{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4G564OEMR7WTB6SENQ4PV3C4ZT","short_pith_number":"pith:4G564OEM","canonical_record":{"source":{"id":"2411.06175","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T13:17:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"69963563ecde1b0410411df19bb622d00969ffb4301c07c002e4eb678770a893","abstract_canon_sha256":"d2c72802b31fb536def237b7e57387d40cd0610bb4a77cd5c1a384436d7fa927"},"schema_version":"1.0"},"canonical_sha256":"e1bbee388c8fed30fa446c38faec5cccfa1a674c72f6b1e2f26f0473d0c6d078","source":{"kind":"arxiv","id":"2411.06175","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06175","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06175v3","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06175","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_12","alias_value":"4G564OEMR7WT","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_16","alias_value":"4G564OEMR7WTB6SE","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_8","alias_value":"4G564OEM","created_at":"2026-07-05T09:54:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4G564OEMR7WTB6SENQ4PV3C4ZT","target":"record","payload":{"canonical_record":{"source":{"id":"2411.06175","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T13:17:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"69963563ecde1b0410411df19bb622d00969ffb4301c07c002e4eb678770a893","abstract_canon_sha256":"d2c72802b31fb536def237b7e57387d40cd0610bb4a77cd5c1a384436d7fa927"},"schema_version":"1.0"},"canonical_sha256":"e1bbee388c8fed30fa446c38faec5cccfa1a674c72f6b1e2f26f0473d0c6d078","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:05.586101Z","signature_b64":"AjUYot08smZYcZ1yrsYTe4ZWFSHlMbht+JEptTM+vfQ5QhyxdoLAQjieFieU2HNDSv1ATg6ZwK27cLqnHGoxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1bbee388c8fed30fa446c38faec5cccfa1a674c72f6b1e2f26f0473d0c6d078","last_reissued_at":"2026-07-05T09:54:05.585595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:05.585595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.06175","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:54:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PZeneOGdZ1hd8w5zwV9yFilF6wSMf1eBTc0KDq1TyiU2AhytDagu9GJzdQcg21ZBmV2R1j4pSHPOg4Q/Jpp5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:26:00.022495Z"},"content_sha256":"17cd9a799b340ae3251f93cb4e72ddf24ea9f97f371e1e356cee4e3c5b199c5b","schema_version":"1.0","event_id":"sha256:17cd9a799b340ae3251f93cb4e72ddf24ea9f97f371e1e356cee4e3c5b199c5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4G564OEMR7WTB6SENQ4PV3C4ZT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clustering Algorithms and RAG Enhancing Semi-Supervised Text Classification with Large LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bohong Lin, Jiahao Zeng, Shan Zhong, Yongxin Yu","submitted_at":"2024-11-09T13:17:39Z","abstract_excerpt":"This paper proposes a Clustering, Labeling, then Augmenting framework that significantly enhances performance in Semi-Supervised Text Classification (SSTC) tasks, effectively addressing the challenge of vast datasets with limited labeled examples. Unlike traditional SSTC approaches that rely on a predefined small set of labeled data to generate pseudo-labels for the unlabeled data, this framework innovatively employs clustering to select representative \"landmarks\" for labeling. These landmarks subsequently act as intermediaries in an ensemble of augmentation techniques, including Retrieval-Aug"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06175","kind":"arxiv","version":3},"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/2411.06175/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":"2026-07-05T09:54:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mL0w/EDj0loQFVt3KypFWRrgYmgbpluIXNJgwmUtbNaY4eTWdKaNoCabmdmM/v7FAvkr+qv5R1TNzHOjTFVABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:26:00.023014Z"},"content_sha256":"24fd061916bb20448b9f57078c6b04e244460fb4a6839a0ec696c4ec37a37bfe","schema_version":"1.0","event_id":"sha256:24fd061916bb20448b9f57078c6b04e244460fb4a6839a0ec696c4ec37a37bfe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4G564OEMR7WTB6SENQ4PV3C4ZT/bundle.json","state_url":"https://pith.science/pith/4G564OEMR7WTB6SENQ4PV3C4ZT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4G564OEMR7WTB6SENQ4PV3C4ZT/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":"2026-08-14T19:26:00Z","links":{"resolver":"https://pith.science/pith/4G564OEMR7WTB6SENQ4PV3C4ZT","bundle":"https://pith.science/pith/4G564OEMR7WTB6SENQ4PV3C4ZT/bundle.json","state":"https://pith.science/pith/4G564OEMR7WTB6SENQ4PV3C4ZT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4G564OEMR7WTB6SENQ4PV3C4ZT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4G564OEMR7WTB6SENQ4PV3C4ZT","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":"d2c72802b31fb536def237b7e57387d40cd0610bb4a77cd5c1a384436d7fa927","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T13:17:39Z","title_canon_sha256":"69963563ecde1b0410411df19bb622d00969ffb4301c07c002e4eb678770a893"},"schema_version":"1.0","source":{"id":"2411.06175","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06175","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06175v3","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06175","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_12","alias_value":"4G564OEMR7WT","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_16","alias_value":"4G564OEMR7WTB6SE","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_8","alias_value":"4G564OEM","created_at":"2026-07-05T09:54:05Z"}],"graph_snapshots":[{"event_id":"sha256:24fd061916bb20448b9f57078c6b04e244460fb4a6839a0ec696c4ec37a37bfe","target":"graph","created_at":"2026-07-05T09:54:05Z","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/2411.06175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a Clustering, Labeling, then Augmenting framework that significantly enhances performance in Semi-Supervised Text Classification (SSTC) tasks, effectively addressing the challenge of vast datasets with limited labeled examples. Unlike traditional SSTC approaches that rely on a predefined small set of labeled data to generate pseudo-labels for the unlabeled data, this framework innovatively employs clustering to select representative \"landmarks\" for labeling. These landmarks subsequently act as intermediaries in an ensemble of augmentation techniques, including Retrieval-Aug","authors_text":"Bohong Lin, Jiahao Zeng, Shan Zhong, Yongxin Yu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T13:17:39Z","title":"Clustering Algorithms and RAG Enhancing Semi-Supervised Text Classification with Large LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06175","kind":"arxiv","version":3},"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":"sha256:17cd9a799b340ae3251f93cb4e72ddf24ea9f97f371e1e356cee4e3c5b199c5b","target":"record","created_at":"2026-07-05T09:54:05Z","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":"d2c72802b31fb536def237b7e57387d40cd0610bb4a77cd5c1a384436d7fa927","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T13:17:39Z","title_canon_sha256":"69963563ecde1b0410411df19bb622d00969ffb4301c07c002e4eb678770a893"},"schema_version":"1.0","source":{"id":"2411.06175","kind":"arxiv","version":3}},"canonical_sha256":"e1bbee388c8fed30fa446c38faec5cccfa1a674c72f6b1e2f26f0473d0c6d078","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1bbee388c8fed30fa446c38faec5cccfa1a674c72f6b1e2f26f0473d0c6d078","first_computed_at":"2026-07-05T09:54:05.585595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:05.585595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AjUYot08smZYcZ1yrsYTe4ZWFSHlMbht+JEptTM+vfQ5QhyxdoLAQjieFieU2HNDSv1ATg6ZwK27cLqnHGoxCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:05.586101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.06175","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17cd9a799b340ae3251f93cb4e72ddf24ea9f97f371e1e356cee4e3c5b199c5b","sha256:24fd061916bb20448b9f57078c6b04e244460fb4a6839a0ec696c4ec37a37bfe"],"state_sha256":"a9e0527306b4d47a4c476e073077234b8296c030f5c77235af8a299828b4b0fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kJ5rTy0IoVvYWwDdFjnqpo155oOIP3NRk+jVAnBcnyrryJI4TyJ89OXxhmpTBptmkmKzmXlFBIjrmYpBoftaAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:26:00.044739Z","bundle_sha256":"998620b5a3063e488778d61fd98a836618df33992d9bb575ee9bc937cc5f2097"}}