{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2U76SUX6LOSEK73JE2TZ47VD6X","short_pith_number":"pith:2U76SUX6","canonical_record":{"source":{"id":"2501.18101","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-30T02:47:41Z","cross_cats_sorted":[],"title_canon_sha256":"d1850248818cb538af8d424f06734bafd74a9c59b0f8c2741782e83cef31fb6d","abstract_canon_sha256":"8e30e158f5e6a53ef6b16677459a42e738e015b04da7ddbeb1a1e76c086d2154"},"schema_version":"1.0"},"canonical_sha256":"d53fe952fe5ba4457f6926a79e7ea3f5f95378d05642d3fc751ec91b9554639d","source":{"kind":"arxiv","id":"2501.18101","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18101","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18101v4","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18101","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"pith_short_12","alias_value":"2U76SUX6LOSE","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"pith_short_16","alias_value":"2U76SUX6LOSEK73J","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"pith_short_8","alias_value":"2U76SUX6","created_at":"2026-07-05T11:07:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2U76SUX6LOSEK73JE2TZ47VD6X","target":"record","payload":{"canonical_record":{"source":{"id":"2501.18101","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-30T02:47:41Z","cross_cats_sorted":[],"title_canon_sha256":"d1850248818cb538af8d424f06734bafd74a9c59b0f8c2741782e83cef31fb6d","abstract_canon_sha256":"8e30e158f5e6a53ef6b16677459a42e738e015b04da7ddbeb1a1e76c086d2154"},"schema_version":"1.0"},"canonical_sha256":"d53fe952fe5ba4457f6926a79e7ea3f5f95378d05642d3fc751ec91b9554639d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:19.782076Z","signature_b64":"YljY9jqTuu+v8scWM0quwfLOqo2oRVOjQPJufhJ2coZUps4ZRCRcLo2tuRqdvOjdcjWb1l1gc7TG09l9vo4wBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d53fe952fe5ba4457f6926a79e7ea3f5f95378d05642d3fc751ec91b9554639d","last_reissued_at":"2026-07-05T11:07:19.781572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:19.781572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.18101","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":"2026-07-05T11:07:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vHsxF+Md1ZVMWl0E8Lr0lYbFikDwvS1Hx54TJ2/cEkXuxAkZKQVkjvzON2tsIfy7lnlA2oWEtE3mjageus+aDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:29:33.598764Z"},"content_sha256":"d900a8de4d8e0b7ca94fc00a7ed042388b2dbc8e72a81435b24b0086d89e528e","schema_version":"1.0","event_id":"sha256:d900a8de4d8e0b7ca94fc00a7ed042388b2dbc8e72a81435b24b0086d89e528e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2U76SUX6LOSEK73JE2TZ47VD6X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diverse Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angelica Chen, Ilia Kulikov, Jack Lanchantin, Jason Weston, Ping Yu, Sainbayar Sukhbaatar, Shehzaad Dhuliawala","submitted_at":"2025-01-30T02:47:41Z","abstract_excerpt":"Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated responses. This is particularly a problem for creative generative tasks where varied responses are desired. In this work we introduce Diverse Preference Optimization (DivPO), an optimization method which learns to generate much more diverse responses than standard pipelines, while maintaining the quality of the generations. In DivPO, preference pairs are selected by first considering"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18101","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/2501.18101/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":"2026-07-05T11:07:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j3PEiT6o1M1y4q6Tt1WZpJq8cnQmy3dCdygH8iBy0nVy6za2Xz216LH6BMZdG8cgpj1P/2JnDAequCTTW/ToDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:29:33.599678Z"},"content_sha256":"07789b5fb0ff7c6b1bf45cc30ee788ae776359bd903f7331e12b0bf157ed6800","schema_version":"1.0","event_id":"sha256:07789b5fb0ff7c6b1bf45cc30ee788ae776359bd903f7331e12b0bf157ed6800"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2U76SUX6LOSEK73JE2TZ47VD6X/bundle.json