{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:I4452XJDOJC4Q5TYYKHVXUHTRO","short_pith_number":"pith:I4452XJD","canonical_record":{"source":{"id":"2502.04517","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T21:36:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8c9f7617e63a289b01f8e89e82978e051e590e8a5b888c64e516234998d9388c","abstract_canon_sha256":"c5732570f0c548bbc206d9738e2881bacf87c41e850b8f77a5b9deb45c6401e5"},"schema_version":"1.0"},"canonical_sha256":"4739dd5d237245c87678c28f5bd0f38ba4ac41738ea3cbd82d9ee0c47a8011de","source":{"kind":"arxiv","id":"2502.04517","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04517","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04517v2","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04517","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"pith_short_12","alias_value":"I4452XJDOJC4","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"pith_short_16","alias_value":"I4452XJDOJC4Q5TY","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"pith_short_8","alias_value":"I4452XJD","created_at":"2026-07-05T11:32:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:I4452XJDOJC4Q5TYYKHVXUHTRO","target":"record","payload":{"canonical_record":{"source":{"id":"2502.04517","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T21:36:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8c9f7617e63a289b01f8e89e82978e051e590e8a5b888c64e516234998d9388c","abstract_canon_sha256":"c5732570f0c548bbc206d9738e2881bacf87c41e850b8f77a5b9deb45c6401e5"},"schema_version":"1.0"},"canonical_sha256":"4739dd5d237245c87678c28f5bd0f38ba4ac41738ea3cbd82d9ee0c47a8011de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:24.454229Z","signature_b64":"F2EmT+qcV2X6bev+7vaDTINqiSIM0vf8wNNpobP9j27/5nu2nMAXkx9DNPyePM08D9jhQe6lZgI1EVsVV4BeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4739dd5d237245c87678c28f5bd0f38ba4ac41738ea3cbd82d9ee0c47a8011de","last_reissued_at":"2026-07-05T11:32:24.453748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:24.453748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.04517","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":"2026-07-05T11:32:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QNAlTC+XsANAi9xn2NrjNHGlHkOPv0D5DsUAznhXTFFqdfIjpd8NbCjVuYFBSPMTlBtlAdcGelEcNAJ2cVh8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:27:42.216153Z"},"content_sha256":"7cf32ddb69b9db2a1e23dcc87841de28188e00e33e91441c0ddb16680ca8a541","schema_version":"1.0","event_id":"sha256:7cf32ddb69b9db2a1e23dcc87841de28188e00e33e91441c0ddb16680ca8a541"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:I4452XJDOJC4Q5TYYKHVXUHTRO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Cost-Effective Reward Guided Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Agustinus Kristiadi, Ahmad Rashid, Hongliang Li, Pascal Poupart, Rongqi Fan, Ruotian Wu","submitted_at":"2025-02-06T21:36:44Z","abstract_excerpt":"Reward-guided text generation (RGTG) has emerged as a viable alternative to offline reinforcement learning from human feedback (RLHF). RGTG methods can align baseline language models to human preferences without further training like in standard RLHF methods. However, they rely on a reward model to score each candidate token generated by the language model at inference, incurring significant test-time overhead. Additionally, the reward model is usually only trained to score full sequences, which can lead to sub-optimal choices for partial sequences. In this work, we present a novel reward mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04517","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/2502.04517/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":"2026-07-05T11:32:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wR8a8SDskqmRTNB97r8z/qJIh3z4BX8qbxYr+PO6XBq5u0+lTrLAq8aRvpGyNlpIGyPwxxSqjq3svx384WFZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:27:42.216758Z"},"content_sha256":"06e3edaccb5c9b7414e7507141df2d73b6feb678c1ed5c56c3f7a8b5bb460efd","schema_version":"1.0","event_id":"sha256:06e3edaccb5c9b7414e7507141df2d73b6feb678c1ed5c56c3f7a8b5bb460efd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I4452XJDOJC4Q5TYYKHVXUHTRO/bundle.json","state_url":"https://pith.