{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:E4YXNZCRI7IV4OI6K3PQZ5FNDO","short_pith_number":"pith:E4YXNZCR","canonical_record":{"source":{"id":"1606.03561","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-06-11T06:52:18Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"010778a638e4862eb8b0b363016acf8c2958acd6347be394e540172d5dbadebf","abstract_canon_sha256":"06f0d13168b67a11e4e78cc0b5ba0325c93bba773e1bd77f6965eb0a8c13817e"},"schema_version":"1.0"},"canonical_sha256":"273176e45147d15e391e56df0cf4ad1b9df2dfa83dd134f136be5ef14966c797","source":{"kind":"arxiv","id":"1606.03561","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.03561","created_at":"2026-05-18T01:12:33Z"},{"alias_kind":"arxiv_version","alias_value":"1606.03561v1","created_at":"2026-05-18T01:12:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.03561","created_at":"2026-05-18T01:12:33Z"},{"alias_kind":"pith_short_12","alias_value":"E4YXNZCRI7IV","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"E4YXNZCRI7IV4OI6","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"E4YXNZCR","created_at":"2026-05-18T12:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:E4YXNZCRI7IV4OI6K3PQZ5FNDO","target":"record","payload":{"canonical_record":{"source":{"id":"1606.03561","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-06-11T06:52:18Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"010778a638e4862eb8b0b363016acf8c2958acd6347be394e540172d5dbadebf","abstract_canon_sha256":"06f0d13168b67a11e4e78cc0b5ba0325c93bba773e1bd77f6965eb0a8c13817e"},"schema_version":"1.0"},"canonical_sha256":"273176e45147d15e391e56df0cf4ad1b9df2dfa83dd134f136be5ef14966c797","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:33.673231Z","signature_b64":"v1UWanfIV9hlH4LO3/njDLmpAR8WjD1Z3ZvOZc6iu7BWe1DAXXlOZlegzsq6ZRdIr0JDSBzNPYUYYhhNZ/6+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"273176e45147d15e391e56df0cf4ad1b9df2dfa83dd134f136be5ef14966c797","last_reissued_at":"2026-05-18T01:12:33.672765Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:33.672765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.03561","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":"2026-05-18T01:12:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FuRkANSIcjluyjZnEN3hTcXnkZVqesycr+PxEKXnSM4nlbPeEj1j6JxBykJICQ9tdQ9PNzTl8ZDSg543vvBvDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:22:31.459153Z"},"content_sha256":"a57db03b085addb996dde8ae1bad88b40db3458e7cd776a4a4af8cef468c8634","schema_version":"1.0","event_id":"sha256:a57db03b085addb996dde8ae1bad88b40db3458e7cd776a4a4af8cef468c8634"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:E4YXNZCRI7IV4OI6K3PQZ5FNDO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sub-Story Detection in Twitter with Hierarchical Dirichlet Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.IR","authors_text":"Daniel Preotiuc-Pietro, Kalina Bontcheva, Mark Hepple, P. K. Srijith","submitted_at":"2016-06-11T06:52:18Z","abstract_excerpt":"Social media has now become the de facto information source on real world events. The challenge, however, due to the high volume and velocity nature of social media streams, is in how to follow all posts pertaining to a given event over time, a task referred to as story detection. Moreover, there are often several different stories pertaining to a given event, which we refer to as sub-stories and the corresponding task of their automatic detection as sub-story detection. This paper proposes hierarchical Dirichlet processes (HDP), a probabilistic topic model, as an effective method for automati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.03561","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":"2026-05-18T01:12:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pT2ha1RPoTonD0IOxCO2miH3tmJOUKb12TioSRVHlVz7AIRL758O3Fvbm9FIaqZPfHy0rjR+0I2p8Ll4iWK/DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:22:31.459821Z"},"content_sha256":"e3493a605a34c5c43ecff4d069e0fd89c99d96c9f7075accadd651b612b7834a","schema_version":"1.0","event_id":"sha256:e3493a605a34c5c43ecff4d069e0fd89c99d96c9f7075accadd651b612b7834a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E4YXNZCRI7IV4OI6K3PQZ5FNDO/bundle.json","state_url":"https://pith.science/pith