{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UE2SUSC6KISN67EJ6ZNU53E3AC","short_pith_number":"pith:UE2SUSC6","canonical_record":{"source":{"id":"2405.04086","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-07T07:39:15Z","cross_cats_sorted":[],"title_canon_sha256":"843b54240afafdf2cb692f2dcdf13e48146e174b4d4129625bfd9f32a17b4a8c","abstract_canon_sha256":"847c2e90f29e1c09d4afbed4a72e787b7ddc7a61cb900b5477a1af15cae0e013"},"schema_version":"1.0"},"canonical_sha256":"a1352a485e5224df7c89f65b4eec9b0094f4ab2e9cdb2ab5950856d96737d6f6","source":{"kind":"arxiv","id":"2405.04086","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04086","created_at":"2026-07-05T08:16:31Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04086v1","created_at":"2026-07-05T08:16:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04086","created_at":"2026-07-05T08:16:31Z"},{"alias_kind":"pith_short_12","alias_value":"UE2SUSC6KISN","created_at":"2026-07-05T08:16:31Z"},{"alias_kind":"pith_short_16","alias_value":"UE2SUSC6KISN67EJ","created_at":"2026-07-05T08:16:31Z"},{"alias_kind":"pith_short_8","alias_value":"UE2SUSC6","created_at":"2026-07-05T08:16:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UE2SUSC6KISN67EJ6ZNU53E3AC","target":"record","payload":{"canonical_record":{"source":{"id":"2405.04086","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-07T07:39:15Z","cross_cats_sorted":[],"title_canon_sha256":"843b54240afafdf2cb692f2dcdf13e48146e174b4d4129625bfd9f32a17b4a8c","abstract_canon_sha256":"847c2e90f29e1c09d4afbed4a72e787b7ddc7a61cb900b5477a1af15cae0e013"},"schema_version":"1.0"},"canonical_sha256":"a1352a485e5224df7c89f65b4eec9b0094f4ab2e9cdb2ab5950856d96737d6f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:31.730448Z","signature_b64":"ePP4HC2d796GbYpQ/lfdxXUwgIzRTvQpkbe7lcBdZaeCvkl1O+A89bjY0bJqYawv3ha8/Ar5ErImrCUh9bg/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1352a485e5224df7c89f65b4eec9b0094f4ab2e9cdb2ab5950856d96737d6f6","last_reissued_at":"2026-07-05T08:16:31.729059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:31.729059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.04086","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":"2026-07-05T08:16:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XLhf7CcCcIUu79sjUZzNrKz8h+Px+YlDfEV00RixP+Yhj8iT+yubyBiKJiRhLieOgsTE6ZAJ+3tugm04u3DpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:46:55.925011Z"},"content_sha256":"687cc2bd1f822118865f57ef27257b3603ffc67555a7c302967806f87ab9f73b","schema_version":"1.0","event_id":"sha256:687cc2bd1f822118865f57ef27257b3603ffc67555a7c302967806f87ab9f73b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UE2SUSC6KISN67EJ6ZNU53E3AC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Language Model's Reasoning Abilities with Weak Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengsong Huang, Dawei Li, Jiaxin Huang, Jingbo Shang, Simeng Han, Sizhe Wang, Yifan Wang, Yongqi Tong, Zi Lin","submitted_at":"2024-05-07T07:39:15Z","abstract_excerpt":"While Large Language Models (LLMs) have demonstrated proficiency in handling complex queries, much of the past work has depended on extensively annotated datasets by human experts. However, this reliance on fully-supervised annotations poses scalability challenges, particularly as models and data requirements grow. To mitigate this, we explore the potential of enhancing LLMs' reasoning abilities with minimal human supervision. In this work, we introduce self-reinforcement, which begins with Supervised Fine-Tuning (SFT) of the model using a small collection of annotated questions. Then it itera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04086","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/2405.04086/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":"2026-07-05T08:16:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eZfY9IkcZTBsqrW3/CYxe5s8Bv0U48Ck7hSQXX7u2D1rKCiSDZRYxoKMQYYAOA8gSM8MVmQWvnsum4Sn2pMEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:46:55.925430Z"},"content_sha256":"6258d051ae3f86a6c385e9969388f5e88cde0532cdcc04caf4a49da805641d89","schema_version":"1.0","event_id":"sha256:6258d051ae3f86a6c385e9969388f5e88cde0532cdcc04caf4a49da805641d89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UE2SUSC6KISN67EJ6ZNU53E3AC/bundle.json","state_url":"https://pith.science