{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:QX7PTP2JDAVL4WC4G5PCRZOUYM","short_pith_number":"pith:QX7PTP2J","canonical_record":{"source":{"id":"1410.6830","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","primary_cat":"cs.CL","submitted_at":"2014-10-24T20:34:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a2ceff135df9110071cb1b17cd5c04c1bcff024e5d8f3cc701642fb5ab498cbf","abstract_canon_sha256":"b2bca1f41436fb5d994c16c7048eb69c9b6cc6cc0792ef780eb475ae607c2d50"},"schema_version":"1.0"},"canonical_sha256":"85fef9bf49182abe585c375e28e5d4c32aca8e07b69dc552d16397cb5077f0d0","source":{"kind":"arxiv","id":"1410.6830","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.6830","created_at":"2026-05-18T02:39:18Z"},{"alias_kind":"arxiv_version","alias_value":"1410.6830v1","created_at":"2026-05-18T02:39:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.6830","created_at":"2026-05-18T02:39:18Z"},{"alias_kind":"pith_short_12","alias_value":"QX7PTP2JDAVL","created_at":"2026-05-18T12:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"QX7PTP2JDAVL4WC4","created_at":"2026-05-18T12:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"QX7PTP2J","created_at":"2026-05-18T12:28:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:QX7PTP2JDAVL4WC4G5PCRZOUYM","target":"record","payload":{"canonical_record":{"source":{"id":"1410.6830","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","primary_cat":"cs.CL","submitted_at":"2014-10-24T20:34:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a2ceff135df9110071cb1b17cd5c04c1bcff024e5d8f3cc701642fb5ab498cbf","abstract_canon_sha256":"b2bca1f41436fb5d994c16c7048eb69c9b6cc6cc0792ef780eb475ae607c2d50"},"schema_version":"1.0"},"canonical_sha256":"85fef9bf49182abe585c375e28e5d4c32aca8e07b69dc552d16397cb5077f0d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:39:18.551196Z","signature_b64":"T8T5Mf8P1OONmBg1oViRi0Y8r+fkQDEEAhsqI5duoBB1uh10fqHIzqkGrr7EkP68J/xautt7PWP59pkzBfRhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85fef9bf49182abe585c375e28e5d4c32aca8e07b69dc552d16397cb5077f0d0","last_reissued_at":"2026-05-18T02:39:18.550741Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:39:18.550741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1410.6830","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":"2026-05-18T02:39:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tni8efrs/Mm6u6Y90Gp2qqgLxU1gxWDM69gg2ci/QNdvb/mhxxdEUxZAKkRyyKiVX7Bx/J2rq/6UyiS7z2tUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T14:41:27.485752Z"},"content_sha256":"8cd5044f265f40e484abadbb4242f18851b65f12d1aaa1e338db67a524778002","schema_version":"1.0","event_id":"sha256:8cd5044f265f40e484abadbb4242f18851b65f12d1aaa1e338db67a524778002"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:QX7PTP2JDAVL4WC4G5PCRZOUYM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clustering Words by Projection Entropy","license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Taylan Cemgil, I\\c{s}{\\i}k Bar{\\i}\\c{s} Fidaner","submitted_at":"2014-10-24T20:34:01Z","abstract_excerpt":"We apply entropy agglomeration (EA), a recently introduced algorithm, to cluster the words of a literary text. EA is a greedy agglomerative procedure that minimizes projection entropy (PE), a function that can quantify the segmentedness of an element set. To apply it, the text is reduced to a feature allocation, a combinatorial object to represent the word occurences in the text's paragraphs. The experiment results demonstrate that EA, despite its reduction and simplicity, is useful in capturing significant relationships among the words in the text. This procedure was implemented in Python and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.6830","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":"2026-05-18T02:39:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7zd2+D0vqIyNBsu5sueFP95dp7oVbDJRAtQeQMxX8JM+7bxijB2UK+fAVpEdnQ+/YefMZWroAsUoOe/RnI4hDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T14:41:27.486211Z"},"content_sha256":"0b7c6c3ff10953ee483db2eae78013a32b7ecdefdc28eb7a89b2f96ca6773373","schema_version":"1.0","event_id":"sha256:0b7c6c3ff10953ee483db2eae78013a32b7ecdefdc28eb7a89b2f96ca6773373"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QX7PTP2JDAVL4WC4G5PCRZOUYM/bundle.json","state_url":"https://pith.science/pith/QX7PTP2JDAVL4WC4G5PCRZOUYM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QX7PTP2JDAVL4WC4G5PCRZOUYM/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":"2026-07-04T14:41:27Z","links":{"resolver":"https://pith.science/pith/QX7PTP2JDAVL4WC4G5PCRZOUYM","bundle":"https://pith.science/pith/QX7PTP2JDAVL4WC4G5PCRZOUYM/bundle.json","state":"https://pith.science/pith/QX7PTP2JDAVL4WC4G5PCRZOUYM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QX7PTP2JDAVL4WC4G5PCRZOUYM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:QX7PTP2JDAVL4WC4G5PCRZOUYM","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":"b2bca1f41436fb5d994c16c7048eb69c9b6cc6cc0792ef780eb475ae607c2d50","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","primary_cat":"cs.CL","submitted_at":"2014-10-24T20:34:01Z","title_canon_sha256":"a2ceff135df9110071cb1b17cd5c04c1bcff024e5d8f3cc701642fb5ab498cbf"},"schema_version":"1.0","source":{"id":"1410.6830","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.6830","created_at":"2026-05-18T02:39:18Z"},{"alias_kind":"arxiv_version","alias_value":"1410.6830v1","created_at":"2026-05-18T02:39:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.6830","created_at":"2026-05-18T02:39:18Z"},{"alias_kind":"pith_short_12","alias_value":"QX7PTP2JDAVL","created_at":"2026-05-18T12:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"QX7PTP2JDAVL4WC4","created_at":"2026-05-18T12:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"QX7PTP2J","created_at":"2026-05-18T12:28:46Z"}],"graph_snapshots":[{"event_id":"sha256:0b7c6c3ff10953ee483db2eae78013a32b7ecdefdc28eb7a89b2f96ca6773373","target":"graph","created_at":"2026-05-18T02:39:18Z","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":"We apply entropy agglomeration (EA), a recently introduced algorithm, to cluster the words of a literary text. EA is a greedy agglomerative procedure that minimizes projection entropy (PE), a function that can quantify the segmentedness of an element set. To apply it, the text is reduced to a feature allocation, a combinatorial object to represent the word occurences in the text's paragraphs. The experiment results demonstrate that EA, despite its reduction and simplicity, is useful in capturing significant relationships among the words in the text. This procedure was implemented in Python and","authors_text":"Ali Taylan Cemgil, I\\c{s}{\\i}k Bar{\\i}\\c{s} Fidaner","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","primary_cat":"cs.CL","submitted_at":"2014-10-24T20:34:01Z","title":"Clustering Words by Projection Entropy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.6830","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":"sha256:8cd5044f265f40e484abadbb4242f18851b65f12d1aaa1e338db67a524778002","target":"record","created_at":"2026-05-18T02:39:18Z","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":"b2bca1f41436fb5d994c16c7048eb69c9b6cc6cc0792ef780eb475ae607c2d50","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","primary_cat":"cs.CL","submitted_at":"2014-10-24T20:34:01Z","title_canon_sha256":"a2ceff135df9110071cb1b17cd5c04c1bcff024e5d8f3cc701642fb5ab498cbf"},"schema_version":"1.0","source":{"id":"1410.6830","kind":"arxiv","version":1}},"canonical_sha256":"85fef9bf49182abe585c375e28e5d4c32aca8e07b69dc552d16397cb5077f0d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85fef9bf49182abe585c375e28e5d4c32aca8e07b69dc552d16397cb5077f0d0","first_computed_at":"2026-05-18T02:39:18.550741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:39:18.550741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T8T5Mf8P1OONmBg1oViRi0Y8r+fkQDEEAhsqI5duoBB1uh10fqHIzqkGrr7EkP68J/xautt7PWP59pkzBfRhAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:39:18.551196Z","signed_message":"canonical_sha256_bytes"},"source_id":"1410.6830","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cd5044f265f40e484abadbb4242f18851b65f12d1aaa1e338db67a524778002","sha256:0b7c6c3ff10953ee483db2eae78013a32b7ecdefdc28eb7a89b2f96ca6773373"],"state_sha256":"64aaf3c51ab205daee2a5a62b241b5e12f47c21905f7905a88bc9ee5e61edd0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K5RtP4uMGl5F6PRsP6R1gY4GRtUUAMiJGU+S0Kx1pWkSa8BObmwwFvIN8QDVtM9WgwoBgjSTtFksqbQVCuTJBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T14:41:27.488353Z","bundle_sha256":"978af93fe40bb64995b29847a911ddbb7e8d6bec5ba2e4a8de624a933ce4c72b"}}