{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TNXHPJGWWBQMFMJKFIHHXKZ2CV","short_pith_number":"pith:TNXHPJGW","canonical_record":{"source":{"id":"2410.10093","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T02:21:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"538674512838f34c7a7a67111e8b90ca9b6ce088a396e12bc8e9903e123b5c19","abstract_canon_sha256":"0c522278e604363095572985a2ef46f17de0f88b775ec24f0f5155b770fc268d"},"schema_version":"1.0"},"canonical_sha256":"9b6e77a4d6b060c2b12a2a0e7bab3a156eaf29eadbefd99146e0769962270013","source":{"kind":"arxiv","id":"2410.10093","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10093","created_at":"2026-07-05T09:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10093v1","created_at":"2026-07-05T09:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10093","created_at":"2026-07-05T09:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"TNXHPJGWWBQM","created_at":"2026-07-05T09:20:11Z"},{"alias_kind":"pith_short_16","alias_value":"TNXHPJGWWBQMFMJK","created_at":"2026-07-05T09:20:11Z"},{"alias_kind":"pith_short_8","alias_value":"TNXHPJGW","created_at":"2026-07-05T09:20:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TNXHPJGWWBQMFMJKFIHHXKZ2CV","target":"record","payload":{"canonical_record":{"source":{"id":"2410.10093","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T02:21:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"538674512838f34c7a7a67111e8b90ca9b6ce088a396e12bc8e9903e123b5c19","abstract_canon_sha256":"0c522278e604363095572985a2ef46f17de0f88b775ec24f0f5155b770fc268d"},"schema_version":"1.0"},"canonical_sha256":"9b6e77a4d6b060c2b12a2a0e7bab3a156eaf29eadbefd99146e0769962270013","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:11.070303Z","signature_b64":"4vDaBVztcSscIAV3qynyCPVZw1FT1leNuKSdA7P0AqyH3M9j+hwv2gCN1exJu+1qxjV5LhOWPcJzs/e8nDCcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b6e77a4d6b060c2b12a2a0e7bab3a156eaf29eadbefd99146e0769962270013","last_reissued_at":"2026-07-05T09:20:11.069881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:11.069881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.10093","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":"2026-07-05T09:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j1Y1HX/mLlkYyRCNfjDGo0O3p826YkWOxnVuSQ3LgVu9c681LKA61bC/ISzpEXB0pLfBAIKM/VKHSPu55ZgUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:12:43.138907Z"},"content_sha256":"f9461d36b3060508f6f96cddd0d0bcbd8aa6d467443170fbaab8d455b0132dca","schema_version":"1.0","event_id":"sha256:f9461d36b3060508f6f96cddd0d0bcbd8aa6d467443170fbaab8d455b0132dca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TNXHPJGWWBQMFMJKFIHHXKZ2CV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chao Cui, Huaisheng Zhu, Mingxiao Li, Teng Xiao, Vasant G Honavar, Yige Yuan","submitted_at":"2024-10-14T02:21:29Z","abstract_excerpt":"This paper introduces a novel generalized self-imitation learning ($\\textbf{GSIL}$) framework, which effectively and efficiently aligns large language models with offline demonstration data. We develop $\\textbf{GSIL}$ by deriving a surrogate objective of imitation learning with density ratio estimates, facilitating the use of self-generated data and optimizing the imitation learning objective with simple classification losses. $\\textbf{GSIL}$ eliminates the need for complex adversarial training in standard imitation learning, achieving lightweight and efficient fine-tuning for large language m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10093","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/2410.10093/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":"2026-07-05T09:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KO6H32LjEPnazD8sN4pUlf0RdQv5LwQ6pfg0dbO7008XrdFotmeUkQbYO7tet6LJQgI0aa9ZAcjn8cH40csmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:12:43.139903Z"},"content_sha256":"c498d4c35bc0be293afd5d425846d2765364afdc7b2f5d0fe53507def81ea6fa","schema_version":"1.0","event_id":"sha256:c498d4c35bc0be293afd5d425846d2765364afdc7b2f5d0fe53507def81ea6fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TNXHPJGWWBQMFMJKFIHHXKZ2CV/bundle.json","state_url":"https://pith.science/