{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VJ4I5GYPUOI53I2WVGDV6ZJ3TK","short_pith_number":"pith:VJ4I5GYP","canonical_record":{"source":{"id":"2305.10425","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T17:57:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c9936b4b9dd69545e9d57c36edcfa92fb9ee754f045937b79fe4495b323f7ef6","abstract_canon_sha256":"116be9e20f6ec229e2f914482a223025774a8175a4563e2b31efcfd75783e5c9"},"schema_version":"1.0"},"canonical_sha256":"aa788e9b0fa391dda356a9875f653b9a889ef6afbc845339768248761f7a717b","source":{"kind":"arxiv","id":"2305.10425","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10425","created_at":"2026-07-05T06:11:14Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10425v1","created_at":"2026-07-05T06:11:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10425","created_at":"2026-07-05T06:11:14Z"},{"alias_kind":"pith_short_12","alias_value":"VJ4I5GYPUOI5","created_at":"2026-07-05T06:11:14Z"},{"alias_kind":"pith_short_16","alias_value":"VJ4I5GYPUOI53I2W","created_at":"2026-07-05T06:11:14Z"},{"alias_kind":"pith_short_8","alias_value":"VJ4I5GYP","created_at":"2026-07-05T06:11:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VJ4I5GYPUOI53I2WVGDV6ZJ3TK","target":"record","payload":{"canonical_record":{"source":{"id":"2305.10425","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T17:57:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c9936b4b9dd69545e9d57c36edcfa92fb9ee754f045937b79fe4495b323f7ef6","abstract_canon_sha256":"116be9e20f6ec229e2f914482a223025774a8175a4563e2b31efcfd75783e5c9"},"schema_version":"1.0"},"canonical_sha256":"aa788e9b0fa391dda356a9875f653b9a889ef6afbc845339768248761f7a717b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:14.347344Z","signature_b64":"Jh+6r6AhP8xn1EO45Nm/f8rB+sDM2YXkz+eU0uDoLbZEMXw5EwCJdzMLr4Gsrbkr6RTN5j8Qs1KbvbHMwEhGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa788e9b0fa391dda356a9875f653b9a889ef6afbc845339768248761f7a717b","last_reissued_at":"2026-07-05T06:11:14.346814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:14.346814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.10425","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":"2026-07-05T06:11:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tNwYZ7cB3vXmYWb/kMgVTon06Z4Job5RituRzVftXNckKRwCcEXZhJ94gNDMW1w7PWdfbgOY864Z26v4ycouBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T05:26:53.249988Z"},"content_sha256":"e2658e5323719b361041edecc0c4db9687e05511c667ea51a25409f1785c4ffe","schema_version":"1.0","event_id":"sha256:e2658e5323719b361041edecc0c4db9687e05511c667ea51a25409f1785c4ffe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VJ4I5GYPUOI53I2WVGDV6ZJ3TK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Misha Khalman, Mohammad Saleh, Peter J. Liu, Rishabh Joshi, Tianqi Liu, Yao Zhao","submitted_at":"2023-05-17T17:57:10Z","abstract_excerpt":"Learning from human feedback has been shown to be effective at aligning language models with human preferences. Past work has often relied on Reinforcement Learning from Human Feedback (RLHF), which optimizes the language model using reward scores assigned from a reward model trained on human preference data. In this work we show how the recently introduced Sequence Likelihood Calibration (SLiC), can also be used to effectively learn from human preferences (SLiC-HF). Furthermore, we demonstrate this can be done with human feedback data collected for a different model, similar to off-policy, of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10425","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/2305.10425/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":"2026-07-05T06:11:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7RyiJxJONAi9bPKiSoW1af7MPw/iwSN7vek0txselNJnZmOltrVdczSUyf2y64/nwC+mEsRvgaRGGJJHBAj7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T05:26:53.254883Z"},"content_sha256":"b182b8c9e296e56c6ec2a9b8bdb255a32f1e62f01948bb26bd36cff438be1fda","schema_version":"1.0","event_id":"sha256:b182b8c9e296e56c6ec2a9b8bdb255a32f1e62f01948bb26bd36cff438be1fda"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJ4I5GYPUOI53I2WVGDV6ZJ3TK/bundle.json","state_url":"https://pith.science