{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RZWALUTGVRIBVKIBFRC7SKCPIJ","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":"abfb4b5d5e59f296bec1e13ea31c22b67661c82c227a42bff753e54c4544dcf1","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T23:13:56Z","title_canon_sha256":"3c6b61cd868acd48f84f9938ed35d2191ce9af05a14d759d44f6428999103ee1"},"schema_version":"1.0","source":{"id":"2406.00888","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00888","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00888v2","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00888","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"pith_short_12","alias_value":"RZWALUTGVRIB","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"pith_short_16","alias_value":"RZWALUTGVRIBVKIB","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"pith_short_8","alias_value":"RZWALUTG","created_at":"2026-07-05T10:51:03Z"}],"graph_snapshots":[{"event_id":"sha256:425ce33e4d4626fe0042e6466a8c9b3064caf2d854194b237853ddf449ba6eab","target":"graph","created_at":"2026-07-05T10:51:03Z","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/2406.00888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models are aligned to emulate the collective voice of many, resulting in outputs that align with no one in particular. Steering LLMs away from generic output is possible through supervised finetuning or RLHF, but requires prohibitively large datasets for new ad-hoc tasks. We argue that it is instead possible to align an LLM to a specific setting by leveraging a very small number (< 10) of demonstrations as feedback. Our method, Demonstration ITerated Task Optimization (DITTO), directly aligns language model outputs to a user's demonstrated behaviors. Derived using ideas from online im","authors_text":"Diyi Yang, Hyundong Cho, Joey Hejna, Michael S. Bernstein, Michelle S. Lam, Omar Shaikh, Yijia Shao","cross_cats":["cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T23:13:56Z","title":"Aligning Language Models with Demonstrated Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00888","kind":"arxiv","version":2},"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:f63bac7e0be9a5e03eec5e1896f0e8c767951a25b47270f91a1e02da6529c9e0","target":"record","created_at":"2026-07-05T10:51:03Z","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":"abfb4b5d5e59f296bec1e13ea31c22b67661c82c227a42bff753e54c4544dcf1","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T23:13:56Z","title_canon_sha256":"3c6b61cd868acd48f84f9938ed35d2191ce9af05a14d759d44f6428999103ee1"},"schema_version":"1.0","source":{"id":"2406.00888","kind":"arxiv","version":2}},"canonical_sha256":"8e6c05d266ac501aa9012c45f9284f4258a2d5ffd84eb4a1f0491568c472f593","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e6c05d266ac501aa9012c45f9284f4258a2d5ffd84eb4a1f0491568c472f593","first_computed_at":"2026-07-05T10:51:03.804182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:03.804182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0rg0UfjKlov7l5hXciBHUR7N1dvtDxN0h1QNskR86ddFVY9OIqDp49CIvfrKZldhJi1U841onQn/tjQetAwIDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:03.804674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00888","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f63bac7e0be9a5e03eec5e1896f0e8c767951a25b47270f91a1e02da6529c9e0","sha256:425ce33e4d4626fe0042e6466a8c9b3064caf2d854194b237853ddf449ba6eab"],"state_sha256":"6525a7ca80df7a5dbe74e6fab40352641a1de9d83a987a28f3136631246036a5"}