{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IUD63DKHPXO7BPJJL5E2WIABAY","short_pith_number":"pith:IUD63DKH","canonical_record":{"source":{"id":"2402.02479","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T13:16:29Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"title_canon_sha256":"8fe3cb29be6804998c0a79b5c6deae41a96e8bdc5c89fe6f70d7be265cd2d8bc","abstract_canon_sha256":"60baa0ee91cdd14b4d2c5670a17218fff355c74addd459067fafc0b1567dcca2"},"schema_version":"1.0"},"canonical_sha256":"4507ed8d477dddf0bd295f49ab2001060bc5a7f5f0efc77c9609e577847db2de","source":{"kind":"arxiv","id":"2402.02479","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02479","created_at":"2026-07-05T08:29:21Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02479v2","created_at":"2026-07-05T08:29:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02479","created_at":"2026-07-05T08:29:21Z"},{"alias_kind":"pith_short_12","alias_value":"IUD63DKHPXO7","created_at":"2026-07-05T08:29:21Z"},{"alias_kind":"pith_short_16","alias_value":"IUD63DKHPXO7BPJJ","created_at":"2026-07-05T08:29:21Z"},{"alias_kind":"pith_short_8","alias_value":"IUD63DKH","created_at":"2026-07-05T08:29:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IUD63DKHPXO7BPJJL5E2WIABAY","target":"record","payload":{"canonical_record":{"source":{"id":"2402.02479","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T13:16:29Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"title_canon_sha256":"8fe3cb29be6804998c0a79b5c6deae41a96e8bdc5c89fe6f70d7be265cd2d8bc","abstract_canon_sha256":"60baa0ee91cdd14b4d2c5670a17218fff355c74addd459067fafc0b1567dcca2"},"schema_version":"1.0"},"canonical_sha256":"4507ed8d477dddf0bd295f49ab2001060bc5a7f5f0efc77c9609e577847db2de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:21.227441Z","signature_b64":"nwacoPjHIDF0dObgubdZ/trMrrfpXdJNJrwbtN5X8MSFQskbxAN4xkaX8w3UOu7yBhoL+Tt2OJqVcmlySOTjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4507ed8d477dddf0bd295f49ab2001060bc5a7f5f0efc77c9609e577847db2de","last_reissued_at":"2026-07-05T08:29:21.226931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:21.226931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.02479","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:29:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i9e2iEsLaVZFfqsFjseDgD+61N4AXZoISKT5xGoHvXuWrUkefTivDuDztmRYIJYNYttcgebymPvcrqGfc7L7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:14:34.942738Z"},"content_sha256":"ec336f47240da0b66b45a48f12af5d8edc9a3b66c7058210699d962665877f3c","schema_version":"1.0","event_id":"sha256:ec336f47240da0b66b45a48f12af5d8edc9a3b66c7058210699d962665877f3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IUD63DKHPXO7BPJJL5E2WIABAY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC"],"primary_cat":"cs.LG","authors_text":"Asim Munawar, Dinesh Raghu, Gaurav Pandey, Guangxuan Xu, Mayank Mishra, Ram\\'on Fernandez Astudillo, Sachindra Joshi, Tahira Naseem, Yatin Nandwani","submitted_at":"2024-02-04T13:16:29Z","abstract_excerpt":"Distribution matching methods for language model alignment such as Generation with Distributional Control (GDC) and Distributional Policy Gradient (DPG) have not received the same level of attention in reinforcement learning from human feedback (RLHF) as contrastive methods such as Sequence Likelihood Calibration (SLiC), Direct Preference Optimization (DPO) and its variants. We identify high variance of the gradient estimate as the primary reason for the lack of success of these methods and propose a self-normalized baseline to reduce the variance. We further generalize the target distribution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02479","kind":"arxiv","version":2},"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/2402.02479/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":"2026-07-05T08:29:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WjTsCiagbNS5rGYC4+47VBtGVGJN4VUVTr78h5ykA9wMMudu/fZVnpid0RHMlxC/7jLuRNi0oHnCrFsKz0VODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:14:34.943770Z"},"content_sha256":"3524a3d67949da09b697d23011d1ec106b578c078580b52f4bb9f7c9f62ddbae","schema_version":"1.0","event_id":"sha256:3524a3d67949da09b697d23011d1ec106b578c078580b52f4bb9f7c9f62ddbae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUD63DKHPXO7BPJJL5E2WIABAY/bundle.json","state_url":"https://pith.science