{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:H66K2HBQSMQYPC2QR5IKXYKAVZ","short_pith_number":"pith:H66K2HBQ","canonical_record":{"source":{"id":"2107.00955","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-02T10:38:43Z","cross_cats_sorted":[],"title_canon_sha256":"7ae7599a92a4fd1b3c18028e7c120b9f2aad8272e21bf801298092b3830f373f","abstract_canon_sha256":"31817181499ed9a6ee6312feaa582a6522a3994e196aeb2f7b166402e890ca0b"},"schema_version":"1.0"},"canonical_sha256":"3fbcad1c309321878b508f50abe140ae4eeef023772964e1c995e72e05a7f593","source":{"kind":"arxiv","id":"2107.00955","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.00955","created_at":"2026-07-05T02:54:35Z"},{"alias_kind":"arxiv_version","alias_value":"2107.00955v1","created_at":"2026-07-05T02:54:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00955","created_at":"2026-07-05T02:54:35Z"},{"alias_kind":"pith_short_12","alias_value":"H66K2HBQSMQY","created_at":"2026-07-05T02:54:35Z"},{"alias_kind":"pith_short_16","alias_value":"H66K2HBQSMQYPC2Q","created_at":"2026-07-05T02:54:35Z"},{"alias_kind":"pith_short_8","alias_value":"H66K2HBQ","created_at":"2026-07-05T02:54:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:H66K2HBQSMQYPC2QR5IKXYKAVZ","target":"record","payload":{"canonical_record":{"source":{"id":"2107.00955","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-02T10:38:43Z","cross_cats_sorted":[],"title_canon_sha256":"7ae7599a92a4fd1b3c18028e7c120b9f2aad8272e21bf801298092b3830f373f","abstract_canon_sha256":"31817181499ed9a6ee6312feaa582a6522a3994e196aeb2f7b166402e890ca0b"},"schema_version":"1.0"},"canonical_sha256":"3fbcad1c309321878b508f50abe140ae4eeef023772964e1c995e72e05a7f593","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:35.643504Z","signature_b64":"Zkv04fuQ1lLsghywAZsBf7OFvhBxXdSjAJhWumeAvDdn+BZeGRbgzHBubm2eNh/xTyaygdbXxBuTQKGzPdNCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fbcad1c309321878b508f50abe140ae4eeef023772964e1c995e72e05a7f593","last_reissued_at":"2026-07-05T02:54:35.643116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:35.643116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.00955","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":"2026-07-05T02:54:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8+vWBQ40/1FbIBPZBk+mvNLdLVxeMYq9E5jNqevyVH3T2rBYOj3Pd0ST5N9A0RPgGnaZNeJbLZyYa0LT37qQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:57:13.228146Z"},"content_sha256":"fb928af897db70764e39dd1750f813b2852621b6749ea0d945dc26a1347cb7a4","schema_version":"1.0","event_id":"sha256:fb928af897db70764e39dd1750f813b2852621b6749ea0d945dc26a1347cb7a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:H66K2HBQSMQYPC2QR5IKXYKAVZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Concept Identification of Directly and Indirectly Related Mentions Referring to Groups of Persons","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anastasia Zhukova, Bela Gipp, Felix Hamborg, Karsten Donnay","submitted_at":"2021-07-02T10:38:43Z","abstract_excerpt":"Unsupervised concept identification through clustering, i.e., identification of semantically related words and phrases, is a common approach to identify contextual primitives employed in various use cases, e.g., text dimension reduction, i.e., replace words with the concepts to reduce the vocabulary size, summarization, and named entity resolution. We demonstrate the first results of an unsupervised approach for the identification of groups of persons as actors extracted from a set of related articles. Specifically, the approach clusters mentions of groups of persons that act as non-named enti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00955","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/2107.00955/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":"2026-07-05T02:54:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EzaTCPV609nb89+73Wa9F0HNwOdzGafTqTeLQm1xr2p7hMA5A6Psf8cJbniZ7Xqw67Hmm2pPTcSyDoXEKqNvDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:57:13.228546Z"},"content_sha256":"750cc0e119ce1c7b5fdd1557131e521e50e4f2014fe186200b8ca5426fe6c64e","schema_version":"1.0","event_id":"sha256:750cc0e119ce1c7b5fdd1557131e521e50e4f2014fe186200b8ca5426fe6c64e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H66K2HBQSMQYPC2QR5IKXYKAVZ/bundle.json","state_url":"https://