{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:T2FYWMG7464GG3XM6WR3IWGPT3","short_pith_number":"pith:T2FYWMG7","canonical_record":{"source":{"id":"2405.15624","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T15:13:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70c2ecb71638d8a21112d7a28845fd232b7acceb41679d8fee8a56288da5a9cb","abstract_canon_sha256":"a2e7e62b3741f41560fe8721ab2ddf69c70ce6baeb682a1078a0fa92aec30d59"},"schema_version":"1.0"},"canonical_sha256":"9e8b8b30dfe7b8636eecf5a3b458cf9ef5acdfbbb00a3ad99d653f7c58525118","source":{"kind":"arxiv","id":"2405.15624","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15624","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15624v2","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15624","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"T2FYWMG7464G","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"T2FYWMG7464GG3XM","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"T2FYWMG7","created_at":"2026-07-05T10:05:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:T2FYWMG7464GG3XM6WR3IWGPT3","target":"record","payload":{"canonical_record":{"source":{"id":"2405.15624","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T15:13:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70c2ecb71638d8a21112d7a28845fd232b7acceb41679d8fee8a56288da5a9cb","abstract_canon_sha256":"a2e7e62b3741f41560fe8721ab2ddf69c70ce6baeb682a1078a0fa92aec30d59"},"schema_version":"1.0"},"canonical_sha256":"9e8b8b30dfe7b8636eecf5a3b458cf9ef5acdfbbb00a3ad99d653f7c58525118","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:10.748921Z","signature_b64":"q0PVv3bsWXxE1Ibbv5W7F0RLOZa+q/MMvKhh+hY2k1a8KFzXZIS6flA2A/sJkDDzlL/srPlq6fMG1lNlRh8MAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e8b8b30dfe7b8636eecf5a3b458cf9ef5acdfbbb00a3ad99d653f7c58525118","last_reissued_at":"2026-07-05T10:05:10.748504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:10.748504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.15624","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zVABChU01nNSUKAaNumc/Ethv5pwz8EIxlN7XvUsG0COqjT8OLstin2Tvk2blmQlHZOLnyCQXb/ZC/D4jNl9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:54:55.219724Z"},"content_sha256":"76f4fa777b8355442f556789db252231e7c7f61541d5dfb297c43b592d5bb0ef","schema_version":"1.0","event_id":"sha256:76f4fa777b8355442f556789db252231e7c7f61541d5dfb297c43b592d5bb0ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:T2FYWMG7464GG3XM6WR3IWGPT3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hao Sun, Mihaela van der Schaar","submitted_at":"2024-05-24T15:13:53Z","abstract_excerpt":"Aligning Large Language Models (LLMs) is crucial for enhancing their safety and utility. However, existing methods, primarily based on preference datasets, face challenges such as noisy labels, high annotation costs, and privacy concerns. In this work, we introduce Alignment from Demonstrations (AfD), a novel approach leveraging high-quality demonstration data to overcome these challenges. We formalize AfD within a sequential decision-making framework, highlighting its unique challenge of missing reward signals. Drawing insights from forward and inverse reinforcement learning, we introduce div"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15624","kind":"arxiv","version":2},"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/2405.15624/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":"2026-07-05T10:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rg4Rb4z99VJ1ffiv+EA+6c7XtoMthcWOWtpYPS30V5POfN+tNbWWdTmQTpq2p4rV+GBsZq8ErSBPLGRoSQKPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:54:55.220325Z"},"content_sha256":"0bb805c5ec7fdcbdb6b32039c5b7e42167ccaa32366b09e32f1c7f1f92334ceb","schema_version":"1.0","event_id":"sha256:0bb805c5ec7fdcbdb6b32039c5b7e42167ccaa32366b09e32f1c7f1f92334ceb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T2FYWMG7464GG3XM6WR3IWGPT3/bundle.json","state_url":"https://pith.science/pith/T2FYWMG7464GG3XM6WR3IWGPT3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T2FYWMG7464GG3XM6WR3IWGPT3/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":"2026-08-07T16:54:55Z","links":{"resolver":"https://pith.science/pith/T2FYWMG7464GG3XM6WR3IWGPT3","bundle":"https://pith.science/pith/T2FYWMG7464GG3XM6WR3IWGPT3/bundle.json","state":"https://pith.science/pith/T2FYWMG7464GG3XM6WR3IWGPT3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T2FYWMG7464GG3XM6WR3IWGPT3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T2FYWMG7464GG3XM6WR3IWGPT3","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":"a2e7e62b3741f41560fe8721ab2ddf69c70ce6baeb682a1078a0fa92aec30d59","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T15:13:53Z","title_canon_sha256":"70c2ecb71638d8a21112d7a28845fd232b7acceb41679d8fee8a56288da5a9cb"},"schema_version":"1.0","source":{"id":"2405.15624","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15624","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15624v2","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15624","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"T2FYWMG7464G","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"T2FYWMG7464GG3XM","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"T2FYWMG7","created_at":"2026-07-05T10:05:10Z"}],"graph_snapshots":[{"event_id":"sha256:0bb805c5ec7fdcbdb6b32039c5b7e42167ccaa32366b09e32f1c7f1f92334ceb","target":"graph","created_at":"2026-07-05T10:05:10Z","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/2405.15624/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning Large Language Models (LLMs) is crucial for enhancing their safety and utility. However, existing methods, primarily based on preference datasets, face challenges such as noisy labels, high annotation costs, and privacy concerns. In this work, we introduce Alignment from Demonstrations (AfD), a novel approach leveraging high-quality demonstration data to overcome these challenges. We formalize AfD within a sequential decision-making framework, highlighting its unique challenge of missing reward signals. Drawing insights from forward and inverse reinforcement learning, we introduce div","authors_text":"Hao Sun, Mihaela van der Schaar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T15:13:53Z","title":"Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15624","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":"sha256:76f4fa777b8355442f556789db252231e7c7f61541d5dfb297c43b592d5bb0ef","target":"record","created_at":"2026-07-05T10:05:10Z","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":"a2e7e62b3741f41560fe8721ab2ddf69c70ce6baeb682a1078a0fa92aec30d59","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T15:13:53Z","title_canon_sha256":"70c2ecb71638d8a21112d7a28845fd232b7acceb41679d8fee8a56288da5a9cb"},"schema_version":"1.0","source":{"id":"2405.15624","kind":"arxiv","version":2}},"canonical_sha256":"9e8b8b30dfe7b8636eecf5a3b458cf9ef5acdfbbb00a3ad99d653f7c58525118","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e8b8b30dfe7b8636eecf5a3b458cf9ef5acdfbbb00a3ad99d653f7c58525118","first_computed_at":"2026-07-05T10:05:10.748504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:10.748504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q0PVv3bsWXxE1Ibbv5W7F0RLOZa+q/MMvKhh+hY2k1a8KFzXZIS6flA2A/sJkDDzlL/srPlq6fMG1lNlRh8MAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:10.748921Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15624","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76f4fa777b8355442f556789db252231e7c7f61541d5dfb297c43b592d5bb0ef","sha256:0bb805c5ec7fdcbdb6b32039c5b7e42167ccaa32366b09e32f1c7f1f92334ceb"],"state_sha256":"d48a364ddc88f8324a6b7300d317c95956593244da3916f18e41b7b875c601a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SBN3Ko25/pMmfirG/FatXlJtglF02/27PPwsbobKBMZoU9yBDok2nNoMm80cHELtxklKUH8MuCSvup+2javMBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:54:55.225336Z","bundle_sha256":"4e22ef325d129e9eddc6124735a2848e3d8289da06a295da26c51039c23f8047"}}