{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N4LDFGPLZEBFXBGBPKN3TMD2T2","short_pith_number":"pith:N4LDFGPL","canonical_record":{"source":{"id":"2409.01369","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-02T16:48:57Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"7b824c5e7da61584b4d3a85ef373350f952936dc8bed93fe48d0ec497cfa2e63","abstract_canon_sha256":"8bdf9d18afb25f79b6c8022d0b2ecc70784bfe1846d917db269058c9a79fe0cb"},"schema_version":"1.0"},"canonical_sha256":"6f163299ebc9025b84c17a9bb9b07a9e9a8a6ae02af3d637cddd4d45bff0e569","source":{"kind":"arxiv","id":"2409.01369","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01369","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01369v2","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01369","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"pith_short_12","alias_value":"N4LDFGPLZEBF","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"pith_short_16","alias_value":"N4LDFGPLZEBFXBGB","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"pith_short_8","alias_value":"N4LDFGPL","created_at":"2026-07-05T09:46:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N4LDFGPLZEBFXBGBPKN3TMD2T2","target":"record","payload":{"canonical_record":{"source":{"id":"2409.01369","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-02T16:48:57Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"7b824c5e7da61584b4d3a85ef373350f952936dc8bed93fe48d0ec497cfa2e63","abstract_canon_sha256":"8bdf9d18afb25f79b6c8022d0b2ecc70784bfe1846d917db269058c9a79fe0cb"},"schema_version":"1.0"},"canonical_sha256":"6f163299ebc9025b84c17a9bb9b07a9e9a8a6ae02af3d637cddd4d45bff0e569","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:29.954962Z","signature_b64":"bsudVgOkMZA5ZIAMmfQxn5aZ/D/96+guq7cw9Yq+r2p9bVKb5lsg8YZv995hr7lP950s7ANRpnREjRZFIT3TAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f163299ebc9025b84c17a9bb9b07a9e9a8a6ae02af3d637cddd4d45bff0e569","last_reissued_at":"2026-07-05T09:46:29.954403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:29.954403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.01369","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":"2026-07-05T09:46:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3rizEoOoYqQ8rSgYODgJ7t24OkYARB57ojymgfOC5fGqjgjyWlDehQoHkl19QeVkz5zjqgkiY84R1SdLdgfMDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T13:34:48.660113Z"},"content_sha256":"0d7eeee5278668e4a6cade16b83ec7c68996b31b2930f8816a6d36a849b87cce","schema_version":"1.0","event_id":"sha256:0d7eeee5278668e4a6cade16b83ec7c68996b31b2930f8816a6d36a849b87cce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N4LDFGPLZEBFXBGBPKN3TMD2T2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Imitating Language via Scalable Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Bewley, Artem Sokolov, Arun Ahuja, Guillaume Desjardins, Jorg Bornschein, Jost Tobias Springenberg, Markus Wulfmeier, Martin Riedmiller, Matt Barnes, Matthieu Geist, Michael Bloesch, Nikola Momchev, Nino Vieillard, Olivier Bachem, Sandy Huang, Sarah Maria Elisabeth Bechtle","submitted_at":"2024-09-02T16:48:57Z","abstract_excerpt":"The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability of maximum likelihood estimation (MLE) for next token prediction led to its role as predominant paradigm. However, the broader field of imitation learning can more effectively utilize the sequential structure underlying autoregressive generation. We focus on investigating the inverse reinforcement learning (IRL) perspective to imitation, extracting rewards an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01369","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/2409.01369/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":"2026-07-05T09:46:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u5kudKqHEiTx9iNobR+KaoczGSGPfa4l8apsQijm7MW8smd2qRQSp62OetwbRzI2eU66v8yo/mFUyVst/Y9MCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T13:34:48.660749Z"},"content_sha256":"9ae16e68f5979eaed15f8ca6ae49e72da9a3d2b7cef8b735576f6faca5bd0b0d","schema_version":"1.0","event_id":"sha256:9ae16e68f5979eaed15f8ca6ae49e72da9a3d2b7cef8b735576f6faca5bd0b0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N4LDFGPLZEBFXBGBPKN3TMD2T2/bundle.json