{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GGBWNSBH4WOKJ3CMUMJESSXQQR","short_pith_number":"pith:GGBWNSBH","canonical_record":{"source":{"id":"2607.28550","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-07-30T17:20:12Z","cross_cats_sorted":[],"title_canon_sha256":"0a0423555d20bc7e244265543c1d71a5d359d81c32db977b20fe529fa6266685","abstract_canon_sha256":"c845fc0d9fa85067ba63aa77b4e97a9a851ce42916a648f75d2bc2c300639f97"},"schema_version":"1.0"},"canonical_sha256":"318366c827e59ca4ec4ca312494af08459ded61c6ecf5e7a12c2af07d5e62413","source":{"kind":"arxiv","id":"2607.28550","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28550","created_at":"2026-07-31T01:38:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28550v1","created_at":"2026-07-31T01:38:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28550","created_at":"2026-07-31T01:38:31Z"},{"alias_kind":"pith_short_12","alias_value":"GGBWNSBH4WOK","created_at":"2026-07-31T01:38:31Z"},{"alias_kind":"pith_short_16","alias_value":"GGBWNSBH4WOKJ3CM","created_at":"2026-07-31T01:38:31Z"},{"alias_kind":"pith_short_8","alias_value":"GGBWNSBH","created_at":"2026-07-31T01:38:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GGBWNSBH4WOKJ3CMUMJESSXQQR","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28550","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-07-30T17:20:12Z","cross_cats_sorted":[],"title_canon_sha256":"0a0423555d20bc7e244265543c1d71a5d359d81c32db977b20fe529fa6266685","abstract_canon_sha256":"c845fc0d9fa85067ba63aa77b4e97a9a851ce42916a648f75d2bc2c300639f97"},"schema_version":"1.0"},"canonical_sha256":"318366c827e59ca4ec4ca312494af08459ded61c6ecf5e7a12c2af07d5e62413","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"318366c827e59ca4ec4ca312494af08459ded61c6ecf5e7a12c2af07d5e62413","last_reissued_at":"2026-07-31T01:38:31.306982Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:38:31.306982Z"},"source_kind":"arxiv","source_id":"2607.28550","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":"2026-07-31T01:38:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HTLWTtLD0WN/2iwBin7E4yLD4xeKWwqzfMdcxiNmtHv3XhFro9pNZ3WzRtVSbv7GwnOmPkc+hA53JQu2vtnDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:26:34.140506Z"},"content_sha256":"cb4bed02b3394381074002b9a61f5098efe7406295edefb2884bf0f86750af1a","schema_version":"1.0","event_id":"sha256:cb4bed02b3394381074002b9a61f5098efe7406295edefb2884bf0f86750af1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GGBWNSBH4WOKJ3CMUMJESSXQQR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Correcting Mode Collapse in Silicon Sampling with Semantic Similarity Rating","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Oscar Heath, Rohan Alexander","submitted_at":"2026-07-30T17:20:12Z","abstract_excerpt":"Silicon sampling refers to the use of Large Language Models (LLMs) to generate responses to surveys. It has shown promise, but tends to generate response distributions with unrealistically low variance. We argue that this mode collapse is due to LLMs failure to generate numeric data, and that text responses may be better suited for this task. We analyze whether Semantic Similarity Rating can improve the fidelity of silicon sampling responses when asked about political attitudes. This method solicits text-only responses from LLMs, then maps this to a numeric scale using text embeddings. We find"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28550","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/2607.28550/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":"2026-07-31T01:38:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hcHm0shKnItWYThPRRQXEG7fcc5FmNva/5Se7Mog+Uq4V38fVazbETBD4aOM/Np35fEWamHBMIKorC2OXZYkDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:26:34.141248Z"},"content_sha256":"11f60b6d5c41d2d6e6b5494a94b5c15e77540a63ce9f788a9118078462a23b19","schema_version":"1.0","event_id":"sha256:11f60b6d5c41d2d6e6b5494a94b5c15e77540a63ce9f788a9118078462a23b19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GGBWNSBH4WOKJ3CMUMJESSXQQR/bundle.json","state_url":"https://pith