{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:V7UCDSEQFAF4KH67DWZR3TGM54","short_pith_number":"pith:V7UCDSEQ","canonical_record":{"source":{"id":"2405.18718","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T02:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"1d4b328ed8665b4b6fbbdb423c1140715e61d10d3476ef5554d5c87b0cc95f97","abstract_canon_sha256":"aa1a79bd6b0a59cc9318eb1f600e602d58eb773a08c9d0401699d01838570483"},"schema_version":"1.0"},"canonical_sha256":"afe821c890280bc51fdf1db31dccccef268a14c66d143355c6f8708174d776ec","source":{"kind":"arxiv","id":"2405.18718","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18718","created_at":"2026-07-05T08:24:29Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18718v1","created_at":"2026-07-05T08:24:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18718","created_at":"2026-07-05T08:24:29Z"},{"alias_kind":"pith_short_12","alias_value":"V7UCDSEQFAF4","created_at":"2026-07-05T08:24:29Z"},{"alias_kind":"pith_short_16","alias_value":"V7UCDSEQFAF4KH67","created_at":"2026-07-05T08:24:29Z"},{"alias_kind":"pith_short_8","alias_value":"V7UCDSEQ","created_at":"2026-07-05T08:24:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:V7UCDSEQFAF4KH67DWZR3TGM54","target":"record","payload":{"canonical_record":{"source":{"id":"2405.18718","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T02:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"1d4b328ed8665b4b6fbbdb423c1140715e61d10d3476ef5554d5c87b0cc95f97","abstract_canon_sha256":"aa1a79bd6b0a59cc9318eb1f600e602d58eb773a08c9d0401699d01838570483"},"schema_version":"1.0"},"canonical_sha256":"afe821c890280bc51fdf1db31dccccef268a14c66d143355c6f8708174d776ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:29.347511Z","signature_b64":"7TKY4Q0KQ9yyZ2Ia7KHHDZ2LrunkSAOWi6fGuYaZPSkr2bE/KuT+iJt86Sb1pbS0JTD3+jPuDnsEAPtAQyoJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afe821c890280bc51fdf1db31dccccef268a14c66d143355c6f8708174d776ec","last_reissued_at":"2026-07-05T08:24:29.346889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:29.346889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.18718","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":"2026-07-05T08:24:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vzo1gDPmc8dFBjMrcFDvI/SsQttS7R7MHO22YT5NmbXWogEpk1bHvWCu83xKvBI2BQv6svd2NaQtiK4jsgLMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:47:08.251679Z"},"content_sha256":"82a856d18775b0b5477bfd65d1c4ccb862932bbc2cf6ce01c922c0fc0d8aeb5d","schema_version":"1.0","event_id":"sha256:82a856d18775b0b5477bfd65d1c4ccb862932bbc2cf6ce01c922c0fc0d8aeb5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:V7UCDSEQFAF4KH67DWZR3TGM54","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Model-agnostic Alignment via Bayesian Persuasion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boyuan Chen, Fengshuo Bai, Mingzhi Wang, Yaodong Yang, Yinda Xu, Ying Wen, Zhaowei Zhang","submitted_at":"2024-05-29T02:57:07Z","abstract_excerpt":"With recent advancements in large language models (LLMs), alignment has emerged as an effective technique for keeping LLMs consensus with human intent. Current methods primarily involve direct training through Supervised Fine-tuning (SFT) or Reinforcement Learning from Human Feedback (RLHF), both of which require substantial computational resources and extensive ground truth data. This paper explores an efficient method for aligning black-box large models using smaller models, introducing a model-agnostic and lightweight Bayesian Persuasion Alignment framework. We formalize this problem as an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18718","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/2405.18718/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":"2026-07-05T08:24:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/SGwOE/jL3syZtRbM4FXzCFL+cpwibg2N9R39qbzHgs+v9+XdEUFS1ij1jrGECOv0T7l74MTIoyVH9wIVU6BDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:47:08.252237Z"},"content_sha256":"4c79b6c6174d23896df1eb07866b1d7d00fd7c9d7838749a226779339b46fdcd","schema_version":"1.0","event_id":"sha256:4c79b6c6174d23896df1eb07866b1d7d00fd7c9d7838749a226779339b46fdcd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V7UCDSEQFAF4KH67DWZR3TGM54/bundle.json","state_url":"https://pith.science