{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4IAT5K5K2XJFZN7MDSCXI4HQS4","short_pith_number":"pith:4IAT5K5K","canonical_record":{"source":{"id":"2510.27313","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-31T09:39:12Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"06c12be2959e34898e5f48374c001627db8975e7f0c042e4a5fb609266d662e7","abstract_canon_sha256":"da886ffb729c7c4ae74b2a723ab9cd41255db8e442fa8181af630bbaff81506d"},"schema_version":"1.0"},"canonical_sha256":"e2013eabaad5d25cb7ec1c857470f0973e37c4972c89981c1d1008dc894cc619","source":{"kind":"arxiv","id":"2510.27313","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.27313","created_at":"2026-08-04T01:58:06Z"},{"alias_kind":"arxiv_version","alias_value":"2510.27313v3","created_at":"2026-08-04T01:58:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.27313","created_at":"2026-08-04T01:58:06Z"},{"alias_kind":"pith_short_12","alias_value":"4IAT5K5K2XJF","created_at":"2026-08-04T01:58:06Z"},{"alias_kind":"pith_short_16","alias_value":"4IAT5K5K2XJFZN7M","created_at":"2026-08-04T01:58:06Z"},{"alias_kind":"pith_short_8","alias_value":"4IAT5K5K","created_at":"2026-08-04T01:58:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4IAT5K5K2XJFZN7MDSCXI4HQS4","target":"record","payload":{"canonical_record":{"source":{"id":"2510.27313","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-31T09:39:12Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"06c12be2959e34898e5f48374c001627db8975e7f0c042e4a5fb609266d662e7","abstract_canon_sha256":"da886ffb729c7c4ae74b2a723ab9cd41255db8e442fa8181af630bbaff81506d"},"schema_version":"1.0"},"canonical_sha256":"e2013eabaad5d25cb7ec1c857470f0973e37c4972c89981c1d1008dc894cc619","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:58:06.818133Z","signature_b64":"a+76g3UWQ8ZIFePFs8PCkLyBC2OjV/uRJJn+YflFwa/XzPnD1nRS5QzrabIF2g6O+GCUh/ep333ePZblKvkxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2013eabaad5d25cb7ec1c857470f0973e37c4972c89981c1d1008dc894cc619","last_reissued_at":"2026-08-04T01:58:06.816587Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:58:06.816587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.27313","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":"2026-08-04T01:58:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"brIcTcXUOBMZYcDbMi46s3tRuYsg2fPZh/YWj71kKTa2BDjaDMyRkkryhqkBKNa6b3vtsQAT2JDtEWUilpv4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:16:28.456077Z"},"content_sha256":"16ada47d0634be066a64035f259e25c63e9ccc528ffe5ca0231d51d026800a45","schema_version":"1.0","event_id":"sha256:16ada47d0634be066a64035f259e25c63e9ccc528ffe5ca0231d51d026800a45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4IAT5K5K2XJFZN7MDSCXI4HQS4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM generation novelty through the lens of semantic similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Ameya Prabhu, Elisa Nguyen, Matthias Bethge, Philipp Davydov, Seong Joon Oh","submitted_at":"2025-10-31T09:39:12Z","abstract_excerpt":"Generation novelty is a key indicator of an LLM's ability to generalize, yet measuring it against full pretraining corpora is computationally challenging. Existing evaluations often rely on lexical overlap, failing to detect paraphrased text, or do not consider the full pretraining corpus. We frame novelty as a semantic retrieval problem. This framing enables us to address novelty with modern embedding and indexing pipelines, allowing for efficient analysis at pre-training scale. Specifically, we propose a three-stage framework that retrieves semantically similar samples, reranks them at varyi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.27313","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/2510.27313/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":"2026-08-04T01:58:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DVzbemjrfoqBuV+DfRAFJXLiSytFOFoaKW1vwqfQvO+vgcPX322ZsFi4tooRlPzHcgWxwpvGr1MDq/TaKRvkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:16:28.456602Z"},"content_sha256":"28a4d2ebb211d8d1e980f05d92750995ac426d444afc6153cc7660e430a289a9","schema_version":"1.0","event_id":"sha256:28a4d2ebb211d8d1e980f05d92750995ac426d444afc6153cc7660e430a289a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4IAT5K5K2XJFZN7MDSCXI4HQS4/bundle.json","state_url":"https://pith.science