.science/pith/GGBWNSBH4WOKJ3CMUMJESSXQQR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GGBWNSBH4WOKJ3CMUMJESSXQQR/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":"2026-08-05T17:26:34Z","links":{"resolver":"https://pith.science/pith/GGBWNSBH4WOKJ3CMUMJESSXQQR","bundle":"https://pith.science/pith/GGBWNSBH4WOKJ3CMUMJESSXQQR/bundle.json","state":"https://pith.science/pith/GGBWNSBH4WOKJ3CMUMJESSXQQR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GGBWNSBH4WOKJ3CMUMJESSXQQR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GGBWNSBH4WOKJ3CMUMJESSXQQR","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":"c845fc0d9fa85067ba63aa77b4e97a9a851ce42916a648f75d2bc2c300639f97","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-07-30T17:20:12Z","title_canon_sha256":"0a0423555d20bc7e244265543c1d71a5d359d81c32db977b20fe529fa6266685"},"schema_version":"1.0","source":{"id":"2607.28550","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28550","created_at":"2026-07-31T01:38:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28550v1","created_at":"2026-07-31T01:38:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28550","created_at":"2026-07-31T01:38:31Z"},{"alias_kind":"pith_short_12","alias_value":"GGBWNSBH4WOK","created_at":"2026-07-31T01:38:31Z"},{"alias_kind":"pith_short_16","alias_value":"GGBWNSBH4WOKJ3CM","created_at":"2026-07-31T01:38:31Z"},{"alias_kind":"pith_short_8","alias_value":"GGBWNSBH","created_at":"2026-07-31T01:38:31Z"}],"graph_snapshots":[{"event_id":"sha256:11f60b6d5c41d2d6e6b5494a94b5c15e77540a63ce9f788a9118078462a23b19","target":"graph","created_at":"2026-07-31T01:38:31Z","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/2607.28550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Silicon sampling refers to the use of Large Language Models (LLMs) to generate responses to surveys. It has shown promise, but tends to generate response distributions with unrealistically low variance. We argue that this mode collapse is due to LLMs failure to generate numeric data, and that text responses may be better suited for this task. We analyze whether Semantic Similarity Rating can improve the fidelity of silicon sampling responses when asked about political attitudes. This method solicits text-only responses from LLMs, then maps this to a numeric scale using text embeddings. We find","authors_text":"Oscar Heath, Rohan Alexander","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-07-30T17:20:12Z","title":"Correcting Mode Collapse in Silicon Sampling with Semantic Similarity Rating"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28550","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:cb4bed02b3394381074002b9a61f5098efe7406295edefb2884bf0f86750af1a","target":"record","created_at":"2026-07-31T01:38:31Z","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":"c845fc0d9fa85067ba63aa77b4e97a9a851ce42916a648f75d2bc2c300639f97","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-07-30T17:20:12Z","title_canon_sha256":"0a0423555d20bc7e244265543c1d71a5d359d81c32db977b20fe529fa6266685"},"schema_version":"1.0","source":{"id":"2607.28550","kind":"arxiv","version":1}},"canonical_sha256":"318366c827e59ca4ec4ca312494af08459ded61c6ecf5e7a12c2af07d5e62413","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"318366c827e59ca4ec4ca312494af08459ded61c6ecf5e7a12c2af07d5e62413","first_computed_at":"2026-07-31T01:38:31.306982Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:38:31.306982Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28550","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb4bed02b3394381074002b9a61f5098efe7406295edefb2884bf0f86750af1a","sha256:11f60b6d5c41d2d6e6b5494a94b5c15e77540a63ce9f788a9118078462a23b19"],"state_sha256":"30558ee4efbf56ccfe99a37484aba91a52915b589d4375c3f80a75db6d3e6747"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IceyOTFKoMKK/xmVhRIlrpshk7OVGIaWLZ3hPQ0ECyiuuqrHWoDE01Dsou+lGEDSe5b33x+22beqS8XtHX78CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:26:34.146897Z","bundle_sha256":"a8da526f5c7aece4dd9b015ea45db1b0273a7e2e3d74419a572c707d7587f685"}}