/E4YXNZCRI7IV4OI6K3PQZ5FNDO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E4YXNZCRI7IV4OI6K3PQZ5FNDO/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":"2026-05-30T17:22:31Z","links":{"resolver":"https://pith.science/pith/E4YXNZCRI7IV4OI6K3PQZ5FNDO","bundle":"https://pith.science/pith/E4YXNZCRI7IV4OI6K3PQZ5FNDO/bundle.json","state":"https://pith.science/pith/E4YXNZCRI7IV4OI6K3PQZ5FNDO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E4YXNZCRI7IV4OI6K3PQZ5FNDO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:E4YXNZCRI7IV4OI6K3PQZ5FNDO","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":"06f0d13168b67a11e4e78cc0b5ba0325c93bba773e1bd77f6965eb0a8c13817e","cross_cats_sorted":["cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-06-11T06:52:18Z","title_canon_sha256":"010778a638e4862eb8b0b363016acf8c2958acd6347be394e540172d5dbadebf"},"schema_version":"1.0","source":{"id":"1606.03561","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.03561","created_at":"2026-05-18T01:12:33Z"},{"alias_kind":"arxiv_version","alias_value":"1606.03561v1","created_at":"2026-05-18T01:12:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.03561","created_at":"2026-05-18T01:12:33Z"},{"alias_kind":"pith_short_12","alias_value":"E4YXNZCRI7IV","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"E4YXNZCRI7IV4OI6","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"E4YXNZCR","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:e3493a605a34c5c43ecff4d069e0fd89c99d96c9f7075accadd651b612b7834a","target":"graph","created_at":"2026-05-18T01:12:33Z","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":"Social media has now become the de facto information source on real world events. The challenge, however, due to the high volume and velocity nature of social media streams, is in how to follow all posts pertaining to a given event over time, a task referred to as story detection. Moreover, there are often several different stories pertaining to a given event, which we refer to as sub-stories and the corresponding task of their automatic detection as sub-story detection. This paper proposes hierarchical Dirichlet processes (HDP), a probabilistic topic model, as an effective method for automati","authors_text":"Daniel Preotiuc-Pietro, Kalina Bontcheva, Mark Hepple, P. K. Srijith","cross_cats":["cs.SI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-06-11T06:52:18Z","title":"Sub-Story Detection in Twitter with Hierarchical Dirichlet Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.03561","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:a57db03b085addb996dde8ae1bad88b40db3458e7cd776a4a4af8cef468c8634","target":"record","created_at":"2026-05-18T01:12:33Z","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":"06f0d13168b67a11e4e78cc0b5ba0325c93bba773e1bd77f6965eb0a8c13817e","cross_cats_sorted":["cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-06-11T06:52:18Z","title_canon_sha256":"010778a638e4862eb8b0b363016acf8c2958acd6347be394e540172d5dbadebf"},"schema_version":"1.0","source":{"id":"1606.03561","kind":"arxiv","version":1}},"canonical_sha256":"273176e45147d15e391e56df0cf4ad1b9df2dfa83dd134f136be5ef14966c797","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"273176e45147d15e391e56df0cf4ad1b9df2dfa83dd134f136be5ef14966c797","first_computed_at":"2026-05-18T01:12:33.672765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:33.672765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v1UWanfIV9hlH4LO3/njDLmpAR8WjD1Z3ZvOZc6iu7BWe1DAXXlOZlegzsq6ZRdIr0JDSBzNPYUYYhhNZ/6+CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:33.673231Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.03561","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a57db03b085addb996dde8ae1bad88b40db3458e7cd776a4a4af8cef468c8634","sha256:e3493a605a34c5c43ecff4d069e0fd89c99d96c9f7075accadd651b612b7834a"],"state_sha256":"b3fb16ef40afef3f0c4d1fa856e9fe6d0c78627ea9499eaababd8b649e86c620"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QiViETuEue2Gcw5Qc95AIDcPta9GbXFN0dfOCBxsCsuuXUB5mNHXbQucmHlJE5MBxtN3Y+Tqg10x5GIXwv7LCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T17:22:31.463117Z","bundle_sha256":"8af4479677faf9fac44a409a090314e4919357ccbd650e5bfdd340a082297305"}}