/pith/4IAT5K5K2XJFZN7MDSCXI4HQS4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4IAT5K5K2XJFZN7MDSCXI4HQS4/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":"2026-08-05T04:16:28Z","links":{"resolver":"https://pith.science/pith/4IAT5K5K2XJFZN7MDSCXI4HQS4","bundle":"https://pith.science/pith/4IAT5K5K2XJFZN7MDSCXI4HQS4/bundle.json","state":"https://pith.science/pith/4IAT5K5K2XJFZN7MDSCXI4HQS4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4IAT5K5K2XJFZN7MDSCXI4HQS4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4IAT5K5K2XJFZN7MDSCXI4HQS4","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":"da886ffb729c7c4ae74b2a723ab9cd41255db8e442fa8181af630bbaff81506d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-31T09:39:12Z","title_canon_sha256":"06c12be2959e34898e5f48374c001627db8975e7f0c042e4a5fb609266d662e7"},"schema_version":"1.0","source":{"id":"2510.27313","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.27313","created_at":"2026-08-04T01:58:06Z"},{"alias_kind":"arxiv_version","alias_value":"2510.27313v3","created_at":"2026-08-04T01:58:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.27313","created_at":"2026-08-04T01:58:06Z"},{"alias_kind":"pith_short_12","alias_value":"4IAT5K5K2XJF","created_at":"2026-08-04T01:58:06Z"},{"alias_kind":"pith_short_16","alias_value":"4IAT5K5K2XJFZN7M","created_at":"2026-08-04T01:58:06Z"},{"alias_kind":"pith_short_8","alias_value":"4IAT5K5K","created_at":"2026-08-04T01:58:06Z"}],"graph_snapshots":[{"event_id":"sha256:28a4d2ebb211d8d1e980f05d92750995ac426d444afc6153cc7660e430a289a9","target":"graph","created_at":"2026-08-04T01:58:06Z","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/2510.27313/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generation novelty is a key indicator of an LLM's ability to generalize, yet measuring it against full pretraining corpora is computationally challenging. Existing evaluations often rely on lexical overlap, failing to detect paraphrased text, or do not consider the full pretraining corpus. We frame novelty as a semantic retrieval problem. This framing enables us to address novelty with modern embedding and indexing pipelines, allowing for efficient analysis at pre-training scale. Specifically, we propose a three-stage framework that retrieves semantically similar samples, reranks them at varyi","authors_text":"Ameya Prabhu, Elisa Nguyen, Matthias Bethge, Philipp Davydov, Seong Joon Oh","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-31T09:39:12Z","title":"LLM generation novelty through the lens of semantic similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.27313","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":"sha256:16ada47d0634be066a64035f259e25c63e9ccc528ffe5ca0231d51d026800a45","target":"record","created_at":"2026-08-04T01:58:06Z","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":"da886ffb729c7c4ae74b2a723ab9cd41255db8e442fa8181af630bbaff81506d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-31T09:39:12Z","title_canon_sha256":"06c12be2959e34898e5f48374c001627db8975e7f0c042e4a5fb609266d662e7"},"schema_version":"1.0","source":{"id":"2510.27313","kind":"arxiv","version":3}},"canonical_sha256":"e2013eabaad5d25cb7ec1c857470f0973e37c4972c89981c1d1008dc894cc619","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2013eabaad5d25cb7ec1c857470f0973e37c4972c89981c1d1008dc894cc619","first_computed_at":"2026-08-04T01:58:06.816587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:58:06.816587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a+76g3UWQ8ZIFePFs8PCkLyBC2OjV/uRJJn+YflFwa/XzPnD1nRS5QzrabIF2g6O+GCUh/ep333ePZblKvkxBw==","signature_status":"signed_v1","signed_at":"2026-08-04T01:58:06.818133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.27313","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16ada47d0634be066a64035f259e25c63e9ccc528ffe5ca0231d51d026800a45","sha256:28a4d2ebb211d8d1e980f05d92750995ac426d444afc6153cc7660e430a289a9"],"state_sha256":"fc3d58374b7982bf902b7c6719169ea09f373abcd810b461f251456d2d892181"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yt1ugdiAcRfPjG50uZ909CEgNyidyBvfm6gNcgROm/zZrGsI7w5XZKvJT0N0LLR3zrUZgGflLZuQXAJLvfTaBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:16:28.463552Z","bundle_sha256":"e001544b79956c0819a17bbf54b8d8e7325e7ec03b06dc067fc409d95c58cf9b"}}