pith.science/pith/H66K2HBQSMQYPC2QR5IKXYKAVZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H66K2HBQSMQYPC2QR5IKXYKAVZ/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":"2026-07-07T07:57:13Z","links":{"resolver":"https://pith.science/pith/H66K2HBQSMQYPC2QR5IKXYKAVZ","bundle":"https://pith.science/pith/H66K2HBQSMQYPC2QR5IKXYKAVZ/bundle.json","state":"https://pith.science/pith/H66K2HBQSMQYPC2QR5IKXYKAVZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H66K2HBQSMQYPC2QR5IKXYKAVZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:H66K2HBQSMQYPC2QR5IKXYKAVZ","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":"31817181499ed9a6ee6312feaa582a6522a3994e196aeb2f7b166402e890ca0b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-02T10:38:43Z","title_canon_sha256":"7ae7599a92a4fd1b3c18028e7c120b9f2aad8272e21bf801298092b3830f373f"},"schema_version":"1.0","source":{"id":"2107.00955","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.00955","created_at":"2026-07-05T02:54:35Z"},{"alias_kind":"arxiv_version","alias_value":"2107.00955v1","created_at":"2026-07-05T02:54:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00955","created_at":"2026-07-05T02:54:35Z"},{"alias_kind":"pith_short_12","alias_value":"H66K2HBQSMQY","created_at":"2026-07-05T02:54:35Z"},{"alias_kind":"pith_short_16","alias_value":"H66K2HBQSMQYPC2Q","created_at":"2026-07-05T02:54:35Z"},{"alias_kind":"pith_short_8","alias_value":"H66K2HBQ","created_at":"2026-07-05T02:54:35Z"}],"graph_snapshots":[{"event_id":"sha256:750cc0e119ce1c7b5fdd1557131e521e50e4f2014fe186200b8ca5426fe6c64e","target":"graph","created_at":"2026-07-05T02:54:35Z","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/2107.00955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised concept identification through clustering, i.e., identification of semantically related words and phrases, is a common approach to identify contextual primitives employed in various use cases, e.g., text dimension reduction, i.e., replace words with the concepts to reduce the vocabulary size, summarization, and named entity resolution. We demonstrate the first results of an unsupervised approach for the identification of groups of persons as actors extracted from a set of related articles. Specifically, the approach clusters mentions of groups of persons that act as non-named enti","authors_text":"Anastasia Zhukova, Bela Gipp, Felix Hamborg, Karsten Donnay","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-02T10:38:43Z","title":"Concept Identification of Directly and Indirectly Related Mentions Referring to Groups of Persons"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00955","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:fb928af897db70764e39dd1750f813b2852621b6749ea0d945dc26a1347cb7a4","target":"record","created_at":"2026-07-05T02:54:35Z","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":"31817181499ed9a6ee6312feaa582a6522a3994e196aeb2f7b166402e890ca0b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-02T10:38:43Z","title_canon_sha256":"7ae7599a92a4fd1b3c18028e7c120b9f2aad8272e21bf801298092b3830f373f"},"schema_version":"1.0","source":{"id":"2107.00955","kind":"arxiv","version":1}},"canonical_sha256":"3fbcad1c309321878b508f50abe140ae4eeef023772964e1c995e72e05a7f593","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fbcad1c309321878b508f50abe140ae4eeef023772964e1c995e72e05a7f593","first_computed_at":"2026-07-05T02:54:35.643116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:54:35.643116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zkv04fuQ1lLsghywAZsBf7OFvhBxXdSjAJhWumeAvDdn+BZeGRbgzHBubm2eNh/xTyaygdbXxBuTQKGzPdNCBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:54:35.643504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.00955","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb928af897db70764e39dd1750f813b2852621b6749ea0d945dc26a1347cb7a4","sha256:750cc0e119ce1c7b5fdd1557131e521e50e4f2014fe186200b8ca5426fe6c64e"],"state_sha256":"efacf8342af7d4540cd428742c855f9fe211a4ff94e9b709e051a704880d075b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cRc2QlrZ48ofimI/fT8E0xm5x4ZIxoYe3OzLP8PZE8FDzFq/iv8a8B0bWE089E8IgiFT+0g56o6L8JCl20V4CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:57:13.230458Z","bundle_sha256":"7c2e2dd5b15ef1bf4ac59800d1be85bd834d9e81de06bddbf6290550b2adde55"}}