{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5OOVPI6MI4AQ6R2OSL5RMUBZEO","short_pith_number":"pith:5OOVPI6M","canonical_record":{"source":{"id":"2312.14591","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-22T10:29:43Z","cross_cats_sorted":[],"title_canon_sha256":"2152f0cec16b977426c0b386a59b17e4a92d099caa69f4312ed2201ae520cd33","abstract_canon_sha256":"7cee8c0be3d3a275bc458487726edd6ce36864e26ba26fe950f001eb59adc183"},"schema_version":"1.0"},"canonical_sha256":"eb9d57a3cc47010f474e92fb165039239ce5ac830872c5756a868c8103b1d32c","source":{"kind":"arxiv","id":"2312.14591","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14591","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14591v4","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14591","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"pith_short_12","alias_value":"5OOVPI6MI4AQ","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"pith_short_16","alias_value":"5OOVPI6MI4AQ6R2O","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"pith_short_8","alias_value":"5OOVPI6M","created_at":"2026-07-05T08:28:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5OOVPI6MI4AQ6R2OSL5RMUBZEO","target":"record","payload":{"canonical_record":{"source":{"id":"2312.14591","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-22T10:29:43Z","cross_cats_sorted":[],"title_canon_sha256":"2152f0cec16b977426c0b386a59b17e4a92d099caa69f4312ed2201ae520cd33","abstract_canon_sha256":"7cee8c0be3d3a275bc458487726edd6ce36864e26ba26fe950f001eb59adc183"},"schema_version":"1.0"},"canonical_sha256":"eb9d57a3cc47010f474e92fb165039239ce5ac830872c5756a868c8103b1d32c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:04.440882Z","signature_b64":"AT46mEkNEmOcBGNq2CAPmS5oKsUcd4ic0++2rxF8feEKHyK1tqxst9kUujEnoy+dGmtMy2fiZS8PLWE0ZzoiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb9d57a3cc47010f474e92fb165039239ce5ac830872c5756a868c8103b1d32c","last_reissued_at":"2026-07-05T08:28:04.440456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:04.440456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.14591","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yNnKmhL7ME1tK1kex0dcqguVwcdrWOsJKQ1g4ARPEpXdJ9LomIPK+G5QGhvMaal6MpQ0yCUFJVRtvs0WyP+RBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:47:48.862798Z"},"content_sha256":"0afd889c5fecf4bb0d31e35b7392a9426fc095b567f8c4c34e65ab4100a655e0","schema_version":"1.0","event_id":"sha256:0afd889c5fecf4bb0d31e35b7392a9426fc095b567f8c4c34e65ab4100a655e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5OOVPI6MI4AQ6R2OSL5RMUBZEO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reasons to Reject? Aligning Language Models with Judgments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deng Cai, Shuming Shi, Wai Lam, Weiwen Xu, Zhisong Zhang","submitted_at":"2023-12-22T10:29:43Z","abstract_excerpt":"As humans, we consistently interact with our peers and receive feedback in the form of natural language. This language feedback allows us to maintain appropriate behavior, and rectify potential errors. The question arises naturally: can we use language feedback to align large language models (LLMs)? In contrast to previous research that aligns LLMs with scalar rewards, we present the first systematic exploration of alignment through the lens of language feedback (i.e., judgment). We start with an in-depth investigation of potential methods that can be adapted for aligning LLMs with judgments, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14591","kind":"arxiv","version":4},"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/2312.14591/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":"2026-07-05T08:28:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y6XGH1wRQUKrDwrOjM6YGbc1iCXhfTVPU1KC4tHqbPJo5gF13KeG5sMZD0QETP2l8iFUzxwYvwx2jeWNIPpiCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:47:48.863163Z"},"content_sha256":"78751a4c4dfef2ffd0b3dc2dd40e90579e03d392132326fa750d361c702160ed","schema_version":"1.0","event_id":"sha256:78751a4c4dfef2ffd0b3dc2dd40e90579e03d392132326fa750d361c702160ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5OOVPI6MI4AQ6R2OSL5RMUBZEO/bundle.json","state_url":"https://pith.science/pith/5OOVPI6MI4AQ6R2OSL5RMUBZEO