{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NZLN6I2X2WA5FPSCBY6Q3SMJHN","short_pith_number":"pith:NZLN6I2X","schema_version":"1.0","canonical_sha256":"6e56df2357d581d2be420e3d0dc9893b5e1d80f70d01841c9f563a8685a7227c","source":{"kind":"arxiv","id":"2512.15605","version":4},"attestation_state":"computed","paper":{"title":"Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Autoregressive language models are equivalent to energy-based models in function space through a bijection from the chain rule of probability.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Germain Vivier-Ardisson, Mathieu Blondel, Michael E. Sander, Tianlin Liu, Vincent Roulet","submitted_at":"2025-12-17T17:14:26Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2512.15605","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-17T17:14:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4a21800a0e271758192b0ab58fafe5ab76d07572b85c36e0e9d446a15cf28341","abstract_canon_sha256":"54408919a33aa2c84ace259bb2729e36799fda794e784c2511a017f86d2e6e2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:04.610106Z","signature_b64":"hc50gi4pDADb3worpFaLnbjcpENxcao5ah4Uo12mgxEe4ITyJniY6P6mmDhFe4E1V+FLe6SqviXoVrWzyC5lCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e56df2357d581d2be420e3d0dc9893b5e1d80f70d01841c9f563a8685a7227c","last_reissued_at":"2026-05-26T02:05:04.609257Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:04.609257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Autoregressive language models are equivalent to energy-based models in function space through a bijection from the chain rule of probability.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Germain Vivier-Ardisson, Mathieu Blondel, Michael E. Sander, Tianlin Liu, Vincent Roulet","submitted_at":"2025-12-17T17:14:26Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Autoregressive language models are equivalent to energy-based models in function space through a bijection from the chain rule of probability.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6b47076c5be2662fa6bc21165739fa785c814ce5a6b927f9e6cdd423af4e178f"},"source":{"id":"2512.15605","kind":"arxiv","version":4},"verdict":{"id":"c18701b4-f004-403c-b076-bcad8e1ad5b9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T21:25:35.218166Z","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","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","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.","pith_extraction_headline":"Autoregressive language models are equivalent to energy-based models in function space through a bijection from the chain rule of probability."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.15605/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":2,"snapshot_sha256":"56eea985e085013488def317f330effba9b0b6efd5b0b6b965b0fd26e2503002"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2512.15605","created_at":"2026-05-26T02:05:04.609352+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.15605v4","created_at":"2026-05-26T02:05:04.609352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.15605","created_at":"2026-05-26T02:05:04.609352+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZLN6I2X2WA5","created_at":"2026-05-26T02:05:04.609352+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZLN6I2X2WA5FPSC","created_at":"2026-05-26T02:05:04.609352+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZLN6I2X","created_at":"2026-05-26T02:05:04.609352+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2604.00555","citing_title":"Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00555","citing_title":"Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11011","citing_title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZLN6I2X2WA5FPSCBY6Q3SMJHN","json":"https://pith.science/pith/NZLN6I2X2WA5FPSCBY6Q3SMJHN.json","graph_json":"https://pith.science/api/pith-number/NZLN6I2X2WA5FPSCBY6Q3SMJHN/graph.json","events_json":"https://pith.science/api/pith-number/NZLN6I2X2WA5FPSCBY6Q3SMJHN/events.json","paper":"https://pith.science/paper/NZLN6I2X"},"agent_actions":{"view_html":"https://pith.science/pith/NZLN6I2X2WA5FPSCBY6Q3SMJHN","download_json":"https://pith.science/pith/NZLN6I2X2WA5FPSCBY6Q3SMJHN.json","view_paper":"https://pith.science/paper/NZLN6I2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.15605&json=true","fetch_graph":"https://pith.science/api/pith-number/NZLN6I2X2WA5FPSCBY6Q3SMJHN/graph.json","fetch_events":"https://pith.science/api/pith-number/NZLN6I2X2WA5FPSCBY6Q3SMJHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZLN6I2X2WA5FPSCBY6Q3SMJHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZLN6I2X2WA5FPSCBY6Q3SMJHN/action/storage_attestation","attest_author":"https://pith.science/pith/NZLN6I2X2WA5FPSCBY6Q3SMJHN/action/author_attestation","sign_citation":"https://pith.science/pith/NZLN6I2X2WA5FPSCBY6Q3SMJHN/action/citation_signature","submit_replication":"https://pith.science/pith/NZLN6I2X2WA5FPSCBY6Q3SMJHN/action/replication_record"}},"created_at":"2026-05-26T02:05:04.609352+00:00","updated_at":"2026-05-26T02:05:04.609352+00:00"}