/pith/V7UCDSEQFAF4KH67DWZR3TGM54/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V7UCDSEQFAF4KH67DWZR3TGM54/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":"2026-08-09T19:47:08Z","links":{"resolver":"https://pith.science/pith/V7UCDSEQFAF4KH67DWZR3TGM54","bundle":"https://pith.science/pith/V7UCDSEQFAF4KH67DWZR3TGM54/bundle.json","state":"https://pith.science/pith/V7UCDSEQFAF4KH67DWZR3TGM54/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V7UCDSEQFAF4KH67DWZR3TGM54/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V7UCDSEQFAF4KH67DWZR3TGM54","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":"aa1a79bd6b0a59cc9318eb1f600e602d58eb773a08c9d0401699d01838570483","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T02:57:07Z","title_canon_sha256":"1d4b328ed8665b4b6fbbdb423c1140715e61d10d3476ef5554d5c87b0cc95f97"},"schema_version":"1.0","source":{"id":"2405.18718","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18718","created_at":"2026-07-05T08:24:29Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18718v1","created_at":"2026-07-05T08:24:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18718","created_at":"2026-07-05T08:24:29Z"},{"alias_kind":"pith_short_12","alias_value":"V7UCDSEQFAF4","created_at":"2026-07-05T08:24:29Z"},{"alias_kind":"pith_short_16","alias_value":"V7UCDSEQFAF4KH67","created_at":"2026-07-05T08:24:29Z"},{"alias_kind":"pith_short_8","alias_value":"V7UCDSEQ","created_at":"2026-07-05T08:24:29Z"}],"graph_snapshots":[{"event_id":"sha256:4c79b6c6174d23896df1eb07866b1d7d00fd7c9d7838749a226779339b46fdcd","target":"graph","created_at":"2026-07-05T08:24:29Z","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/2405.18718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With recent advancements in large language models (LLMs), alignment has emerged as an effective technique for keeping LLMs consensus with human intent. Current methods primarily involve direct training through Supervised Fine-tuning (SFT) or Reinforcement Learning from Human Feedback (RLHF), both of which require substantial computational resources and extensive ground truth data. This paper explores an efficient method for aligning black-box large models using smaller models, introducing a model-agnostic and lightweight Bayesian Persuasion Alignment framework. We formalize this problem as an ","authors_text":"Boyuan Chen, Fengshuo Bai, Mingzhi Wang, Yaodong Yang, Yinda Xu, Ying Wen, Zhaowei Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T02:57:07Z","title":"Efficient Model-agnostic Alignment via Bayesian Persuasion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18718","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":"sha256:82a856d18775b0b5477bfd65d1c4ccb862932bbc2cf6ce01c922c0fc0d8aeb5d","target":"record","created_at":"2026-07-05T08:24:29Z","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":"aa1a79bd6b0a59cc9318eb1f600e602d58eb773a08c9d0401699d01838570483","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T02:57:07Z","title_canon_sha256":"1d4b328ed8665b4b6fbbdb423c1140715e61d10d3476ef5554d5c87b0cc95f97"},"schema_version":"1.0","source":{"id":"2405.18718","kind":"arxiv","version":1}},"canonical_sha256":"afe821c890280bc51fdf1db31dccccef268a14c66d143355c6f8708174d776ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afe821c890280bc51fdf1db31dccccef268a14c66d143355c6f8708174d776ec","first_computed_at":"2026-07-05T08:24:29.346889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:29.346889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7TKY4Q0KQ9yyZ2Ia7KHHDZ2LrunkSAOWi6fGuYaZPSkr2bE/KuT+iJt86Sb1pbS0JTD3+jPuDnsEAPtAQyoJDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:29.347511Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18718","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82a856d18775b0b5477bfd65d1c4ccb862932bbc2cf6ce01c922c0fc0d8aeb5d","sha256:4c79b6c6174d23896df1eb07866b1d7d00fd7c9d7838749a226779339b46fdcd"],"state_sha256":"c55c493692b343d2e80a3eae87ab950d6e1958265792d2d566a6f2b5630d29a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6D6hubTZANWlGPe3CpT2QPoJk0a7Gu3uCI0Yb0Sk5pOy5dvnKnKhnGIAuPeazCkvws0hINQK7k6DnpHylbm4Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:47:08.259269Z","bundle_sha256":"7cc557e5ba934106991fc0607cfaf6a82e5f1a755cf64a7067c87821dc5b2b51"}}