{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VJNDN3E4NDV7SYKXB4H7AAGRUC","short_pith_number":"pith:VJNDN3E4","canonical_record":{"source":{"id":"2308.06259","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-11T17:47:54Z","cross_cats_sorted":[],"title_canon_sha256":"eac7c416539e6376e8808a322468f059f279e990eec4a462c39941b21a17aa17","abstract_canon_sha256":"020ea4b150f456e9302f45cb58631900e78849606f8a56c5bf7b71b080d0707d"},"schema_version":"1.0"},"canonical_sha256":"aa5a36ec9c68ebf961570f0ff000d1a0850a5188c1034b32ad8322ed0ff34db2","source":{"kind":"arxiv","id":"2308.06259","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.06259","created_at":"2026-07-05T07:54:50Z"},{"alias_kind":"arxiv_version","alias_value":"2308.06259v3","created_at":"2026-07-05T07:54:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06259","created_at":"2026-07-05T07:54:50Z"},{"alias_kind":"pith_short_12","alias_value":"VJNDN3E4NDV7","created_at":"2026-07-05T07:54:50Z"},{"alias_kind":"pith_short_16","alias_value":"VJNDN3E4NDV7SYKX","created_at":"2026-07-05T07:54:50Z"},{"alias_kind":"pith_short_8","alias_value":"VJNDN3E4","created_at":"2026-07-05T07:54:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VJNDN3E4NDV7SYKXB4H7AAGRUC","target":"record","payload":{"canonical_record":{"source":{"id":"2308.06259","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-11T17:47:54Z","cross_cats_sorted":[],"title_canon_sha256":"eac7c416539e6376e8808a322468f059f279e990eec4a462c39941b21a17aa17","abstract_canon_sha256":"020ea4b150f456e9302f45cb58631900e78849606f8a56c5bf7b71b080d0707d"},"schema_version":"1.0"},"canonical_sha256":"aa5a36ec9c68ebf961570f0ff000d1a0850a5188c1034b32ad8322ed0ff34db2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:50.183840Z","signature_b64":"NyqtmdIao2kpLGGzM6MUmNW2ZDfgOGRj1OYtBjMpTfvAlVfNLxASQs029ERVEvoViiWn/gej9jC3M615PJrxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa5a36ec9c68ebf961570f0ff000d1a0850a5188c1034b32ad8322ed0ff34db2","last_reissued_at":"2026-07-05T07:54:50.183424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:50.183424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.06259","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:54:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QBOv882WwxyZcgGN6yW36LH7zCbBjiH8QASSAjWoahCKEKVAuzxDj/go2SYgABnpYKVXc6eaFtrp8QN095p1Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:00:08.464166Z"},"content_sha256":"db6248c412e2f5cd48a55090f6843ded81d03f8bd3b5e8527d1ed32a4fea8f4c","schema_version":"1.0","event_id":"sha256:db6248c412e2f5cd48a55090f6843ded81d03f8bd3b5e8527d1ed32a4fea8f4c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VJNDN3E4NDV7SYKXB4H7AAGRUC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Alignment with Instruction Backtranslation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunting Zhou, Jason Weston, Luke Zettlemoyer, Mike Lewis, Omer Levy, Ping Yu, Timo Schick, Xian Li","submitted_at":"2023-08-11T17:47:54Z","abstract_excerpt":"We present a scalable method to build a high quality instruction following language model by automatically labelling human-written text with corresponding instructions. Our approach, named instruction backtranslation, starts with a language model finetuned on a small amount of seed data, and a given web corpus. The seed model is used to construct training examples by generating instruction prompts for web documents (self-augmentation), and then selecting high quality examples from among these candidates (self-curation). This data is then used to finetune a stronger model. Finetuning LLaMa on t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06259","kind":"arxiv","version":3},"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/2308.06259/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":"2026-07-05T07:54:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bUrTWM6S/adg5d3GUEhTvjf58/C4u8DT5jy0IpfG4sS3NJfO9xTWuVibMD5FUyWiXU6wQQngyC4k5H57v3iqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:00:08.464796Z"},"content_sha256":"54d742860137d790901dc6e82c78a90eb03053989269080d30fc84bdcbf0c30a","schema_version":"1.0","event_id":"sha256:54d742860137d790901dc6e82c78a90eb03053989269080d30fc84bdcbf0c30a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJNDN3E4NDV7SYKXB4H7AAGRUC/bundle.json","state_url":"https://pith.science