/pith/UE2SUSC6KISN67EJ6ZNU53E3AC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UE2SUSC6KISN67EJ6ZNU53E3AC/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":"2026-07-07T13:46:55Z","links":{"resolver":"https://pith.science/pith/UE2SUSC6KISN67EJ6ZNU53E3AC","bundle":"https://pith.science/pith/UE2SUSC6KISN67EJ6ZNU53E3AC/bundle.json","state":"https://pith.science/pith/UE2SUSC6KISN67EJ6ZNU53E3AC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UE2SUSC6KISN67EJ6ZNU53E3AC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UE2SUSC6KISN67EJ6ZNU53E3AC","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":"847c2e90f29e1c09d4afbed4a72e787b7ddc7a61cb900b5477a1af15cae0e013","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-07T07:39:15Z","title_canon_sha256":"843b54240afafdf2cb692f2dcdf13e48146e174b4d4129625bfd9f32a17b4a8c"},"schema_version":"1.0","source":{"id":"2405.04086","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04086","created_at":"2026-07-05T08:16:31Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04086v1","created_at":"2026-07-05T08:16:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04086","created_at":"2026-07-05T08:16:31Z"},{"alias_kind":"pith_short_12","alias_value":"UE2SUSC6KISN","created_at":"2026-07-05T08:16:31Z"},{"alias_kind":"pith_short_16","alias_value":"UE2SUSC6KISN67EJ","created_at":"2026-07-05T08:16:31Z"},{"alias_kind":"pith_short_8","alias_value":"UE2SUSC6","created_at":"2026-07-05T08:16:31Z"}],"graph_snapshots":[{"event_id":"sha256:6258d051ae3f86a6c385e9969388f5e88cde0532cdcc04caf4a49da805641d89","target":"graph","created_at":"2026-07-05T08:16:31Z","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/2405.04086/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Large Language Models (LLMs) have demonstrated proficiency in handling complex queries, much of the past work has depended on extensively annotated datasets by human experts. However, this reliance on fully-supervised annotations poses scalability challenges, particularly as models and data requirements grow. To mitigate this, we explore the potential of enhancing LLMs' reasoning abilities with minimal human supervision. In this work, we introduce self-reinforcement, which begins with Supervised Fine-Tuning (SFT) of the model using a small collection of annotated questions. Then it itera","authors_text":"Chengsong Huang, Dawei Li, Jiaxin Huang, Jingbo Shang, Simeng Han, Sizhe Wang, Yifan Wang, Yongqi Tong, Zi Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-07T07:39:15Z","title":"Optimizing Language Model's Reasoning Abilities with Weak Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04086","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":"sha256:687cc2bd1f822118865f57ef27257b3603ffc67555a7c302967806f87ab9f73b","target":"record","created_at":"2026-07-05T08:16:31Z","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":"847c2e90f29e1c09d4afbed4a72e787b7ddc7a61cb900b5477a1af15cae0e013","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-07T07:39:15Z","title_canon_sha256":"843b54240afafdf2cb692f2dcdf13e48146e174b4d4129625bfd9f32a17b4a8c"},"schema_version":"1.0","source":{"id":"2405.04086","kind":"arxiv","version":1}},"canonical_sha256":"a1352a485e5224df7c89f65b4eec9b0094f4ab2e9cdb2ab5950856d96737d6f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1352a485e5224df7c89f65b4eec9b0094f4ab2e9cdb2ab5950856d96737d6f6","first_computed_at":"2026-07-05T08:16:31.729059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:31.729059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ePP4HC2d796GbYpQ/lfdxXUwgIzRTvQpkbe7lcBdZaeCvkl1O+A89bjY0bJqYawv3ha8/Ar5ErImrCUh9bg/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:31.730448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.04086","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:687cc2bd1f822118865f57ef27257b3603ffc67555a7c302967806f87ab9f73b","sha256:6258d051ae3f86a6c385e9969388f5e88cde0532cdcc04caf4a49da805641d89"],"state_sha256":"1bd9827cd6a13aa1b0e998c647f540ee45b0bb2d0595d3dd98928ac3a464077c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FHrILaDZD0b2YU9kIftuf+p7EGhuAWdB+4DzOC7e5yCQmgsSCz3E+Ij7DoINvtzo6OvAqdrHjZEzupNzGMAPAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:46:55.927430Z","bundle_sha256":"19916fef8d1bee2ae65fe742241e0fb033a4f510ff58da0c45d98d65614d47d8"}}