{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IKDUZI2LHKELS5MJ3XDCACEL5H","short_pith_number":"pith:IKDUZI2L","canonical_record":{"source":{"id":"2412.04305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T16:26:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e216b33b6660bb9b5fe9b11a6b21c764e96b6d3b1569c86e03b5c20d53942783","abstract_canon_sha256":"ec3e6177bbc3add6f239ee993403add904c344910af29a95d2e00e7139b5d992"},"schema_version":"1.0"},"canonical_sha256":"42874ca34b3a88b97589ddc620088be9d6d7920809784a1157858c378d645fa0","source":{"kind":"arxiv","id":"2412.04305","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04305","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04305v1","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04305","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_12","alias_value":"IKDUZI2LHKEL","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_16","alias_value":"IKDUZI2LHKELS5MJ","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_8","alias_value":"IKDUZI2L","created_at":"2026-07-05T09:45:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IKDUZI2LHKELS5MJ3XDCACEL5H","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T16:26:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e216b33b6660bb9b5fe9b11a6b21c764e96b6d3b1569c86e03b5c20d53942783","abstract_canon_sha256":"ec3e6177bbc3add6f239ee993403add904c344910af29a95d2e00e7139b5d992"},"schema_version":"1.0"},"canonical_sha256":"42874ca34b3a88b97589ddc620088be9d6d7920809784a1157858c378d645fa0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:02.235956Z","signature_b64":"F6HSd5SRtUex6Nk/QsLVef6hb9PadvpYEul2QO4Dw6Uf9aBhofTnUO0IvvkjLpnIqD+mIqb7IS/0AL2d4yIVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42874ca34b3a88b97589ddc620088be9d6d7920809784a1157858c378d645fa0","last_reissued_at":"2026-07-05T09:45:02.235473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:02.235473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04305","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":"2026-07-05T09:45:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qSYlB1Hop9lb2NOnnX2QaQ174rHja2wuXuzwrQVAgtQTEfh8GQai0nPtBMP2Y8sxudRR5EAlOECMY1/Tmla4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:18:19.482352Z"},"content_sha256":"d10895c9641b86ff6d59b5b28762a378962f3eca24b78f5e91320663b72afd01","schema_version":"1.0","event_id":"sha256:d10895c9641b86ff6d59b5b28762a378962f3eca24b78f5e91320663b72afd01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IKDUZI2LHKELS5MJ3XDCACEL5H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ALMA: Alignment with Minimal Annotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrew Cohen, Chunting Zhou, Jason Weston, Leonid Shamis, Luke Zettlemoyer, Marjan Ghazvininejad, Michihiro Yasunaga","submitted_at":"2024-12-05T16:26:31Z","abstract_excerpt":"Recent approaches to large language model (LLM) alignment typically require millions of human annotations or rely on external aligned models for synthetic data generation. This paper introduces ALMA: Alignment with Minimal Annotation, demonstrating that effective alignment can be achieved using only 9,000 labeled examples -- less than 1% of conventional approaches. ALMA generates large amounts of high-quality synthetic alignment data through new techniques: diverse prompt synthesis via few-shot learning, diverse response generation with multiple model checkpoints, and judge (reward model) enha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04305","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/2412.04305/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":"2026-07-05T09:45:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tIerLFlGqs3iCqdhxTpVw2g5rBvAgnas6V9xwOz1RTUwJazOoIWdd6M8FK+woL7BVOlLjb9A1Ynw/imn14O2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:18:19.482891Z"},"content_sha256":"f5b0580dca2370570465625cf9c51c2c54ede48476731ff4b06bd1151c6590f7","schema_version":"1.0","event_id":"sha256:f5b0580dca2370570465625cf9c51c2c54ede48476731ff4b06bd1151c6590f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IKDUZI2LHKELS5MJ3XDCACEL5H/bundle.json","state_url":"https://pith.science/pith/IKDUZI2LHKELS5MJ3XDCACEL5H