{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FHJ2CM5J2KX67FJAYOUOWEWUVB","short_pith_number":"pith:FHJ2CM5J","canonical_record":{"source":{"id":"2607.01181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T17:13:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d84893a6c9836fdee3dd609b63cf96f6e3793430bd580a4e9af5393923248a01","abstract_canon_sha256":"acb9abce2599b8ca6ed6a92465b78b88072dfd91538e36a8b1ed6127057aa181"},"schema_version":"1.0"},"canonical_sha256":"29d3a133a9d2afef9520c3a8eb12d4a8407a78f88d0463c38c416fe62197ff05","source":{"kind":"arxiv","id":"2607.01181","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01181","created_at":"2026-07-02T01:18:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01181v1","created_at":"2026-07-02T01:18:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01181","created_at":"2026-07-02T01:18:31Z"},{"alias_kind":"pith_short_12","alias_value":"FHJ2CM5J2KX6","created_at":"2026-07-02T01:18:31Z"},{"alias_kind":"pith_short_16","alias_value":"FHJ2CM5J2KX67FJA","created_at":"2026-07-02T01:18:31Z"},{"alias_kind":"pith_short_8","alias_value":"FHJ2CM5J","created_at":"2026-07-02T01:18:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FHJ2CM5J2KX67FJAYOUOWEWUVB","target":"record","payload":{"canonical_record":{"source":{"id":"2607.01181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T17:13:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d84893a6c9836fdee3dd609b63cf96f6e3793430bd580a4e9af5393923248a01","abstract_canon_sha256":"acb9abce2599b8ca6ed6a92465b78b88072dfd91538e36a8b1ed6127057aa181"},"schema_version":"1.0"},"canonical_sha256":"29d3a133a9d2afef9520c3a8eb12d4a8407a78f88d0463c38c416fe62197ff05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:31.913561Z","signature_b64":"LtToMB0T/1pE4qjqLhrtbi9CQXNXZX0tiyPlcZ7scAclq/LLQbrMn+lWP2fW+bnmZbuiv1DPBEGgEB8iehShDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29d3a133a9d2afef9520c3a8eb12d4a8407a78f88d0463c38c416fe62197ff05","last_reissued_at":"2026-07-02T01:18:31.913189Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:31.913189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.01181","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":"2026-07-02T01:18:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c8SyIWSKMCZ9rAy8WOUb0vHB5oYFvXU2WD6UBPajJA3m8KS1Iwms5G2zh/6XOXRBsELjtJsSQU5dmMhKu2JJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T13:27:32.451533Z"},"content_sha256":"cd3755f38d72c0d1cc9728897b83e578d21268c8fd9a6c362a2c84349c83c642","schema_version":"1.0","event_id":"sha256:cd3755f38d72c0d1cc9728897b83e578d21268c8fd9a6c362a2c84349c83c642"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FHJ2CM5J2KX67FJAYOUOWEWUVB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Idan Shenfeld, Isha Puri, Jacob Andreas, Mehul Damani","submitted_at":"2026-07-01T17:13:35Z","abstract_excerpt":"RL with verifiable rewards (RLVR) has emerged as a powerful paradigm for training LMs on tasks with well-defined success metrics, such as code generation and mathematical reasoning. However, current RLVR methods optimize only what can be objectively scored, often neglecting subjective, non-verifiable aspects of human-like outputs, such as style and structure. This limitation leads to well-documented failure modes such as diversity collapse, unnatural-sounding responses, and reward hacking. We propose an adversarial generator-discriminator framework that augments verifiable rewards with a learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01181","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/2607.01181/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":"2026-07-02T01:18:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"71AWxicxN0cRJJ0hNbDeIzrIfpW/aCN57HB5VTZlDBW+vYOekBw2gyoiWibRiz+8e7w2GO9gRSuhxncnJZBsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T13:27:32.451909Z"},"content_sha256":"650a971526a3a318a348a1d7825df6e78a77a1e4bfca0bc86eaaa80debe9d535","schema_version":"1.0","event_id":"sha256:650a971526a3a318a348a1d7825df6e78a77a1e4bfca0bc86eaaa80debe9d535"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FHJ2CM5J2KX67FJAYOUOWEWUVB/bundle.json","state_url":"https://pith.science/pith/FHJ2CM5J2KX67FJAYOUOWEWUVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FHJ2CM5J2KX67FJAYOUOWEWUVB/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":"2026-07-03T13:27:32Z","links":{"resolver":"https://pith.science/pith/FHJ2CM5J2KX67FJAYOUOWEWUVB","bundle":"https://pith.science/pith/FHJ2CM5J2KX67FJAYOUOWEWUVB/bundle.json","state":"https://pith.science/pith/FHJ2CM5J2KX67FJAYOUOWEWUVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FHJ2CM5J2KX67FJAYOUOWEWUVB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FHJ2CM5J2KX67FJAYOUOWEWUVB","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":"acb9abce2599b8ca6ed6a92465b78b88072dfd91538e36a8b1ed6127057aa181","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T17:13:35Z","title_canon_sha256":"d84893a6c9836fdee3dd609b63cf96f6e3793430bd580a4e9af5393923248a01"},"schema_version":"1.0","source":{"id":"2607.01181","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01181","created_at":"2026-07-02T01:18:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01181v1","created_at":"2026-07-02T01:18:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01181","created_at":"2026-07-02T01:18:31Z"},{"alias_kind":"pith_short_12","alias_value":"FHJ2CM5J2KX6","created_at":"2026-07-02T01:18:31Z"},{"alias_kind":"pith_short_16","alias_value":"FHJ2CM5J2KX67FJA","created_at":"2026-07-02T01:18:31Z"},{"alias_kind":"pith_short_8","alias_value":"FHJ2CM5J","created_at":"2026-07-02T01:18:31Z"}],"graph_snapshots":[{"event_id":"sha256:650a971526a3a318a348a1d7825df6e78a77a1e4bfca0bc86eaaa80debe9d535","target":"graph","created_at":"2026-07-02T01:18:31Z","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/2607.01181/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"RL with verifiable rewards (RLVR) has emerged as a powerful paradigm for training LMs on tasks with well-defined success metrics, such as code generation and mathematical reasoning. However, current RLVR methods optimize only what can be objectively scored, often neglecting subjective, non-verifiable aspects of human-like outputs, such as style and structure. This limitation leads to well-documented failure modes such as diversity collapse, unnatural-sounding responses, and reward hacking. We propose an adversarial generator-discriminator framework that augments verifiable rewards with a learn","authors_text":"Idan Shenfeld, Isha Puri, Jacob Andreas, Mehul Damani","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T17:13:35Z","title":"Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01181","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:cd3755f38d72c0d1cc9728897b83e578d21268c8fd9a6c362a2c84349c83c642","target":"record","created_at":"2026-07-02T01:18:31Z","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":"acb9abce2599b8ca6ed6a92465b78b88072dfd91538e36a8b1ed6127057aa181","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T17:13:35Z","title_canon_sha256":"d84893a6c9836fdee3dd609b63cf96f6e3793430bd580a4e9af5393923248a01"},"schema_version":"1.0","source":{"id":"2607.01181","kind":"arxiv","version":1}},"canonical_sha256":"29d3a133a9d2afef9520c3a8eb12d4a8407a78f88d0463c38c416fe62197ff05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29d3a133a9d2afef9520c3a8eb12d4a8407a78f88d0463c38c416fe62197ff05","first_computed_at":"2026-07-02T01:18:31.913189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:18:31.913189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LtToMB0T/1pE4qjqLhrtbi9CQXNXZX0tiyPlcZ7scAclq/LLQbrMn+lWP2fW+bnmZbuiv1DPBEGgEB8iehShDw==","signature_status":"signed_v1","signed_at":"2026-07-02T01:18:31.913561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01181","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd3755f38d72c0d1cc9728897b83e578d21268c8fd9a6c362a2c84349c83c642","sha256:650a971526a3a318a348a1d7825df6e78a77a1e4bfca0bc86eaaa80debe9d535"],"state_sha256":"64dfe9e37a048604004481d83ec3510ee0a8cafcabaffcb6781d2fd5ab96614f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w46LNAZsA25MF7KkIHdA9PXKNkrAPOCkyconurFqu4AxoaZhgwh2ZvCDIv0xHBjA3OqcddZi/5eQ7dbqSLMFCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T13:27:32.453996Z","bundle_sha256":"460e32c333ce65f7200f4a6b01895c7d9fe4b7ffe29f71094377e1956989ec81"}}