{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Y57MRET3NST3BH23BP2L5LHSKF","short_pith_number":"pith:Y57MRET3","canonical_record":{"source":{"id":"2510.01171","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-01T17:55:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"07dbe66f0f4c1b8c84864a51b18b4fb86acce9974162b034b4979bef85e0dc82","abstract_canon_sha256":"f2fc1b8c53bd3458030fc924bd90c04abe5207a61afd66868350f9755a1c519d"},"schema_version":"1.0"},"canonical_sha256":"c77ec8927b6ca7b09f5b0bf4beacf25163cca468a563d4c5513b01955079e0a6","source":{"kind":"arxiv","id":"2510.01171","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.01171","created_at":"2026-07-17T00:20:41Z"},{"alias_kind":"arxiv_version","alias_value":"2510.01171v4","created_at":"2026-07-17T00:20:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01171","created_at":"2026-07-17T00:20:41Z"},{"alias_kind":"pith_short_12","alias_value":"Y57MRET3NST3","created_at":"2026-07-17T00:20:41Z"},{"alias_kind":"pith_short_16","alias_value":"Y57MRET3NST3BH23","created_at":"2026-07-17T00:20:41Z"},{"alias_kind":"pith_short_8","alias_value":"Y57MRET3","created_at":"2026-07-17T00:20:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Y57MRET3NST3BH23BP2L5LHSKF","target":"record","payload":{"canonical_record":{"source":{"id":"2510.01171","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-01T17:55:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"07dbe66f0f4c1b8c84864a51b18b4fb86acce9974162b034b4979bef85e0dc82","abstract_canon_sha256":"f2fc1b8c53bd3458030fc924bd90c04abe5207a61afd66868350f9755a1c519d"},"schema_version":"1.0"},"canonical_sha256":"c77ec8927b6ca7b09f5b0bf4beacf25163cca468a563d4c5513b01955079e0a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:20:41.119042Z","signature_b64":"OC9pJqynPaEE46JSCRXyg8AQamI3dAXJmAA0ubkUs7uzomV4xIuNMevHM9sPP6jVO48ZmDb46E/0hAEZv+ojCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c77ec8927b6ca7b09f5b0bf4beacf25163cca468a563d4c5513b01955079e0a6","last_reissued_at":"2026-07-17T00:20:41.117999Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:20:41.117999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.01171","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-17T00:20:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"32VB1RDHN4UV7+9CzbxSHWtc2faLe/tyEi8IuQAzS07xeQkHMEuZxO7SoNXq2i5PTIAxjAxCH9djXMkdUaL1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T06:19:56.121296Z"},"content_sha256":"748bee7912ecccd69281059338c60582f4a8c4ad75f5c77478ed1c3dcc421f51","schema_version":"1.0","event_id":"sha256:748bee7912ecccd69281059338c60582f4a8c4ad75f5c77478ed1c3dcc421f51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Y57MRET3NST3BH23BP2L5LHSKF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anthony Sicilia, Christopher D. Manning, Derek Chong, Jiayi Zhang, Michael R. Tomz, Simon Yu, Weiyan Shi","submitted_at":"2025-10-01T17:55:37Z","abstract_excerpt":"Post-training alignment often reduces LLM diversity, leading to a phenomenon known as mode collapse. Unlike prior work that attributes this effect to algorithmic limitations, we identify a fundamental, pervasive data-level driver: typicality bias in preference data, whereby annotators systematically favor familiar text as a result of well-established findings in cognitive psychology. We formalize this bias theoretically, verify it on preference datasets empirically, and show that it plays a central role in mode collapse. Motivated by this analysis, we introduce Verbalized Sampling, a simple, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.01171","kind":"arxiv","version":4},"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/2510.01171/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":"2026-07-17T00:20:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sG4ayMfgGWw0jQbaBEOm0FSbcALx/jc9Ebu4lJ6OmD+VrhWa/QhM2mS58alIEIVxMO5oTF5nwL8j+EBPeseQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T06:19:56.122033Z"},"content_sha256":"8c53d7f5a8f91fcab21ac6f11257fdbd86ebd3d5eb22651ea0036567c421ead4","schema_version":"1.0","event_id":"sha256:8c53d7f5a8f91fcab21ac6f11257fdbd86ebd3d5eb22651ea0036567c421ead4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y57MRET3NST3BH23BP2L5LHSKF/bundle.json","state_url":"https://pith.science/pith/Y57MRET3NST3BH23BP2L