/pith/VJNDN3E4NDV7SYKXB4H7AAGRUC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJNDN3E4NDV7SYKXB4H7AAGRUC/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":"2026-08-17T13:00:08Z","links":{"resolver":"https://pith.science/pith/VJNDN3E4NDV7SYKXB4H7AAGRUC","bundle":"https://pith.science/pith/VJNDN3E4NDV7SYKXB4H7AAGRUC/bundle.json","state":"https://pith.science/pith/VJNDN3E4NDV7SYKXB4H7AAGRUC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJNDN3E4NDV7SYKXB4H7AAGRUC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VJNDN3E4NDV7SYKXB4H7AAGRUC","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":"020ea4b150f456e9302f45cb58631900e78849606f8a56c5bf7b71b080d0707d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-11T17:47:54Z","title_canon_sha256":"eac7c416539e6376e8808a322468f059f279e990eec4a462c39941b21a17aa17"},"schema_version":"1.0","source":{"id":"2308.06259","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.06259","created_at":"2026-07-05T07:54:50Z"},{"alias_kind":"arxiv_version","alias_value":"2308.06259v3","created_at":"2026-07-05T07:54:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06259","created_at":"2026-07-05T07:54:50Z"},{"alias_kind":"pith_short_12","alias_value":"VJNDN3E4NDV7","created_at":"2026-07-05T07:54:50Z"},{"alias_kind":"pith_short_16","alias_value":"VJNDN3E4NDV7SYKX","created_at":"2026-07-05T07:54:50Z"},{"alias_kind":"pith_short_8","alias_value":"VJNDN3E4","created_at":"2026-07-05T07:54:50Z"}],"graph_snapshots":[{"event_id":"sha256:54d742860137d790901dc6e82c78a90eb03053989269080d30fc84bdcbf0c30a","target":"graph","created_at":"2026-07-05T07:54:50Z","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/2308.06259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a scalable method to build a high quality instruction following language model by automatically labelling human-written text with corresponding instructions. Our approach, named instruction backtranslation, starts with a language model finetuned on a small amount of seed data, and a given web corpus. The seed model is used to construct training examples by generating instruction prompts for web documents (self-augmentation), and then selecting high quality examples from among these candidates (self-curation). This data is then used to finetune a stronger model. Finetuning LLaMa on t","authors_text":"Chunting Zhou, Jason Weston, Luke Zettlemoyer, Mike Lewis, Omer Levy, Ping Yu, Timo Schick, Xian Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-11T17:47:54Z","title":"Self-Alignment with Instruction Backtranslation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06259","kind":"arxiv","version":3},"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:db6248c412e2f5cd48a55090f6843ded81d03f8bd3b5e8527d1ed32a4fea8f4c","target":"record","created_at":"2026-07-05T07:54:50Z","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":"020ea4b150f456e9302f45cb58631900e78849606f8a56c5bf7b71b080d0707d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-11T17:47:54Z","title_canon_sha256":"eac7c416539e6376e8808a322468f059f279e990eec4a462c39941b21a17aa17"},"schema_version":"1.0","source":{"id":"2308.06259","kind":"arxiv","version":3}},"canonical_sha256":"aa5a36ec9c68ebf961570f0ff000d1a0850a5188c1034b32ad8322ed0ff34db2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa5a36ec9c68ebf961570f0ff000d1a0850a5188c1034b32ad8322ed0ff34db2","first_computed_at":"2026-07-05T07:54:50.183424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:50.183424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NyqtmdIao2kpLGGzM6MUmNW2ZDfgOGRj1OYtBjMpTfvAlVfNLxASQs029ERVEvoViiWn/gej9jC3M615PJrxBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:50.183840Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.06259","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db6248c412e2f5cd48a55090f6843ded81d03f8bd3b5e8527d1ed32a4fea8f4c","sha256:54d742860137d790901dc6e82c78a90eb03053989269080d30fc84bdcbf0c30a"],"state_sha256":"9c3888e9757a9d33a6a1b2e22b5b02c28ae2402c6647cd2e8a0f9cebbb96d899"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YlfkTXRFtLnxRjSPJEGIB4ZFcbpXe3+jGxfh592999YZ42ZhUow5SVuC6OOf3XJbKBz6uav1VeAzmO6hI1waCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T13:00:08.471183Z","bundle_sha256":"0d14daf666f6199367dc576c974fd7ccf9ea6fb13ed4f7b01c3efb6d11ff692d"}}