{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7CJNSS7CS6E3WRAOCREHY72ZKD","short_pith_number":"pith:7CJNSS7C","canonical_record":{"source":{"id":"2507.13793","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T10:07:42Z","cross_cats_sorted":[],"title_canon_sha256":"ba1698ff147c156a4937e6b4cec550886e9e953f8e74c21daad79b40bc43b1a1","abstract_canon_sha256":"d259aa77e3dd8c7cc0ea250b72269707b7b09f58169911d49258701f82d316c4"},"schema_version":"1.0"},"canonical_sha256":"f892d94be29789bb440e14487c7f5950e4dd95fbe10d9855a03c1622d1a71e43","source":{"kind":"arxiv","id":"2507.13793","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13793","created_at":"2026-07-05T11:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13793v1","created_at":"2026-07-05T11:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13793","created_at":"2026-07-05T11:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"7CJNSS7CS6E3","created_at":"2026-07-05T11:39:23Z"},{"alias_kind":"pith_short_16","alias_value":"7CJNSS7CS6E3WRAO","created_at":"2026-07-05T11:39:23Z"},{"alias_kind":"pith_short_8","alias_value":"7CJNSS7C","created_at":"2026-07-05T11:39:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7CJNSS7CS6E3WRAOCREHY72ZKD","target":"record","payload":{"canonical_record":{"source":{"id":"2507.13793","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T10:07:42Z","cross_cats_sorted":[],"title_canon_sha256":"ba1698ff147c156a4937e6b4cec550886e9e953f8e74c21daad79b40bc43b1a1","abstract_canon_sha256":"d259aa77e3dd8c7cc0ea250b72269707b7b09f58169911d49258701f82d316c4"},"schema_version":"1.0"},"canonical_sha256":"f892d94be29789bb440e14487c7f5950e4dd95fbe10d9855a03c1622d1a71e43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:23.273910Z","signature_b64":"BS+NoAzl5Rwj+snHCMfMRN+SMp7RcaI+LE8EeTOBzCNO9vMMQH/4sIkbBaxor4IijX7D1mks4F8CoudlI2n/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f892d94be29789bb440e14487c7f5950e4dd95fbe10d9855a03c1622d1a71e43","last_reissued_at":"2026-07-05T11:39:23.273482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:23.273482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.13793","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":"2026-07-05T11:39:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ktN+PYViblQWOBKUzxezZOVgPNKuo79YHUfW9AXpA5gdNUg4B5x+eaJhVHHq5+asG11AAtPVtNNOadGp8koBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:44:43.765908Z"},"content_sha256":"53f246a04e39d7c2bc196ea5f9961b95e82277fece2faa313ab4b18dc832f007","schema_version":"1.0","event_id":"sha256:53f246a04e39d7c2bc196ea5f9961b95e82277fece2faa313ab4b18dc832f007"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7CJNSS7CS6E3WRAOCREHY72ZKD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Enhanced Model-based Approach for Short Text Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Enhao Cheng, Jianhua Yin, Liqiang Nie, Shoujia Zhang, Tian Gan, Xuemeng Song","submitted_at":"2025-07-18T10:07:42Z","abstract_excerpt":"Short text clustering has become increasingly important with the popularity of social media like Twitter, Google+, and Facebook. Existing methods can be broadly categorized into two paradigms: topic model-based approaches and deep representation learning-based approaches. This task is inherently challenging due to the sparse, large-scale, and high-dimensional characteristics of the short text data. Furthermore, the computational intensity required by representation learning significantly increases the running time. To address these issues, we propose a collapsed Gibbs Sampling algorithm for th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13793","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/2507.13793/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":"2026-07-05T11:39:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DbP6dqDo53qhU3fkdSIP4OoiZuLxvpYbPQuwgKpJxmOsGbQuwBHzyz++lIz5YQOqqg8xVLSXfeIFE+2DBWQ/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:44:43.766805Z"},"content_sha256":"b15340d2418e9df7518f38e7b2e7d1c079e8ceb509d683c46053c71f2a71efc7","schema_version":"1.0","event_id":"sha256:b15340d2418e9df7518f38e7b2e7d1c079e8ceb509d683c46053c71f2a71efc7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7CJNSS7CS6E3WRAOCREHY72ZKD/bundle.json","state_url":"https://pith