/pith/IUD63DKHPXO7BPJJL5E2WIABAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUD63DKHPXO7BPJJL5E2WIABAY/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":"2026-07-31T14:14:34Z","links":{"resolver":"https://pith.science/pith/IUD63DKHPXO7BPJJL5E2WIABAY","bundle":"https://pith.science/pith/IUD63DKHPXO7BPJJL5E2WIABAY/bundle.json","state":"https://pith.science/pith/IUD63DKHPXO7BPJJL5E2WIABAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUD63DKHPXO7BPJJL5E2WIABAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IUD63DKHPXO7BPJJL5E2WIABAY","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":"60baa0ee91cdd14b4d2c5670a17218fff355c74addd459067fafc0b1567dcca2","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T13:16:29Z","title_canon_sha256":"8fe3cb29be6804998c0a79b5c6deae41a96e8bdc5c89fe6f70d7be265cd2d8bc"},"schema_version":"1.0","source":{"id":"2402.02479","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02479","created_at":"2026-07-05T08:29:21Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02479v2","created_at":"2026-07-05T08:29:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02479","created_at":"2026-07-05T08:29:21Z"},{"alias_kind":"pith_short_12","alias_value":"IUD63DKHPXO7","created_at":"2026-07-05T08:29:21Z"},{"alias_kind":"pith_short_16","alias_value":"IUD63DKHPXO7BPJJ","created_at":"2026-07-05T08:29:21Z"},{"alias_kind":"pith_short_8","alias_value":"IUD63DKH","created_at":"2026-07-05T08:29:21Z"}],"graph_snapshots":[{"event_id":"sha256:3524a3d67949da09b697d23011d1ec106b578c078580b52f4bb9f7c9f62ddbae","target":"graph","created_at":"2026-07-05T08:29:21Z","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/2402.02479/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distribution matching methods for language model alignment such as Generation with Distributional Control (GDC) and Distributional Policy Gradient (DPG) have not received the same level of attention in reinforcement learning from human feedback (RLHF) as contrastive methods such as Sequence Likelihood Calibration (SLiC), Direct Preference Optimization (DPO) and its variants. We identify high variance of the gradient estimate as the primary reason for the lack of success of these methods and propose a self-normalized baseline to reduce the variance. We further generalize the target distribution","authors_text":"Asim Munawar, Dinesh Raghu, Gaurav Pandey, Guangxuan Xu, Mayank Mishra, Ram\\'on Fernandez Astudillo, Sachindra Joshi, Tahira Naseem, Yatin Nandwani","cross_cats":["cs.AI","cs.CL","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T13:16:29Z","title":"BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02479","kind":"arxiv","version":2},"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:ec336f47240da0b66b45a48f12af5d8edc9a3b66c7058210699d962665877f3c","target":"record","created_at":"2026-07-05T08:29:21Z","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":"60baa0ee91cdd14b4d2c5670a17218fff355c74addd459067fafc0b1567dcca2","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T13:16:29Z","title_canon_sha256":"8fe3cb29be6804998c0a79b5c6deae41a96e8bdc5c89fe6f70d7be265cd2d8bc"},"schema_version":"1.0","source":{"id":"2402.02479","kind":"arxiv","version":2}},"canonical_sha256":"4507ed8d477dddf0bd295f49ab2001060bc5a7f5f0efc77c9609e577847db2de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4507ed8d477dddf0bd295f49ab2001060bc5a7f5f0efc77c9609e577847db2de","first_computed_at":"2026-07-05T08:29:21.226931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:21.226931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nwacoPjHIDF0dObgubdZ/trMrrfpXdJNJrwbtN5X8MSFQskbxAN4xkaX8w3UOu7yBhoL+Tt2OJqVcmlySOTjCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:21.227441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02479","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec336f47240da0b66b45a48f12af5d8edc9a3b66c7058210699d962665877f3c","sha256:3524a3d67949da09b697d23011d1ec106b578c078580b52f4bb9f7c9f62ddbae"],"state_sha256":"64df399f6aaea4156102c72e5ba366dec65297e816e0afcfb8c243e4f3628c02"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EgLIdZ7LUEsRYY+D6Y9k4367LDfIOdIWfEoujG6He+d1scc2A7tDa/xW40tkF02+YdU4tbfEH5MCVHy5JPQIBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T14:14:34.953977Z","bundle_sha256":"c8680378f510b00407bdb5c67d9e42f7811aca0736d7051aa50e180f7c7bb1c4"}}