{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XAD6NZTIJVCPPKQ5UWDMFQNEXL","short_pith_number":"pith:XAD6NZTI","canonical_record":{"source":{"id":"2607.01392","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T18:50:14Z","cross_cats_sorted":[],"title_canon_sha256":"a12ec27c5f8ce1e3e6e4eba94e91c538b4b6bf7fe585b83848d11b7c56029997","abstract_canon_sha256":"d48f1f386b3df1efbbe506bdab1384b2bedc4c9e21c68a000465e63a0e9c1622"},"schema_version":"1.0"},"canonical_sha256":"b807e6e6684d44f7aa1da586c2c1a4baca26e9ae538ac7c5ff7349a07cca0c4f","source":{"kind":"arxiv","id":"2607.01392","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01392","created_at":"2026-07-03T00:16:59Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01392v1","created_at":"2026-07-03T00:16:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01392","created_at":"2026-07-03T00:16:59Z"},{"alias_kind":"pith_short_12","alias_value":"XAD6NZTIJVCP","created_at":"2026-07-03T00:16:59Z"},{"alias_kind":"pith_short_16","alias_value":"XAD6NZTIJVCPPKQ5","created_at":"2026-07-03T00:16:59Z"},{"alias_kind":"pith_short_8","alias_value":"XAD6NZTI","created_at":"2026-07-03T00:16:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XAD6NZTIJVCPPKQ5UWDMFQNEXL","target":"record","payload":{"canonical_record":{"source":{"id":"2607.01392","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T18:50:14Z","cross_cats_sorted":[],"title_canon_sha256":"a12ec27c5f8ce1e3e6e4eba94e91c538b4b6bf7fe585b83848d11b7c56029997","abstract_canon_sha256":"d48f1f386b3df1efbbe506bdab1384b2bedc4c9e21c68a000465e63a0e9c1622"},"schema_version":"1.0"},"canonical_sha256":"b807e6e6684d44f7aa1da586c2c1a4baca26e9ae538ac7c5ff7349a07cca0c4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T00:16:59.165237Z","signature_b64":"m4FyDg5ImN60+ZF1zTKAesFLTsdZGhqOODISiW72BBm4NW1cORsBryT2SaZnPgxz+Z/VRHj9dLsxiDh9BNayAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b807e6e6684d44f7aa1da586c2c1a4baca26e9ae538ac7c5ff7349a07cca0c4f","last_reissued_at":"2026-07-03T00:16:59.164875Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T00:16:59.164875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.01392","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":"2026-07-03T00:16:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xJ3y5kNvzUyzOAgnDnp8OlDLH1m8FhZRKG1d5lSDLgLPDh+aNVpX4P43cQHKVTeTqi/oAMrEk+eNK4jnMQ7dBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:30:15.978420Z"},"content_sha256":"326c1881900349d7898cad9e22efd3cd41cc107537273bf16b329bb776cd7767","schema_version":"1.0","event_id":"sha256:326c1881900349d7898cad9e22efd3cd41cc107537273bf16b329bb776cd7767"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XAD6NZTIJVCPPKQ5UWDMFQNEXL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Objective Exploration and Preference Optimization via Mutual Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deqing Wang, Hongyan Xie, Jianxin Li, Ruiyu Fang, Shuangyong Song, Yikun Ban, Zixuang Huang","submitted_at":"2026-07-01T18:50:14Z","abstract_excerpt":"Aligning large language models with diverse and heterogeneous human values requires multi-objective alignment methods to effectively trade off conflicting preference dimensions. Current methods achieve this trade-off by training policies conditioned on preference vectors and leveraging online direct preference optimization. However, exploration uncertainty can cause the reward distributions of responses generated under different preference vectors to overlap, and the generated responses may fail to effectively align with the corresponding preference vectors. In this paper, we propose Multi-Obj"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01392","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/2607.01392/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":"2026-07-03T00:16:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tiJJsbPpy4kj3a4+iBfzI84O9iXNsCezK/h1c/rk735ue7oULGokjkKQfCOlS72BdwQ/DQnyh82Mhbxp6+Q2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:30:15.978795Z"},"content_sha256":"92b84fec25d8df06f80ec203c6383a76d34cc09d98ac6c3be626067ed3774aa7","schema_version":"1.0","event_id":"sha256:92b84fec25d8df06f80ec203c6383a76d34cc09d98ac6c3be626067ed3774aa7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XAD6NZTIJVCPPKQ5UWDMFQNEXL/bundle.json","state_url":"https://pith.science