{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FQJRVHDV5IS35XKYFNN3F3NAOV","short_pith_number":"pith:FQJRVHDV","canonical_record":{"source":{"id":"2311.09335","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T19:49:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1cf32370918bfe5196d3088b9065e79cf138bbe908697aeeb45e50f853208aa6","abstract_canon_sha256":"6ac294b9d1453c6709f290f76add5ea5a7f4141ab42d7e8e336bc537a3155e86"},"schema_version":"1.0"},"canonical_sha256":"2c131a9c75ea25bedd582b5bb2eda07554131d92063ccc3d6b0e949931332b11","source":{"kind":"arxiv","id":"2311.09335","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09335","created_at":"2026-07-05T09:25:36Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09335v3","created_at":"2026-07-05T09:25:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09335","created_at":"2026-07-05T09:25:36Z"},{"alias_kind":"pith_short_12","alias_value":"FQJRVHDV5IS3","created_at":"2026-07-05T09:25:36Z"},{"alias_kind":"pith_short_16","alias_value":"FQJRVHDV5IS35XKY","created_at":"2026-07-05T09:25:36Z"},{"alias_kind":"pith_short_8","alias_value":"FQJRVHDV","created_at":"2026-07-05T09:25:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FQJRVHDV5IS35XKYFNN3F3NAOV","target":"record","payload":{"canonical_record":{"source":{"id":"2311.09335","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T19:49:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1cf32370918bfe5196d3088b9065e79cf138bbe908697aeeb45e50f853208aa6","abstract_canon_sha256":"6ac294b9d1453c6709f290f76add5ea5a7f4141ab42d7e8e336bc537a3155e86"},"schema_version":"1.0"},"canonical_sha256":"2c131a9c75ea25bedd582b5bb2eda07554131d92063ccc3d6b0e949931332b11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:36.101904Z","signature_b64":"sTPtMNUj4SweXDMdS8ujo5cIrYqcfAqliIc35iIMIVoRhvy54wXYjdLWA9wyNFt+XfD/ug7P5NquaK5VNB+WCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c131a9c75ea25bedd582b5bb2eda07554131d92063ccc3d6b0e949931332b11","last_reissued_at":"2026-07-05T09:25:36.101456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:36.101456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.09335","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":"2026-07-05T09:25:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JRyOUcpZ4EuIH63EfjrkVKNP/Dxa2EtNgeWUASyUIhAdBGXAM+gvz14WYIWWsZAIno90JdPqUufBSsmGga+DDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:06:16.276786Z"},"content_sha256":"feb1151c726250b4834230cb55d88160ef66394803d2bc31d73879c124ca5601","schema_version":"1.0","event_id":"sha256:feb1151c726250b4834230cb55d88160ef66394803d2bc31d73879c124ca5601"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FQJRVHDV5IS35XKYFNN3F3NAOV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"George Chrysostomou, Miles Williams, Nikolaos Aletras, Zhixue Zhao","submitted_at":"2023-11-15T19:49:24Z","abstract_excerpt":"Despite the remarkable performance of generative large language models (LLMs) on abstractive summarization, they face two significant challenges: their considerable size and tendency to hallucinate. Hallucinations are concerning because they erode reliability and raise safety issues. Pruning is a technique that reduces model size by removing redundant weights, enabling more efficient sparse inference. Pruned models yield downstream task performance comparable to the original, making them ideal alternatives when operating on a limited budget. However, the effect that pruning has upon hallucinat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09335","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/2311.09335/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":"2026-07-05T09:25:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vfme4lWxlSy97keNyoiOf1HYwY24ymFq05fTr4dQi3usAuH1lF/dHT7nStQxeNZW8nj8kt3OiZRpfjN4gTOTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:06:16.277291Z"},"content_sha256":"069e0d8b06cc5f5b49bd6e876c69f05bced1d700750b4aa4c5daa958e64219b6","schema_version":"1.0","event_id":"sha256:069e0d8b06cc5f5b49bd6e876c69f05bced1d700750b4aa4c5daa958e64219b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FQJRVHDV5IS35XKYFNN3F3NAOV/bundle.json","state_url":"https://pith.science/pith/FQJRVHDV5IS35XKYFNN3F3NAOV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FQJRVHDV5IS35XKYFNN3F3NAOV/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":"2026-08-01T05:06:16Z","links":{"resolver":"https://pith.science/pith/FQJRVHDV5IS35XKYFNN3F3NAOV","bundle":"https://pith.science/pith/FQJRVHDV5IS35XKYFNN3F3NAOV/bundle.json","state":"https://pith.science/pith/FQJRVHDV5IS35XKYFNN3F3NAOV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FQJRVHDV5IS35XKYFNN3F3NAOV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FQJRVHDV5IS35XKYFNN3F3NAOV","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":"6ac294b9d1453c6709f290f76add5ea5a7f4141ab42d7e8e336bc537a3155e86","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T19:49:24Z","title_canon_sha256":"1cf32370918bfe5196d3088b9065e79cf138bbe908697aeeb45e50f853208aa6"},"schema_version":"1.0","source":{"id":"2311.09335","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09335","created_at":"2026-07-05T09:25:36Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09335v3","created_at":"2026-07-05T09:25:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09335","created_at":"2026-07-05T09:25:36Z"},{"alias_kind":"pith_short_12","alias_value":"FQJRVHDV5IS3","created_at":"2026-07-05T09:25:36Z"},{"alias_kind":"pith_short_16","alias_value":"FQJRVHDV5IS35XKY","created_at":"2026-07-05T09:25:36Z"},{"alias_kind":"pith_short_8","alias_value":"FQJRVHDV","created_at":"2026-07-05T09:25:36Z"}],"graph_snapshots":[{"event_id":"sha256:069e0d8b06cc5f5b49bd6e876c69f05bced1d700750b4aa4c5daa958e64219b6","target":"graph","created_at":"2026-07-05T09:25:36Z","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/2311.09335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the remarkable performance of generative large language models (LLMs) on abstractive summarization, they face two significant challenges: their considerable size and tendency to hallucinate. Hallucinations are concerning because they erode reliability and raise safety issues. Pruning is a technique that reduces model size by removing redundant weights, enabling more efficient sparse inference. Pruned models yield downstream task performance comparable to the original, making them ideal alternatives when operating on a limited budget. However, the effect that pruning has upon hallucinat","authors_text":"George Chrysostomou, Miles Williams, Nikolaos Aletras, Zhixue Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T19:49:24Z","title":"Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09335","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:feb1151c726250b4834230cb55d88160ef66394803d2bc31d73879c124ca5601","target":"record","created_at":"2026-07-05T09:25:36Z","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":"6ac294b9d1453c6709f290f76add5ea5a7f4141ab42d7e8e336bc537a3155e86","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T19:49:24Z","title_canon_sha256":"1cf32370918bfe5196d3088b9065e79cf138bbe908697aeeb45e50f853208aa6"},"schema_version":"1.0","source":{"id":"2311.09335","kind":"arxiv","version":3}},"canonical_sha256":"2c131a9c75ea25bedd582b5bb2eda07554131d92063ccc3d6b0e949931332b11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c131a9c75ea25bedd582b5bb2eda07554131d92063ccc3d6b0e949931332b11","first_computed_at":"2026-07-05T09:25:36.101456Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:36.101456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sTPtMNUj4SweXDMdS8ujo5cIrYqcfAqliIc35iIMIVoRhvy54wXYjdLWA9wyNFt+XfD/ug7P5NquaK5VNB+WCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:36.101904Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09335","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:feb1151c726250b4834230cb55d88160ef66394803d2bc31d73879c124ca5601","sha256:069e0d8b06cc5f5b49bd6e876c69f05bced1d700750b4aa4c5daa958e64219b6"],"state_sha256":"e35bcc85d2e2d0f96678393f8880ba333152d9c4f946ba4827a3b2f54dda300f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Madr/+CBTMucK3oeaZRxuFsAxPOd/PJtsbO/iNL2Twror+Ypdc9Yd0H28TpjwMDPloMT1DVmzCRQrLO5oigOAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T05:06:16.280776Z","bundle_sha256":"d1bd5681f8ea30c0ea5f32feab425704f7195951a0507b93fd5a03119f5fa3d2"}}