.science/pith/7CJNSS7CS6E3WRAOCREHY72ZKD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7CJNSS7CS6E3WRAOCREHY72ZKD/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":"2026-08-07T15:44:43Z","links":{"resolver":"https://pith.science/pith/7CJNSS7CS6E3WRAOCREHY72ZKD","bundle":"https://pith.science/pith/7CJNSS7CS6E3WRAOCREHY72ZKD/bundle.json","state":"https://pith.science/pith/7CJNSS7CS6E3WRAOCREHY72ZKD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7CJNSS7CS6E3WRAOCREHY72ZKD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7CJNSS7CS6E3WRAOCREHY72ZKD","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":"d259aa77e3dd8c7cc0ea250b72269707b7b09f58169911d49258701f82d316c4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T10:07:42Z","title_canon_sha256":"ba1698ff147c156a4937e6b4cec550886e9e953f8e74c21daad79b40bc43b1a1"},"schema_version":"1.0","source":{"id":"2507.13793","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13793","created_at":"2026-07-05T11:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13793v1","created_at":"2026-07-05T11:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13793","created_at":"2026-07-05T11:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"7CJNSS7CS6E3","created_at":"2026-07-05T11:39:23Z"},{"alias_kind":"pith_short_16","alias_value":"7CJNSS7CS6E3WRAO","created_at":"2026-07-05T11:39:23Z"},{"alias_kind":"pith_short_8","alias_value":"7CJNSS7C","created_at":"2026-07-05T11:39:23Z"}],"graph_snapshots":[{"event_id":"sha256:b15340d2418e9df7518f38e7b2e7d1c079e8ceb509d683c46053c71f2a71efc7","target":"graph","created_at":"2026-07-05T11:39:23Z","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/2507.13793/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Short text clustering has become increasingly important with the popularity of social media like Twitter, Google+, and Facebook. Existing methods can be broadly categorized into two paradigms: topic model-based approaches and deep representation learning-based approaches. This task is inherently challenging due to the sparse, large-scale, and high-dimensional characteristics of the short text data. Furthermore, the computational intensity required by representation learning significantly increases the running time. To address these issues, we propose a collapsed Gibbs Sampling algorithm for th","authors_text":"Enhao Cheng, Jianhua Yin, Liqiang Nie, Shoujia Zhang, Tian Gan, Xuemeng Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T10:07:42Z","title":"An Enhanced Model-based Approach for Short Text Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13793","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":"sha256:53f246a04e39d7c2bc196ea5f9961b95e82277fece2faa313ab4b18dc832f007","target":"record","created_at":"2026-07-05T11:39:23Z","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":"d259aa77e3dd8c7cc0ea250b72269707b7b09f58169911d49258701f82d316c4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T10:07:42Z","title_canon_sha256":"ba1698ff147c156a4937e6b4cec550886e9e953f8e74c21daad79b40bc43b1a1"},"schema_version":"1.0","source":{"id":"2507.13793","kind":"arxiv","version":1}},"canonical_sha256":"f892d94be29789bb440e14487c7f5950e4dd95fbe10d9855a03c1622d1a71e43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f892d94be29789bb440e14487c7f5950e4dd95fbe10d9855a03c1622d1a71e43","first_computed_at":"2026-07-05T11:39:23.273482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:23.273482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BS+NoAzl5Rwj+snHCMfMRN+SMp7RcaI+LE8EeTOBzCNO9vMMQH/4sIkbBaxor4IijX7D1mks4F8CoudlI2n/AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:23.273910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13793","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53f246a04e39d7c2bc196ea5f9961b95e82277fece2faa313ab4b18dc832f007","sha256:b15340d2418e9df7518f38e7b2e7d1c079e8ceb509d683c46053c71f2a71efc7"],"state_sha256":"4da891cf150a6c2fb27cb0de2d3a5108b76013f86e6be8ef5d3a4c971ba29d1c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3dwtL6lqODwb7ThVBBl+cPhvNrgGpQm4TV93GX7vN9xn5LebLvOoT/1xGom7o82a9kVK+srfpf2bqKSzlKAXBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:44:43.775770Z","bundle_sha256":"096fe6097e3b50737c1d858b30af37e530c5ceb2904ce15afd643be9ce324f88"}}