{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:QNQM2PDLW3TBE7XWMDE7BDUBHW","short_pith_number":"pith:QNQM2PDL","canonical_record":{"source":{"id":"1207.2714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2012-07-11T17:31:11Z","cross_cats_sorted":[],"title_canon_sha256":"610cfe3ee31f5bf10de33905258b9d70b994152f58a5f8c6ec23bd58a8f1e4ae","abstract_canon_sha256":"cdfa21672c671f7e41718143307fabf1e0e7fb8f05314387012f26a6f808d3b0"},"schema_version":"1.0"},"canonical_sha256":"8360cd3c6bb6e6127ef660c9f08e813db7e1207067e63edae6ae8494816557e3","source":{"kind":"arxiv","id":"1207.2714","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1207.2714","created_at":"2026-05-18T03:51:14Z"},{"alias_kind":"arxiv_version","alias_value":"1207.2714v1","created_at":"2026-05-18T03:51:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.2714","created_at":"2026-05-18T03:51:14Z"},{"alias_kind":"pith_short_12","alias_value":"QNQM2PDLW3TB","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"QNQM2PDLW3TBE7XW","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"QNQM2PDL","created_at":"2026-05-18T12:27:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:QNQM2PDLW3TBE7XWMDE7BDUBHW","target":"record","payload":{"canonical_record":{"source":{"id":"1207.2714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2012-07-11T17:31:11Z","cross_cats_sorted":[],"title_canon_sha256":"610cfe3ee31f5bf10de33905258b9d70b994152f58a5f8c6ec23bd58a8f1e4ae","abstract_canon_sha256":"cdfa21672c671f7e41718143307fabf1e0e7fb8f05314387012f26a6f808d3b0"},"schema_version":"1.0"},"canonical_sha256":"8360cd3c6bb6e6127ef660c9f08e813db7e1207067e63edae6ae8494816557e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:51:14.720041Z","signature_b64":"52WzvnoOimBj2jOCfUwTAzkW9TtBdufbbcRH/E0avN9SMYZdBVvs4VzQBVRXtQo9fKddH4phWpJ1GzVTGLHsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8360cd3c6bb6e6127ef660c9f08e813db7e1207067e63edae6ae8494816557e3","last_reissued_at":"2026-05-18T03:51:14.719401Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:51:14.719401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1207.2714","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":"2026-05-18T03:51:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3fHUjfyYCSf9fsAck79KqoIDrN9Wobvgk9UGGbrG5GdQZ94FJpo1tQRlQfgm+Vh23+/zX/rtobu7iHuPKQA3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T05:24:23.288154Z"},"content_sha256":"6d8982a674b7cfe2fab64cdf2c0d624ec500e731e8ac50e454b8ee5ee1cb9ed2","schema_version":"1.0","event_id":"sha256:6d8982a674b7cfe2fab64cdf2c0d624ec500e731e8ac50e454b8ee5ee1cb9ed2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:QNQM2PDLW3TBE7XWMDE7BDUBHW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clustering based approach extracting collocations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mohamed Achraf Ben Mohamed, Mohsen Maraoui, Mounir Zrigui","submitted_at":"2012-07-11T17:31:11Z","abstract_excerpt":"The following study presents a collocation extraction approach based on clustering technique. This study uses a combination of several classical measures which cover all aspects of a given corpus then it suggests separating bigrams found in the corpus in several disjoint groups according to the probability of presence of collocations. This will allow excluding groups where the presence of collocations is very unlikely and thus reducing in a meaningful way the search space."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.2714","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":"2026-05-18T03:51:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nt4BNGJPtsaFPALI12EWiGcft3Qh8v+LUOi/IMssPGd2PwQR0Ser4vIzR6cNgstrZOBfxlSPvuc2mrLKreAuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T05:24:23.288755Z"},"content_sha256":"4d22c8742c2089cf960e3e0c014789e3c49ee51a2bd29e0dd0a25dc1c5eb55ba","schema_version":"1.0","event_id":"sha256:4d22c8742c2089cf960e3e0c014789e3c49ee51a2bd29e0dd0a25dc1c5eb55ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QNQM2PDLW3TBE7XWMDE7BDUBHW/bundle.json","state_url":"https://pith.science/pith