/pith/VJ4I5GYPUOI53I2WVGDV6ZJ3TK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJ4I5GYPUOI53I2WVGDV6ZJ3TK/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":"2026-08-15T05:26:53Z","links":{"resolver":"https://pith.science/pith/VJ4I5GYPUOI53I2WVGDV6ZJ3TK","bundle":"https://pith.science/pith/VJ4I5GYPUOI53I2WVGDV6ZJ3TK/bundle.json","state":"https://pith.science/pith/VJ4I5GYPUOI53I2WVGDV6ZJ3TK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJ4I5GYPUOI53I2WVGDV6ZJ3TK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VJ4I5GYPUOI53I2WVGDV6ZJ3TK","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":"116be9e20f6ec229e2f914482a223025774a8175a4563e2b31efcfd75783e5c9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T17:57:10Z","title_canon_sha256":"c9936b4b9dd69545e9d57c36edcfa92fb9ee754f045937b79fe4495b323f7ef6"},"schema_version":"1.0","source":{"id":"2305.10425","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10425","created_at":"2026-07-05T06:11:14Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10425v1","created_at":"2026-07-05T06:11:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10425","created_at":"2026-07-05T06:11:14Z"},{"alias_kind":"pith_short_12","alias_value":"VJ4I5GYPUOI5","created_at":"2026-07-05T06:11:14Z"},{"alias_kind":"pith_short_16","alias_value":"VJ4I5GYPUOI53I2W","created_at":"2026-07-05T06:11:14Z"},{"alias_kind":"pith_short_8","alias_value":"VJ4I5GYP","created_at":"2026-07-05T06:11:14Z"}],"graph_snapshots":[{"event_id":"sha256:b182b8c9e296e56c6ec2a9b8bdb255a32f1e62f01948bb26bd36cff438be1fda","target":"graph","created_at":"2026-07-05T06:11:14Z","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/2305.10425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning from human feedback has been shown to be effective at aligning language models with human preferences. Past work has often relied on Reinforcement Learning from Human Feedback (RLHF), which optimizes the language model using reward scores assigned from a reward model trained on human preference data. In this work we show how the recently introduced Sequence Likelihood Calibration (SLiC), can also be used to effectively learn from human preferences (SLiC-HF). Furthermore, we demonstrate this can be done with human feedback data collected for a different model, similar to off-policy, of","authors_text":"Misha Khalman, Mohammad Saleh, Peter J. Liu, Rishabh Joshi, Tianqi Liu, Yao Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T17:57:10Z","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10425","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:e2658e5323719b361041edecc0c4db9687e05511c667ea51a25409f1785c4ffe","target":"record","created_at":"2026-07-05T06:11:14Z","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":"116be9e20f6ec229e2f914482a223025774a8175a4563e2b31efcfd75783e5c9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T17:57:10Z","title_canon_sha256":"c9936b4b9dd69545e9d57c36edcfa92fb9ee754f045937b79fe4495b323f7ef6"},"schema_version":"1.0","source":{"id":"2305.10425","kind":"arxiv","version":1}},"canonical_sha256":"aa788e9b0fa391dda356a9875f653b9a889ef6afbc845339768248761f7a717b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa788e9b0fa391dda356a9875f653b9a889ef6afbc845339768248761f7a717b","first_computed_at":"2026-07-05T06:11:14.346814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:14.346814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jh+6r6AhP8xn1EO45Nm/f8rB+sDM2YXkz+eU0uDoLbZEMXw5EwCJdzMLr4Gsrbkr6RTN5j8Qs1KbvbHMwEhGDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:14.347344Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10425","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2658e5323719b361041edecc0c4db9687e05511c667ea51a25409f1785c4ffe","sha256:b182b8c9e296e56c6ec2a9b8bdb255a32f1e62f01948bb26bd36cff438be1fda"],"state_sha256":"00f97fd314c0009a1cb4f36dbe2bed7c2ae37d63b3fcb0d7657ab7de975d4873"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jf0RPOQQYCGr6d4J+ZP6baBb3jEb4bV96x3nhC28KbA9SucH2kSh+NjQdau1vr9bb09AK4i+fVuYYMpYs++iAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T05:26:53.259944Z","bundle_sha256":"1e932f6cc8d24db04ab49b4a9fe57fceddd8f1edd5f7c24450cf33a6458c1ca3"}}