5LHSKF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y57MRET3NST3BH23BP2L5LHSKF/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":"2026-07-28T06:19:56Z","links":{"resolver":"https://pith.science/pith/Y57MRET3NST3BH23BP2L5LHSKF","bundle":"https://pith.science/pith/Y57MRET3NST3BH23BP2L5LHSKF/bundle.json","state":"https://pith.science/pith/Y57MRET3NST3BH23BP2L5LHSKF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y57MRET3NST3BH23BP2L5LHSKF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y57MRET3NST3BH23BP2L5LHSKF","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":"f2fc1b8c53bd3458030fc924bd90c04abe5207a61afd66868350f9755a1c519d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-01T17:55:37Z","title_canon_sha256":"07dbe66f0f4c1b8c84864a51b18b4fb86acce9974162b034b4979bef85e0dc82"},"schema_version":"1.0","source":{"id":"2510.01171","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.01171","created_at":"2026-07-17T00:20:41Z"},{"alias_kind":"arxiv_version","alias_value":"2510.01171v4","created_at":"2026-07-17T00:20:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01171","created_at":"2026-07-17T00:20:41Z"},{"alias_kind":"pith_short_12","alias_value":"Y57MRET3NST3","created_at":"2026-07-17T00:20:41Z"},{"alias_kind":"pith_short_16","alias_value":"Y57MRET3NST3BH23","created_at":"2026-07-17T00:20:41Z"},{"alias_kind":"pith_short_8","alias_value":"Y57MRET3","created_at":"2026-07-17T00:20:41Z"}],"graph_snapshots":[{"event_id":"sha256:8c53d7f5a8f91fcab21ac6f11257fdbd86ebd3d5eb22651ea0036567c421ead4","target":"graph","created_at":"2026-07-17T00:20:41Z","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/2510.01171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training alignment often reduces LLM diversity, leading to a phenomenon known as mode collapse. Unlike prior work that attributes this effect to algorithmic limitations, we identify a fundamental, pervasive data-level driver: typicality bias in preference data, whereby annotators systematically favor familiar text as a result of well-established findings in cognitive psychology. We formalize this bias theoretically, verify it on preference datasets empirically, and show that it plays a central role in mode collapse. Motivated by this analysis, we introduce Verbalized Sampling, a simple, t","authors_text":"Anthony Sicilia, Christopher D. Manning, Derek Chong, Jiayi Zhang, Michael R. Tomz, Simon Yu, Weiyan Shi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-01T17:55:37Z","title":"Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.01171","kind":"arxiv","version":4},"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":"sha256:748bee7912ecccd69281059338c60582f4a8c4ad75f5c77478ed1c3dcc421f51","target":"record","created_at":"2026-07-17T00:20:41Z","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":"f2fc1b8c53bd3458030fc924bd90c04abe5207a61afd66868350f9755a1c519d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-01T17:55:37Z","title_canon_sha256":"07dbe66f0f4c1b8c84864a51b18b4fb86acce9974162b034b4979bef85e0dc82"},"schema_version":"1.0","source":{"id":"2510.01171","kind":"arxiv","version":4}},"canonical_sha256":"c77ec8927b6ca7b09f5b0bf4beacf25163cca468a563d4c5513b01955079e0a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c77ec8927b6ca7b09f5b0bf4beacf25163cca468a563d4c5513b01955079e0a6","first_computed_at":"2026-07-17T00:20:41.117999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T00:20:41.117999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OC9pJqynPaEE46JSCRXyg8AQamI3dAXJmAA0ubkUs7uzomV4xIuNMevHM9sPP6jVO48ZmDb46E/0hAEZv+ojCg==","signature_status":"signed_v1","signed_at":"2026-07-17T00:20:41.119042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.01171","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:748bee7912ecccd69281059338c60582f4a8c4ad75f5c77478ed1c3dcc421f51","sha256:8c53d7f5a8f91fcab21ac6f11257fdbd86ebd3d5eb22651ea0036567c421ead4"],"state_sha256":"9cf1f3785b80dbbd45032f519c5e148a146f2ebc58b055d766f4b9e94bbdc6df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uprtKBYh2c3r8PQrzpkqhGBZc/ejjyXjBTM7EblnkLqwfM9PTETxi/s1OO63ITFxIgujFlFsFuuliTSAZ+XQBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-28T06:19:56.124225Z","bundle_sha256":"d6dd0f62080f2bc1f484983884a33800e08ed66df60cf546ee5a858076314114"}}