pith/TNXHPJGWWBQMFMJKFIHHXKZ2CV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TNXHPJGWWBQMFMJKFIHHXKZ2CV/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":"2026-08-10T03:12:43Z","links":{"resolver":"https://pith.science/pith/TNXHPJGWWBQMFMJKFIHHXKZ2CV","bundle":"https://pith.science/pith/TNXHPJGWWBQMFMJKFIHHXKZ2CV/bundle.json","state":"https://pith.science/pith/TNXHPJGWWBQMFMJKFIHHXKZ2CV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TNXHPJGWWBQMFMJKFIHHXKZ2CV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TNXHPJGWWBQMFMJKFIHHXKZ2CV","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":"0c522278e604363095572985a2ef46f17de0f88b775ec24f0f5155b770fc268d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T02:21:29Z","title_canon_sha256":"538674512838f34c7a7a67111e8b90ca9b6ce088a396e12bc8e9903e123b5c19"},"schema_version":"1.0","source":{"id":"2410.10093","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10093","created_at":"2026-07-05T09:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10093v1","created_at":"2026-07-05T09:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10093","created_at":"2026-07-05T09:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"TNXHPJGWWBQM","created_at":"2026-07-05T09:20:11Z"},{"alias_kind":"pith_short_16","alias_value":"TNXHPJGWWBQMFMJK","created_at":"2026-07-05T09:20:11Z"},{"alias_kind":"pith_short_8","alias_value":"TNXHPJGW","created_at":"2026-07-05T09:20:11Z"}],"graph_snapshots":[{"event_id":"sha256:c498d4c35bc0be293afd5d425846d2765364afdc7b2f5d0fe53507def81ea6fa","target":"graph","created_at":"2026-07-05T09:20:11Z","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/2410.10093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces a novel generalized self-imitation learning ($\\textbf{GSIL}$) framework, which effectively and efficiently aligns large language models with offline demonstration data. We develop $\\textbf{GSIL}$ by deriving a surrogate objective of imitation learning with density ratio estimates, facilitating the use of self-generated data and optimizing the imitation learning objective with simple classification losses. $\\textbf{GSIL}$ eliminates the need for complex adversarial training in standard imitation learning, achieving lightweight and efficient fine-tuning for large language m","authors_text":"Chao Cui, Huaisheng Zhu, Mingxiao Li, Teng Xiao, Vasant G Honavar, Yige Yuan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T02:21:29Z","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10093","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:f9461d36b3060508f6f96cddd0d0bcbd8aa6d467443170fbaab8d455b0132dca","target":"record","created_at":"2026-07-05T09:20:11Z","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":"0c522278e604363095572985a2ef46f17de0f88b775ec24f0f5155b770fc268d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T02:21:29Z","title_canon_sha256":"538674512838f34c7a7a67111e8b90ca9b6ce088a396e12bc8e9903e123b5c19"},"schema_version":"1.0","source":{"id":"2410.10093","kind":"arxiv","version":1}},"canonical_sha256":"9b6e77a4d6b060c2b12a2a0e7bab3a156eaf29eadbefd99146e0769962270013","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b6e77a4d6b060c2b12a2a0e7bab3a156eaf29eadbefd99146e0769962270013","first_computed_at":"2026-07-05T09:20:11.069881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:11.069881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4vDaBVztcSscIAV3qynyCPVZw1FT1leNuKSdA7P0AqyH3M9j+hwv2gCN1exJu+1qxjV5LhOWPcJzs/e8nDCcAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:11.070303Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10093","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9461d36b3060508f6f96cddd0d0bcbd8aa6d467443170fbaab8d455b0132dca","sha256:c498d4c35bc0be293afd5d425846d2765364afdc7b2f5d0fe53507def81ea6fa"],"state_sha256":"6ecce34433b2481d63166d79d795c918cd48726da8bb9c543df0a9d6e12a3662"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vnhh0eQ1JkVpolAhTwcCn8hrHzsf1GXSnDiELU3S07CRVC1Nxy9TcYMKzpbbUIQayTcvzGHe/3B039FZ3MCeAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:12:43.147575Z","bundle_sha256":"885e49e57fdb3b2fb2cedc8bb1df45e83d5ea0b9adb32bf385418c1f763d5a96"}}