","state_url":"https://pith.science/pith/N4LDFGPLZEBFXBGBPKN3TMD2T2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N4LDFGPLZEBFXBGBPKN3TMD2T2/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":"2026-08-20T13:34:48Z","links":{"resolver":"https://pith.science/pith/N4LDFGPLZEBFXBGBPKN3TMD2T2","bundle":"https://pith.science/pith/N4LDFGPLZEBFXBGBPKN3TMD2T2/bundle.json","state":"https://pith.science/pith/N4LDFGPLZEBFXBGBPKN3TMD2T2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N4LDFGPLZEBFXBGBPKN3TMD2T2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N4LDFGPLZEBFXBGBPKN3TMD2T2","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":"8bdf9d18afb25f79b6c8022d0b2ecc70784bfe1846d917db269058c9a79fe0cb","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-02T16:48:57Z","title_canon_sha256":"7b824c5e7da61584b4d3a85ef373350f952936dc8bed93fe48d0ec497cfa2e63"},"schema_version":"1.0","source":{"id":"2409.01369","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01369","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01369v2","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01369","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"pith_short_12","alias_value":"N4LDFGPLZEBF","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"pith_short_16","alias_value":"N4LDFGPLZEBFXBGB","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"pith_short_8","alias_value":"N4LDFGPL","created_at":"2026-07-05T09:46:29Z"}],"graph_snapshots":[{"event_id":"sha256:9ae16e68f5979eaed15f8ca6ae49e72da9a3d2b7cef8b735576f6faca5bd0b0d","target":"graph","created_at":"2026-07-05T09:46:29Z","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/2409.01369/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability of maximum likelihood estimation (MLE) for next token prediction led to its role as predominant paradigm. However, the broader field of imitation learning can more effectively utilize the sequential structure underlying autoregressive generation. We focus on investigating the inverse reinforcement learning (IRL) perspective to imitation, extracting rewards an","authors_text":"Alex Bewley, Artem Sokolov, Arun Ahuja, Guillaume Desjardins, Jorg Bornschein, Jost Tobias Springenberg, Markus Wulfmeier, Martin Riedmiller, Matt Barnes, Matthieu Geist, Michael Bloesch, Nikola Momchev, Nino Vieillard, Olivier Bachem, Sandy Huang, Sarah Maria Elisabeth Bechtle","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-02T16:48:57Z","title":"Imitating Language via Scalable Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01369","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":"sha256:0d7eeee5278668e4a6cade16b83ec7c68996b31b2930f8816a6d36a849b87cce","target":"record","created_at":"2026-07-05T09:46:29Z","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":"8bdf9d18afb25f79b6c8022d0b2ecc70784bfe1846d917db269058c9a79fe0cb","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-02T16:48:57Z","title_canon_sha256":"7b824c5e7da61584b4d3a85ef373350f952936dc8bed93fe48d0ec497cfa2e63"},"schema_version":"1.0","source":{"id":"2409.01369","kind":"arxiv","version":2}},"canonical_sha256":"6f163299ebc9025b84c17a9bb9b07a9e9a8a6ae02af3d637cddd4d45bff0e569","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f163299ebc9025b84c17a9bb9b07a9e9a8a6ae02af3d637cddd4d45bff0e569","first_computed_at":"2026-07-05T09:46:29.954403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:29.954403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bsudVgOkMZA5ZIAMmfQxn5aZ/D/96+guq7cw9Yq+r2p9bVKb5lsg8YZv995hr7lP950s7ANRpnREjRZFIT3TAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:29.954962Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.01369","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d7eeee5278668e4a6cade16b83ec7c68996b31b2930f8816a6d36a849b87cce","sha256:9ae16e68f5979eaed15f8ca6ae49e72da9a3d2b7cef8b735576f6faca5bd0b0d"],"state_sha256":"3d148d3c01a4e9ba45b48183e9dfba09699bc4a54423398af99c9b2600971194"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p5FEDPXLV6LpBaFxkkk0ivxN0mBRh98wjnRDUEpjO+C0+tbuQrTaaxE5BHqIFEJJLVRJwvVaDvSdk2WxFQn4Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T13:34:48.667880Z","bundle_sha256":"735ecf6815c58f493e66c54735b4d1f18f7f6243b968265cb1f726e2df6a260a"}}