/QNQM2PDLW3TBE7XWMDE7BDUBHW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QNQM2PDLW3TBE7XWMDE7BDUBHW/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":"2026-08-21T05:24:23Z","links":{"resolver":"https://pith.science/pith/QNQM2PDLW3TBE7XWMDE7BDUBHW","bundle":"https://pith.science/pith/QNQM2PDLW3TBE7XWMDE7BDUBHW/bundle.json","state":"https://pith.science/pith/QNQM2PDLW3TBE7XWMDE7BDUBHW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QNQM2PDLW3TBE7XWMDE7BDUBHW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:QNQM2PDLW3TBE7XWMDE7BDUBHW","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":"cdfa21672c671f7e41718143307fabf1e0e7fb8f05314387012f26a6f808d3b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2012-07-11T17:31:11Z","title_canon_sha256":"610cfe3ee31f5bf10de33905258b9d70b994152f58a5f8c6ec23bd58a8f1e4ae"},"schema_version":"1.0","source":{"id":"1207.2714","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1207.2714","created_at":"2026-05-18T03:51:14Z"},{"alias_kind":"arxiv_version","alias_value":"1207.2714v1","created_at":"2026-05-18T03:51:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.2714","created_at":"2026-05-18T03:51:14Z"},{"alias_kind":"pith_short_12","alias_value":"QNQM2PDLW3TB","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"QNQM2PDLW3TBE7XW","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"QNQM2PDL","created_at":"2026-05-18T12:27:18Z"}],"graph_snapshots":[{"event_id":"sha256:4d22c8742c2089cf960e3e0c014789e3c49ee51a2bd29e0dd0a25dc1c5eb55ba","target":"graph","created_at":"2026-05-18T03:51:14Z","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":"The following study presents a collocation extraction approach based on clustering technique. This study uses a combination of several classical measures which cover all aspects of a given corpus then it suggests separating bigrams found in the corpus in several disjoint groups according to the probability of presence of collocations. This will allow excluding groups where the presence of collocations is very unlikely and thus reducing in a meaningful way the search space.","authors_text":"Mohamed Achraf Ben Mohamed, Mohsen Maraoui, Mounir Zrigui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2012-07-11T17:31:11Z","title":"Clustering based approach extracting collocations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.2714","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":"sha256:6d8982a674b7cfe2fab64cdf2c0d624ec500e731e8ac50e454b8ee5ee1cb9ed2","target":"record","created_at":"2026-05-18T03:51:14Z","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":"cdfa21672c671f7e41718143307fabf1e0e7fb8f05314387012f26a6f808d3b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2012-07-11T17:31:11Z","title_canon_sha256":"610cfe3ee31f5bf10de33905258b9d70b994152f58a5f8c6ec23bd58a8f1e4ae"},"schema_version":"1.0","source":{"id":"1207.2714","kind":"arxiv","version":1}},"canonical_sha256":"8360cd3c6bb6e6127ef660c9f08e813db7e1207067e63edae6ae8494816557e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8360cd3c6bb6e6127ef660c9f08e813db7e1207067e63edae6ae8494816557e3","first_computed_at":"2026-05-18T03:51:14.719401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:51:14.719401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"52WzvnoOimBj2jOCfUwTAzkW9TtBdufbbcRH/E0avN9SMYZdBVvs4VzQBVRXtQo9fKddH4phWpJ1GzVTGLHsDw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:51:14.720041Z","signed_message":"canonical_sha256_bytes"},"source_id":"1207.2714","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d8982a674b7cfe2fab64cdf2c0d624ec500e731e8ac50e454b8ee5ee1cb9ed2","sha256:4d22c8742c2089cf960e3e0c014789e3c49ee51a2bd29e0dd0a25dc1c5eb55ba"],"state_sha256":"07f0c545aa921d0528b630190746dd43ab97cecd1ef3a80410183a3e0a69764d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VG5mS5JnIDG1p+fMZl1bHg2bxTK2f3O7dwbn8lhT1H4UqqGuULu8JFyWt/V0NRfJHOXX6Fuths2Doj1v2ZDuCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T05:24:23.292952Z","bundle_sha256":"d01fa3b60f92d6992f47e28548357fca592838f24a56564d5f56e4f4b7228b97"}}