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IKDUZI2LHKELS5MJ3XDCACEL5H/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":"2026-08-09T02:18:19Z","links":{"resolver":"https://pith.science/pith/IKDUZI2LHKELS5MJ3XDCACEL5H","bundle":"https://pith.science/pith/IKDUZI2LHKELS5MJ3XDCACEL5H/bundle.json","state":"https://pith.science/pith/IKDUZI2LHKELS5MJ3XDCACEL5H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IKDUZI2LHKELS5MJ3XDCACEL5H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IKDUZI2LHKELS5MJ3XDCACEL5H","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":"ec3e6177bbc3add6f239ee993403add904c344910af29a95d2e00e7139b5d992","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T16:26:31Z","title_canon_sha256":"e216b33b6660bb9b5fe9b11a6b21c764e96b6d3b1569c86e03b5c20d53942783"},"schema_version":"1.0","source":{"id":"2412.04305","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04305","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04305v1","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04305","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_12","alias_value":"IKDUZI2LHKEL","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_16","alias_value":"IKDUZI2LHKELS5MJ","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_8","alias_value":"IKDUZI2L","created_at":"2026-07-05T09:45:02Z"}],"graph_snapshots":[{"event_id":"sha256:f5b0580dca2370570465625cf9c51c2c54ede48476731ff4b06bd1151c6590f7","target":"graph","created_at":"2026-07-05T09:45:02Z","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/2412.04305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent approaches to large language model (LLM) alignment typically require millions of human annotations or rely on external aligned models for synthetic data generation. This paper introduces ALMA: Alignment with Minimal Annotation, demonstrating that effective alignment can be achieved using only 9,000 labeled examples -- less than 1% of conventional approaches. ALMA generates large amounts of high-quality synthetic alignment data through new techniques: diverse prompt synthesis via few-shot learning, diverse response generation with multiple model checkpoints, and judge (reward model) enha","authors_text":"Andrew Cohen, Chunting Zhou, Jason Weston, Leonid Shamis, Luke Zettlemoyer, Marjan Ghazvininejad, Michihiro Yasunaga","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T16:26:31Z","title":"ALMA: Alignment with Minimal Annotation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04305","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:d10895c9641b86ff6d59b5b28762a378962f3eca24b78f5e91320663b72afd01","target":"record","created_at":"2026-07-05T09:45:02Z","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":"ec3e6177bbc3add6f239ee993403add904c344910af29a95d2e00e7139b5d992","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T16:26:31Z","title_canon_sha256":"e216b33b6660bb9b5fe9b11a6b21c764e96b6d3b1569c86e03b5c20d53942783"},"schema_version":"1.0","source":{"id":"2412.04305","kind":"arxiv","version":1}},"canonical_sha256":"42874ca34b3a88b97589ddc620088be9d6d7920809784a1157858c378d645fa0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42874ca34b3a88b97589ddc620088be9d6d7920809784a1157858c378d645fa0","first_computed_at":"2026-07-05T09:45:02.235473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:02.235473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F6HSd5SRtUex6Nk/QsLVef6hb9PadvpYEul2QO4Dw6Uf9aBhofTnUO0IvvkjLpnIqD+mIqb7IS/0AL2d4yIVAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:02.235956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04305","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d10895c9641b86ff6d59b5b28762a378962f3eca24b78f5e91320663b72afd01","sha256:f5b0580dca2370570465625cf9c51c2c54ede48476731ff4b06bd1151c6590f7"],"state_sha256":"e813108c582548935ca3a99ef730f74983508552df3a389a763a54433458c070"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uiuqF8AScyU8+fFdVLVg8UWz30HjHRjv05WFBoC4Rj6iQtXkZSVI/JlGWAA6KUOgWLLDOkL6Dy6FMkErf1DKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:18:19.487320Z","bundle_sha256":"75fc4ac91ced426a2018984290db4ce59bce38632469f13265d8e076c8cf01e5"}}