/pith/XAD6NZTIJVCPPKQ5UWDMFQNEXL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XAD6NZTIJVCPPKQ5UWDMFQNEXL/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":"2026-07-04T18:30:15Z","links":{"resolver":"https://pith.science/pith/XAD6NZTIJVCPPKQ5UWDMFQNEXL","bundle":"https://pith.science/pith/XAD6NZTIJVCPPKQ5UWDMFQNEXL/bundle.json","state":"https://pith.science/pith/XAD6NZTIJVCPPKQ5UWDMFQNEXL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XAD6NZTIJVCPPKQ5UWDMFQNEXL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XAD6NZTIJVCPPKQ5UWDMFQNEXL","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":"d48f1f386b3df1efbbe506bdab1384b2bedc4c9e21c68a000465e63a0e9c1622","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T18:50:14Z","title_canon_sha256":"a12ec27c5f8ce1e3e6e4eba94e91c538b4b6bf7fe585b83848d11b7c56029997"},"schema_version":"1.0","source":{"id":"2607.01392","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01392","created_at":"2026-07-03T00:16:59Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01392v1","created_at":"2026-07-03T00:16:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01392","created_at":"2026-07-03T00:16:59Z"},{"alias_kind":"pith_short_12","alias_value":"XAD6NZTIJVCP","created_at":"2026-07-03T00:16:59Z"},{"alias_kind":"pith_short_16","alias_value":"XAD6NZTIJVCPPKQ5","created_at":"2026-07-03T00:16:59Z"},{"alias_kind":"pith_short_8","alias_value":"XAD6NZTI","created_at":"2026-07-03T00:16:59Z"}],"graph_snapshots":[{"event_id":"sha256:92b84fec25d8df06f80ec203c6383a76d34cc09d98ac6c3be626067ed3774aa7","target":"graph","created_at":"2026-07-03T00:16:59Z","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/2607.01392/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning large language models with diverse and heterogeneous human values requires multi-objective alignment methods to effectively trade off conflicting preference dimensions. Current methods achieve this trade-off by training policies conditioned on preference vectors and leveraging online direct preference optimization. However, exploration uncertainty can cause the reward distributions of responses generated under different preference vectors to overlap, and the generated responses may fail to effectively align with the corresponding preference vectors. In this paper, we propose Multi-Obj","authors_text":"Deqing Wang, Hongyan Xie, Jianxin Li, Ruiyu Fang, Shuangyong Song, Yikun Ban, Zixuang Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T18:50:14Z","title":"Multi-Objective Exploration and Preference Optimization via Mutual Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01392","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":"sha256:326c1881900349d7898cad9e22efd3cd41cc107537273bf16b329bb776cd7767","target":"record","created_at":"2026-07-03T00:16:59Z","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":"d48f1f386b3df1efbbe506bdab1384b2bedc4c9e21c68a000465e63a0e9c1622","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T18:50:14Z","title_canon_sha256":"a12ec27c5f8ce1e3e6e4eba94e91c538b4b6bf7fe585b83848d11b7c56029997"},"schema_version":"1.0","source":{"id":"2607.01392","kind":"arxiv","version":1}},"canonical_sha256":"b807e6e6684d44f7aa1da586c2c1a4baca26e9ae538ac7c5ff7349a07cca0c4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b807e6e6684d44f7aa1da586c2c1a4baca26e9ae538ac7c5ff7349a07cca0c4f","first_computed_at":"2026-07-03T00:16:59.164875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T00:16:59.164875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m4FyDg5ImN60+ZF1zTKAesFLTsdZGhqOODISiW72BBm4NW1cORsBryT2SaZnPgxz+Z/VRHj9dLsxiDh9BNayAA==","signature_status":"signed_v1","signed_at":"2026-07-03T00:16:59.165237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01392","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:326c1881900349d7898cad9e22efd3cd41cc107537273bf16b329bb776cd7767","sha256:92b84fec25d8df06f80ec203c6383a76d34cc09d98ac6c3be626067ed3774aa7"],"state_sha256":"a4b58014fc2e154d3250c5700fca96795c05f7f47a7bd8149e050c68fec66fbd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v9QgePU953SZbytko1CT41h01B2fU24rOitFflm/qKItLsg9jJj+hlpg++Tm5i+Fi3SYq+gCY5dpw7vahOJFBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T18:30:15.981004Z","bundle_sha256":"8a5a7719d82310016df3edc39d6a5006a9312119e85dcaf5bf8db0c8e59532e4"}}