{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HKJ2S5HZZSTSBW2IYSQOJPDXRE","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":"155a9709ac774e9828fea944d8796fdec1390f0a7d4bbc93d07b735ec047163a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T17:03:17Z","title_canon_sha256":"63cd604b08f87c9ec56938cd375b335a864a9612f91d6769b3eb2116d51d2b22"},"schema_version":"1.0","source":{"id":"2503.04618","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04618","created_at":"2026-07-05T10:25:43Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04618v1","created_at":"2026-07-05T10:25:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04618","created_at":"2026-07-05T10:25:43Z"},{"alias_kind":"pith_short_12","alias_value":"HKJ2S5HZZSTS","created_at":"2026-07-05T10:25:43Z"},{"alias_kind":"pith_short_16","alias_value":"HKJ2S5HZZSTSBW2I","created_at":"2026-07-05T10:25:43Z"},{"alias_kind":"pith_short_8","alias_value":"HKJ2S5HZ","created_at":"2026-07-05T10:25:43Z"}],"graph_snapshots":[{"event_id":"sha256:62da8db65fb8645548c03f6d8e9160e175d57d78b1e34192fb52a6f32297ce74","target":"graph","created_at":"2026-07-05T10:25:43Z","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/2503.04618/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Process supervision, i.e., evaluating each step, is critical for complex large language model (LLM) reasoning and test-time searching with increased inference compute. Existing approaches, represented by process reward models (PRMs), primarily focus on rewarding signals up to the current step, exhibiting a one-directional nature and lacking a mechanism to model the distance to the final target. To address this problem, we draw inspiration from the A* algorithm, which states that an effective supervisory signal should simultaneously consider the incurred cost and the estimated cost for reaching","authors_text":"Boyang Hong, Honglin Guo, Jiazheng Zhang, Nijun Li, Qi Zhang, Rui Zheng, Tao Gui, Wei He, Wenxiang Chen, Xuanjing Huang, Yun Li, Zhiheng Xi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T17:03:17Z","title":"Better Process Supervision with Bi-directional Rewarding Signals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04618","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:f99f616abfbb334f59cb361129a4cd7d5cf3f5c74aeb66495dd86968b908ddf1","target":"record","created_at":"2026-07-05T10:25:43Z","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":"155a9709ac774e9828fea944d8796fdec1390f0a7d4bbc93d07b735ec047163a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T17:03:17Z","title_canon_sha256":"63cd604b08f87c9ec56938cd375b335a864a9612f91d6769b3eb2116d51d2b22"},"schema_version":"1.0","source":{"id":"2503.04618","kind":"arxiv","version":1}},"canonical_sha256":"3a93a974f9cca720db48c4a0e4bc77891ad6567551a89a2fb99ccc8573aaa01d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a93a974f9cca720db48c4a0e4bc77891ad6567551a89a2fb99ccc8573aaa01d","first_computed_at":"2026-07-05T10:25:43.465555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:43.465555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5aT6yr+eHPcrUeIEcNI2Sd3Wgz0ADV5RhoIzuRgZKBjSLsZXwTu2zrXnIH26CaS5DP02oP12f3ejescDohDVAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:43.466038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04618","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f99f616abfbb334f59cb361129a4cd7d5cf3f5c74aeb66495dd86968b908ddf1","sha256:62da8db65fb8645548c03f6d8e9160e175d57d78b1e34192fb52a6f32297ce74"],"state_sha256":"0dcfd607658121938374d0b3e06f9b57f9e00f2d80956f3bed21cea3966b1a71"}