{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NZLN6I2X2WA5FPSCBY6Q3SMJHN","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":"54408919a33aa2c84ace259bb2729e36799fda794e784c2511a017f86d2e6e2a","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-17T17:14:26Z","title_canon_sha256":"4a21800a0e271758192b0ab58fafe5ab76d07572b85c36e0e9d446a15cf28341"},"schema_version":"1.0","source":{"id":"2512.15605","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.15605","created_at":"2026-05-26T02:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2512.15605v4","created_at":"2026-05-26T02:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.15605","created_at":"2026-05-26T02:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"NZLN6I2X2WA5","created_at":"2026-05-26T02:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"NZLN6I2X2WA5FPSC","created_at":"2026-05-26T02:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"NZLN6I2X","created_at":"2026-05-26T02:05:04Z"}],"graph_snapshots":[{"event_id":"sha256:64c6d52d2dd20d2a9a743f3d0e5db93f99b46ea23d834d609d2ff06b1c7e5bac","target":"graph","created_at":"2026-05-26T02:05:04Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"we establish an explicit bijection between ARMs and EBMs in function space, which we show to correspond to a special case of the soft Bellman equation in maximum entropy reinforcement learning"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The chain rule of probability directly yields the claimed bijection in function space with no additional restrictions on model capacity, training dynamics, or the form of the energy function."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Autoregressive language models are equivalent to energy-based models through a bijection that corresponds to the soft Bellman equation, explaining their lookahead capabilities despite next-token training."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Autoregressive language models are equivalent to energy-based models in function space through a bijection from the chain rule of probability."}],"snapshot_sha256":"6b47076c5be2662fa6bc21165739fa785c814ce5a6b927f9e6cdd423af4e178f"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"56eea985e085013488def317f330effba9b0b6efd5b0b6b965b0fd26e2503002"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2512.15605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive models (ARMs) currently constitute the dominant paradigm for large language models (LLMs). Energy-based models (EBMs) represent another class of models, which have historically been less prevalent in LLM development, yet naturally characterize the optimal policy in post-training alignment. In this paper, we provide a unified view of these two model classes. Taking the chain rule of probability as a starting point, we establish an explicit bijection between ARMs and EBMs in function space, which we show to correspond to a special case of the soft Bellman equation in maximum entro","authors_text":"Germain Vivier-Ardisson, Mathieu Blondel, Michael E. Sander, Tianlin Liu, Vincent Roulet","cross_cats":["stat.ML"],"headline":"Autoregressive language models are equivalent to energy-based models in function space through a bijection from the chain rule of probability.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-17T17:14:26Z","title":"Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.15605","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-16T21:25:35.218166Z","id":"c18701b4-f004-403c-b076-bcad8e1ad5b9","model_set":{"reader":"grok-4.3"},"one_line_summary":"Autoregressive language models are equivalent to energy-based models through a bijection that corresponds to the soft Bellman equation, explaining their lookahead capabilities despite next-token training.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Autoregressive language models are equivalent to energy-based models in function space through a bijection from the chain rule of probability.","strongest_claim":"we establish an explicit bijection between ARMs and EBMs in function space, which we show to correspond to a special case of the soft Bellman equation in maximum entropy reinforcement learning","weakest_assumption":"The chain rule of probability directly yields the claimed bijection in function space with no additional restrictions on model capacity, training dynamics, or the form of the energy function."}},"verdict_id":"c18701b4-f004-403c-b076-bcad8e1ad5b9"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:46f33ce3a22e7afa7993191d1f95a0a9bac0e0ad072ca8f0c9723fa810ae0e1b","target":"record","created_at":"2026-05-26T02:05:04Z","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":"54408919a33aa2c84ace259bb2729e36799fda794e784c2511a017f86d2e6e2a","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-17T17:14:26Z","title_canon_sha256":"4a21800a0e271758192b0ab58fafe5ab76d07572b85c36e0e9d446a15cf28341"},"schema_version":"1.0","source":{"id":"2512.15605","kind":"arxiv","version":4}},"canonical_sha256":"6e56df2357d581d2be420e3d0dc9893b5e1d80f70d01841c9f563a8685a7227c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e56df2357d581d2be420e3d0dc9893b5e1d80f70d01841c9f563a8685a7227c","first_computed_at":"2026-05-26T02:05:04.609257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:04.609257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hc50gi4pDADb3worpFaLnbjcpENxcao5ah4Uo12mgxEe4ITyJniY6P6mmDhFe4E1V+FLe6SqviXoVrWzyC5lCw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:04.610106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.15605","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46f33ce3a22e7afa7993191d1f95a0a9bac0e0ad072ca8f0c9723fa810ae0e1b","sha256:64c6d52d2dd20d2a9a743f3d0e5db93f99b46ea23d834d609d2ff06b1c7e5bac"],"state_sha256":"f3021b77e6d00fde7cc582a096a2435575e65049c3a8d43058bac84ff0231775"}