CZVNELXIC","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IJ7CZVNELXICUSNY","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IJ7CZVNE","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:IJ7CZVNELXICUSNYQAVG2PN3KT","target":"record","payload":{"canonical_record":{"source":{"id":"1707.03253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-11T13:04:15Z","cross_cats_sorted":[],"title_canon_sha256":"fb2cc12b0991f62edcf7198005cf7a2a3e99625bafcebd06f3850d0ec3b68d84","abstract_canon_sha256":"fc8aa06c1563746afeb7a091e8a9d0a4b01fe023133df538b25ecb213465c75b"},"schema_version":"1.0"},"canonical_sha256":"427e2cd5a45dd02a49b8802a6d3dbb54e380e0f690fc1501414a4f7c4351a869","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:29.488060Z","signature_b64":"RpuAtxN+5GbKWsd8vnaSgHhYZqlo7gwpFYeqHWEpDNy3oBj26TCqIySQeI62n1kbYWWaHq8X5LFtfzDPEyJwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"427e2cd5a45dd02a49b8802a6d3dbb54e380e0f690fc1501414a4f7c4351a869","last_reissued_at":"2026-05-18T00:40:29.487571Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:29.487571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.03253","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":"2026-05-18T00:40:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vgaEgyclou2A5hWbvhOVeltp8ezMQ90vzSpU9WhCi9BYmOMXWpNZ9azERGnYJRwATkeWEfVHdgGW22PoCpalDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:55:47.273414Z"},"content_sha256":"92b3811b75ed69df3918299c8745a5f95880cbeab16e1da8c19fd3707f137562","schema_version":"1.0","event_id":"sha256:92b3811b75ed69df3918299c8745a5f95880cbeab16e1da8c19fd3707f137562"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:IJ7CZVNELXICUSNYQAVG2PN3KT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leipzig Corpus Miner - A Text Mining Infrastructure for Qualitative Data Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andreas Niekler, Gerhard Heyer, Gregor Wiedemann","submitted_at":"2017-07-11T13:04:15Z","abstract_excerpt":"This paper presents the \"Leipzig Corpus Miner\", a technical infrastructure for supporting qualitative and quantitative content analysis. The infrastructure aims at the integration of 'close reading' procedures on individual documents with procedures of 'distant reading', e.g. lexical characteristics of large document collections. Therefore information retrieval systems, lexicometric statistics and machine learning procedures are combined in a coherent framework which enables qualitative data analysts to make use of state-of-the-art Natural Language Processing techniques on very large document "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03253","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":"2026-05-18T00:40:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AyYFUqGKFd/iUqXSteljR9V7+v40ZRZChrZsboM0jrXkI8CFha60v6JuBwaXpLgCrxwslVqZqMYrwH+WqXvtCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:55:47.273774Z"},"content_sha256":"a2556984a00eb468cfbf5006a45cdc2007a700bddd3e5d13b9fa982f4391acb9","schema_version":"1.0","event_id":"sha256:a2556984a00eb468cfbf5006a45cdc2007a700bddd3e5d13b9fa982f4391acb9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IJ7CZVNELXICUSNYQAVG2PN3KT/bundle.json","state_url":"https://pith.science/pith/IJ7CZVNELXICUSNYQAVG2PN3KT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IJ7CZVNELXICUSNYQAVG2PN3KT/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":"2026-06-01T06:55:47Z","links":{"resolver":"https://pith.science/pith/IJ7CZVNELXICUSNYQAVG2PN3KT","bundle":"https://pith.science/pith/IJ7CZVNELXICUSNYQAVG2PN3KT/bundle.json","state":"https://pith.science/pith/IJ7CZVNELXICUSNYQAVG2PN3KT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IJ7CZVNELXICUSNYQAVG2PN3KT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:IJ7CZVNELXICUSNYQAVG2PN3KT","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":"fc8aa06c1563746afeb7a091e8a9d0a4b01fe023133df538b25ecb213465c75b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-11T13:04:15Z","title_canon_sha256":"fb2cc12b0991f62edcf7198005cf7a2a3e99625bafcebd06f3850d0ec3b68d84"},"schema_version":"1.0","source":{"id":"1707.03253","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.03253","created_at":"2026-05-18T00:40:29Z"},{"alias_kind":"arxiv_version","alias_value":"1707.03253v1","created_at":"2026-05-18T00:40:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03253","created_at":"2026-05-18T00:40:29Z"},{"alias_kind":"pith_short_12","alias_value":"IJ7CZVNELXIC","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IJ7CZVNELXICUSNY","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IJ7CZVNE","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:a2556984a00eb468cfbf5006a45cdc2007a700bddd3e5d13b9fa982f4391acb9","target":"graph","created_at":"2026-05-18T00:40:29Z","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":"This paper presents the \"Leipzig Corpus Miner\", a technical infrastructure for supporting qualitative and quantitative content analysis. The infrastructure aims at the integration of 'close reading' procedures on individual documents with procedures of 'distant reading', e.g. lexical characteristics of large document collections. Therefore information retrieval systems, lexicometric statistics and machine learning procedures are combined in a coherent framework which enables qualitative data analysts to make use of state-of-the-art Natural Language Processing techniques on very large document ","authors_text":"Andreas Niekler, Gerhard Heyer, Gregor Wiedemann","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-11T13:04:15Z","title":"Leipzig Corpus Miner - A Text Mining Infrastructure for Qualitative Data Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03253","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":"sha256:92b3811b75ed69df3918299c8745a5f95880cbeab16e1da8c19fd3707f137562","target":"record","created_at":"2026-05-18T00:40:29Z","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":"fc8aa06c1563746afeb7a091e8a9d0a4b01fe023133df538b25ecb213465c75b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-11T13:04:15Z","title_canon_sha256":"fb2cc12b0991f62edcf7198005cf7a2a3e99625bafcebd06f3850d0ec3b68d84"},"schema_version":"1.0","source":{"id":"1707.03253","kind":"arxiv","version":1}},"canonical_sha256":"427e2cd5a45dd02a49b8802a6d3dbb54e380e0f690fc1501414a4f7c4351a869","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"427e2cd5a45dd02a49b8802a6d3dbb54e380e0f690fc1501414a4f7c4351a869","first_computed_at":"2026-05-18T00:40:29.487571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:29.487571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RpuAtxN+5GbKWsd8vnaSgHhYZqlo7gwpFYeqHWEpDNy3oBj26TCqIySQeI62n1kbYWWaHq8X5LFtfzDPEyJwDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:29.488060Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.03253","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92b3811b75ed69df3918299c8745a5f95880cbeab16e1da8c19fd3707f137562","sha256:a2556984a00eb468cfbf5006a45cdc2007a700bddd3e5d13b9fa982f4391acb9"],"state_sha256":"e37d01f0f3f46ffc6ce58e4d3494d076d613e17b44c7ef83e0f09ce802f4146c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a5Sc8+eXWrEG2nAzrL9OO5d8KXXhn7re7M2avPPNt84/rMh3y9kGmCzJp2V8NWPcdLr5S2qdr7WwOimGQotODQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T06:55:47.276276Z","bundle_sha256":"6dfcab0e43edd6cffd1626c9ddc9dd5572a2d07300acd1f39584923f2bdfea19"}}