science/pith/I4452XJDOJC4Q5TYYKHVXUHTRO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I4452XJDOJC4Q5TYYKHVXUHTRO/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":"2026-08-10T18:27:42Z","links":{"resolver":"https://pith.science/pith/I4452XJDOJC4Q5TYYKHVXUHTRO","bundle":"https://pith.science/pith/I4452XJDOJC4Q5TYYKHVXUHTRO/bundle.json","state":"https://pith.science/pith/I4452XJDOJC4Q5TYYKHVXUHTRO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I4452XJDOJC4Q5TYYKHVXUHTRO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I4452XJDOJC4Q5TYYKHVXUHTRO","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":"c5732570f0c548bbc206d9738e2881bacf87c41e850b8f77a5b9deb45c6401e5","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T21:36:44Z","title_canon_sha256":"8c9f7617e63a289b01f8e89e82978e051e590e8a5b888c64e516234998d9388c"},"schema_version":"1.0","source":{"id":"2502.04517","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04517","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04517v2","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04517","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"pith_short_12","alias_value":"I4452XJDOJC4","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"pith_short_16","alias_value":"I4452XJDOJC4Q5TY","created_at":"2026-07-05T11:32:24Z"},{"alias_kind":"pith_short_8","alias_value":"I4452XJD","created_at":"2026-07-05T11:32:24Z"}],"graph_snapshots":[{"event_id":"sha256:06e3edaccb5c9b7414e7507141df2d73b6feb678c1ed5c56c3f7a8b5bb460efd","target":"graph","created_at":"2026-07-05T11:32:24Z","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/2502.04517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward-guided text generation (RGTG) has emerged as a viable alternative to offline reinforcement learning from human feedback (RLHF). RGTG methods can align baseline language models to human preferences without further training like in standard RLHF methods. However, they rely on a reward model to score each candidate token generated by the language model at inference, incurring significant test-time overhead. Additionally, the reward model is usually only trained to score full sequences, which can lead to sub-optimal choices for partial sequences. In this work, we present a novel reward mode","authors_text":"Agustinus Kristiadi, Ahmad Rashid, Hongliang Li, Pascal Poupart, Rongqi Fan, Ruotian Wu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T21:36:44Z","title":"Towards Cost-Effective Reward Guided Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04517","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":"sha256:7cf32ddb69b9db2a1e23dcc87841de28188e00e33e91441c0ddb16680ca8a541","target":"record","created_at":"2026-07-05T11:32:24Z","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":"c5732570f0c548bbc206d9738e2881bacf87c41e850b8f77a5b9deb45c6401e5","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T21:36:44Z","title_canon_sha256":"8c9f7617e63a289b01f8e89e82978e051e590e8a5b888c64e516234998d9388c"},"schema_version":"1.0","source":{"id":"2502.04517","kind":"arxiv","version":2}},"canonical_sha256":"4739dd5d237245c87678c28f5bd0f38ba4ac41738ea3cbd82d9ee0c47a8011de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4739dd5d237245c87678c28f5bd0f38ba4ac41738ea3cbd82d9ee0c47a8011de","first_computed_at":"2026-07-05T11:32:24.453748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:24.453748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F2EmT+qcV2X6bev+7vaDTINqiSIM0vf8wNNpobP9j27/5nu2nMAXkx9DNPyePM08D9jhQe6lZgI1EVsVV4BeCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:24.454229Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04517","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cf32ddb69b9db2a1e23dcc87841de28188e00e33e91441c0ddb16680ca8a541","sha256:06e3edaccb5c9b7414e7507141df2d73b6feb678c1ed5c56c3f7a8b5bb460efd"],"state_sha256":"54c1078efa6ef19b88898b40cbdaaea4caced66038fd27156460dbab804ca8bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"32l6MModZtDaYCgzsll1RK4xVYmJwk6TgC6bldrR/gfcf3al4HkO7ira6qHQK42ALqRv/JQnPNI8e/LF0DRNCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:27:42.221254Z","bundle_sha256":"88ffb8956ba30b5a13fd94a40595e1f43aadf26b3dcc25ed6a36ad507cf202f6"}}