{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QWXZ7FAB5L2IMTHGIO6Y4TESFW","short_pith_number":"pith:QWXZ7FAB","canonical_record":{"source":{"id":"2406.02756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T20:21:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"72d0d3aeeab2d020ca6c4b0265db1b2f540bb60a24183d995dfd69e6fecba1ba","abstract_canon_sha256":"532d86043c09ab0e67d488019532da96a5b830ff84e82eef82caf4db10b9a021"},"schema_version":"1.0"},"canonical_sha256":"85af9f9401eaf4864ce643bd8e4c922d972386b9e8f1ea0b49b7d5d71d324f1c","source":{"kind":"arxiv","id":"2406.02756","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02756","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02756v1","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02756","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"pith_short_12","alias_value":"QWXZ7FAB5L2I","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"pith_short_16","alias_value":"QWXZ7FAB5L2IMTHG","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"pith_short_8","alias_value":"QWXZ7FAB","created_at":"2026-07-05T08:27:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QWXZ7FAB5L2IMTHGIO6Y4TESFW","target":"record","payload":{"canonical_record":{"source":{"id":"2406.02756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T20:21:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"72d0d3aeeab2d020ca6c4b0265db1b2f540bb60a24183d995dfd69e6fecba1ba","abstract_canon_sha256":"532d86043c09ab0e67d488019532da96a5b830ff84e82eef82caf4db10b9a021"},"schema_version":"1.0"},"canonical_sha256":"85af9f9401eaf4864ce643bd8e4c922d972386b9e8f1ea0b49b7d5d71d324f1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:29.729055Z","signature_b64":"fsxRBshmw89nZN4byv5uKAn8Lzs3RNURjyx1jYWWHr5RREK39fHwLPD4YFo7aGo/j+XGEyRozAecDI+KqAOsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85af9f9401eaf4864ce643bd8e4c922d972386b9e8f1ea0b49b7d5d71d324f1c","last_reissued_at":"2026-07-05T08:27:29.728568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:29.728568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.02756","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":"2026-07-05T08:27:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ngi+sj7/+a2ADLUrLQD79HFUxMGh5PXllm8XUn974go1vkrcah/NcRqcNAZCZGRSJ76B7Dk3UQpjQzYvjUg2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:18:40.244721Z"},"content_sha256":"d96d59cbef82ac2c1eaa1f7c1cb5056b151897cfc60a539dd4c4990a4608c5ec","schema_version":"1.0","event_id":"sha256:d96d59cbef82ac2c1eaa1f7c1cb5056b151897cfc60a539dd4c4990a4608c5ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QWXZ7FAB5L2IMTHGIO6Y4TESFW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Large Language Models via Fine-grained Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dehong Xu, Faisal Ladhak, Jaeyoung Do, Liang Qiu, Minseok Kim","submitted_at":"2024-06-04T20:21:45Z","abstract_excerpt":"Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human feedback (RLHF) to improve model alignment, which works by transforming coarse human preferences of LLM outputs into a feedback signal that guides the model learning process. However, because this approach operates on sequence-level feedback, it lacks the precision to identify the exact parts of the output affecting user preferences. To address this gap, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02756","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/2406.02756/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":"2026-07-05T08:27:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"08s1j+hsZtTiijkj5xbWSnXnPNV7ftyLTOrYYXgDBQ7Ig9LIGcM2+DhW25/XEm457BYCs+vobALHdG3UpWdQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:18:40.245237Z"},"content_sha256":"dd0b8cceb647e89c78ce108cc7f46a0ad342c3efc63170f2e490027b2a17d4eb","schema_version":"1.0","event_id":"sha256:dd0b8cceb647e89c78ce108cc7f46a0ad342c3efc63170f2e490027b2a17d4eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QWXZ7FAB5L2IMTHGIO6Y4TESFW/bundle.json","state_url":"https://pith.science/pith/QWXZ7FAB5L2IMTHGIO6Y4TESFW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QWXZ7FAB5L2IMTHGIO6Y4TESFW/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":"2026-08-10T08:18:40Z","links":{"resolver":"https://pith.science/pith/QWXZ7FAB5L2IMTHGIO6Y4TESFW","bundle":"https://pith.science/pith/QWXZ7FAB5L2IMTHGIO6Y4TESFW/bundle.json","state":"https://pith.science/pith/QWXZ7FAB5L2IMTHGIO6Y4TESFW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QWXZ7FAB5L2IMTHGIO6Y4TESFW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QWXZ7FAB5L2IMTHGIO6Y4TESFW","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":"532d86043c09ab0e67d488019532da96a5b830ff84e82eef82caf4db10b9a021","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T20:21:45Z","title_canon_sha256":"72d0d3aeeab2d020ca6c4b0265db1b2f540bb60a24183d995dfd69e6fecba1ba"},"schema_version":"1.0","source":{"id":"2406.02756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02756","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02756v1","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02756","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"pith_short_12","alias_value":"QWXZ7FAB5L2I","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"pith_short_16","alias_value":"QWXZ7FAB5L2IMTHG","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"pith_short_8","alias_value":"QWXZ7FAB","created_at":"2026-07-05T08:27:29Z"}],"graph_snapshots":[{"event_id":"sha256:dd0b8cceb647e89c78ce108cc7f46a0ad342c3efc63170f2e490027b2a17d4eb","target":"graph","created_at":"2026-07-05T08:27:29Z","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/2406.02756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human feedback (RLHF) to improve model alignment, which works by transforming coarse human preferences of LLM outputs into a feedback signal that guides the model learning process. However, because this approach operates on sequence-level feedback, it lacks the precision to identify the exact parts of the output affecting user preferences. To address this gap, we pr","authors_text":"Dehong Xu, Faisal Ladhak, Jaeyoung Do, Liang Qiu, Minseok Kim","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T20:21:45Z","title":"Aligning Large Language Models via Fine-grained Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02756","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:d96d59cbef82ac2c1eaa1f7c1cb5056b151897cfc60a539dd4c4990a4608c5ec","target":"record","created_at":"2026-07-05T08:27:29Z","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":"532d86043c09ab0e67d488019532da96a5b830ff84e82eef82caf4db10b9a021","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T20:21:45Z","title_canon_sha256":"72d0d3aeeab2d020ca6c4b0265db1b2f540bb60a24183d995dfd69e6fecba1ba"},"schema_version":"1.0","source":{"id":"2406.02756","kind":"arxiv","version":1}},"canonical_sha256":"85af9f9401eaf4864ce643bd8e4c922d972386b9e8f1ea0b49b7d5d71d324f1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85af9f9401eaf4864ce643bd8e4c922d972386b9e8f1ea0b49b7d5d71d324f1c","first_computed_at":"2026-07-05T08:27:29.728568Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:29.728568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fsxRBshmw89nZN4byv5uKAn8Lzs3RNURjyx1jYWWHr5RREK39fHwLPD4YFo7aGo/j+XGEyRozAecDI+KqAOsBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:29.729055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d96d59cbef82ac2c1eaa1f7c1cb5056b151897cfc60a539dd4c4990a4608c5ec","sha256:dd0b8cceb647e89c78ce108cc7f46a0ad342c3efc63170f2e490027b2a17d4eb"],"state_sha256":"2b543292571170c9317ba465a203518a845a65af9d271871a6e01133d0d95d4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qcuazdkqrx/nocnw2h4eETOcFCqDeHoTWTbBWaTcCkfsyNP2y44kJSGT0Gr2JfshO+++jJKwN2zS3PPd8WXQBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:18:40.249244Z","bundle_sha256":"11f9019a8176ce71f4f505c91f541c7822b95adc3cbe1f96578e7744163cbb82"}}