","state_url":"https://pith.science/pith/2U76SUX6LOSEK73JE2TZ47VD6X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2U76SUX6LOSEK73JE2TZ47VD6X/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":"2026-08-19T16:29:33Z","links":{"resolver":"https://pith.science/pith/2U76SUX6LOSEK73JE2TZ47VD6X","bundle":"https://pith.science/pith/2U76SUX6LOSEK73JE2TZ47VD6X/bundle.json","state":"https://pith.science/pith/2U76SUX6LOSEK73JE2TZ47VD6X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2U76SUX6LOSEK73JE2TZ47VD6X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2U76SUX6LOSEK73JE2TZ47VD6X","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":"8e30e158f5e6a53ef6b16677459a42e738e015b04da7ddbeb1a1e76c086d2154","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-30T02:47:41Z","title_canon_sha256":"d1850248818cb538af8d424f06734bafd74a9c59b0f8c2741782e83cef31fb6d"},"schema_version":"1.0","source":{"id":"2501.18101","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18101","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18101v4","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18101","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"pith_short_12","alias_value":"2U76SUX6LOSE","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"pith_short_16","alias_value":"2U76SUX6LOSEK73J","created_at":"2026-07-05T11:07:19Z"},{"alias_kind":"pith_short_8","alias_value":"2U76SUX6","created_at":"2026-07-05T11:07:19Z"}],"graph_snapshots":[{"event_id":"sha256:07789b5fb0ff7c6b1bf45cc30ee788ae776359bd903f7331e12b0bf157ed6800","target":"graph","created_at":"2026-07-05T11:07:19Z","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/2501.18101/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated responses. This is particularly a problem for creative generative tasks where varied responses are desired. In this work we introduce Diverse Preference Optimization (DivPO), an optimization method which learns to generate much more diverse responses than standard pipelines, while maintaining the quality of the generations. In DivPO, preference pairs are selected by first considering","authors_text":"Angelica Chen, Ilia Kulikov, Jack Lanchantin, Jason Weston, Ping Yu, Sainbayar Sukhbaatar, Shehzaad Dhuliawala","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-30T02:47:41Z","title":"Diverse Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18101","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:d900a8de4d8e0b7ca94fc00a7ed042388b2dbc8e72a81435b24b0086d89e528e","target":"record","created_at":"2026-07-05T11:07:19Z","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":"8e30e158f5e6a53ef6b16677459a42e738e015b04da7ddbeb1a1e76c086d2154","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-30T02:47:41Z","title_canon_sha256":"d1850248818cb538af8d424f06734bafd74a9c59b0f8c2741782e83cef31fb6d"},"schema_version":"1.0","source":{"id":"2501.18101","kind":"arxiv","version":4}},"canonical_sha256":"d53fe952fe5ba4457f6926a79e7ea3f5f95378d05642d3fc751ec91b9554639d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d53fe952fe5ba4457f6926a79e7ea3f5f95378d05642d3fc751ec91b9554639d","first_computed_at":"2026-07-05T11:07:19.781572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:19.781572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YljY9jqTuu+v8scWM0quwfLOqo2oRVOjQPJufhJ2coZUps4ZRCRcLo2tuRqdvOjdcjWb1l1gc7TG09l9vo4wBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:19.782076Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18101","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d900a8de4d8e0b7ca94fc00a7ed042388b2dbc8e72a81435b24b0086d89e528e","sha256:07789b5fb0ff7c6b1bf45cc30ee788ae776359bd903f7331e12b0bf157ed6800"],"state_sha256":"686be79629cc85a34ce3c3807d237ebe71682efebd3b98c47f89a7cc8e21baa6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MiIMd9LrPcc5DWj7VVtlYrbYLazKVMQRAlR9OeQG2Y8s1SVGRMyAq8h/IuzCKcWMmmpUq7gMKU7HvQ2MnSb/CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T16:29:33.611147Z","bundle_sha256":"9de4c474865648ca887b497f422fb7b73d485077052bc88575c27cb8ebf71def"}}