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5OOVPI6MI4AQ6R2OSL5RMUBZEO/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":"2026-07-06T13:47:48Z","links":{"resolver":"https://pith.science/pith/5OOVPI6MI4AQ6R2OSL5RMUBZEO","bundle":"https://pith.science/pith/5OOVPI6MI4AQ6R2OSL5RMUBZEO/bundle.json","state":"https://pith.science/pith/5OOVPI6MI4AQ6R2OSL5RMUBZEO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5OOVPI6MI4AQ6R2OSL5RMUBZEO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5OOVPI6MI4AQ6R2OSL5RMUBZEO","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":"7cee8c0be3d3a275bc458487726edd6ce36864e26ba26fe950f001eb59adc183","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-22T10:29:43Z","title_canon_sha256":"2152f0cec16b977426c0b386a59b17e4a92d099caa69f4312ed2201ae520cd33"},"schema_version":"1.0","source":{"id":"2312.14591","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14591","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14591v4","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14591","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"pith_short_12","alias_value":"5OOVPI6MI4AQ","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"pith_short_16","alias_value":"5OOVPI6MI4AQ6R2O","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"pith_short_8","alias_value":"5OOVPI6M","created_at":"2026-07-05T08:28:04Z"}],"graph_snapshots":[{"event_id":"sha256:78751a4c4dfef2ffd0b3dc2dd40e90579e03d392132326fa750d361c702160ed","target":"graph","created_at":"2026-07-05T08:28:04Z","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/2312.14591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As humans, we consistently interact with our peers and receive feedback in the form of natural language. This language feedback allows us to maintain appropriate behavior, and rectify potential errors. The question arises naturally: can we use language feedback to align large language models (LLMs)? In contrast to previous research that aligns LLMs with scalar rewards, we present the first systematic exploration of alignment through the lens of language feedback (i.e., judgment). We start with an in-depth investigation of potential methods that can be adapted for aligning LLMs with judgments, ","authors_text":"Deng Cai, Shuming Shi, Wai Lam, Weiwen Xu, Zhisong Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-22T10:29:43Z","title":"Reasons to Reject? Aligning Language Models with Judgments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14591","kind":"arxiv","version":4},"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":"sha256:0afd889c5fecf4bb0d31e35b7392a9426fc095b567f8c4c34e65ab4100a655e0","target":"record","created_at":"2026-07-05T08:28:04Z","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":"7cee8c0be3d3a275bc458487726edd6ce36864e26ba26fe950f001eb59adc183","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-22T10:29:43Z","title_canon_sha256":"2152f0cec16b977426c0b386a59b17e4a92d099caa69f4312ed2201ae520cd33"},"schema_version":"1.0","source":{"id":"2312.14591","kind":"arxiv","version":4}},"canonical_sha256":"eb9d57a3cc47010f474e92fb165039239ce5ac830872c5756a868c8103b1d32c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb9d57a3cc47010f474e92fb165039239ce5ac830872c5756a868c8103b1d32c","first_computed_at":"2026-07-05T08:28:04.440456Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:04.440456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AT46mEkNEmOcBGNq2CAPmS5oKsUcd4ic0++2rxF8feEKHyK1tqxst9kUujEnoy+dGmtMy2fiZS8PLWE0ZzoiAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:04.440882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.14591","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0afd889c5fecf4bb0d31e35b7392a9426fc095b567f8c4c34e65ab4100a655e0","sha256:78751a4c4dfef2ffd0b3dc2dd40e90579e03d392132326fa750d361c702160ed"],"state_sha256":"fdf34a9edba83cdb3cc26fbc0bfa92c83a7a5e45584ade2410324a94f4402033"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J+gBgk4k3fEPfwIsJ/qcAqFfbFqcia+eK1Yyte21PxjzHoLINJTXogVLQxLtVE3st2IvZ6/NeiIPNugGeYzMCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T13:47:48.865114Z","bundle_sha256":"c9e6facb71d154b5f280ae9e12f9569b30658751c344f4417a0f116d1f808d62"}}