{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:A5HKX26NWKQQAZPPQJI77TKPEQ","short_pith_number":"pith:A5HKX26N","canonical_record":{"source":{"id":"2206.12840","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-26T10:58:41Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1c2dc94bf0f911fef4f00df495629c8cd8f307b183e051f23f5272d8452e96ea","abstract_canon_sha256":"3428a730b38ec5e9445d2b71459b08af08178aaa61c6847b22a8ff71fc97ad55"},"schema_version":"1.0"},"canonical_sha256":"074eabebcdb2a10065ef8251ffcd4f2403741c0ba8d703906fca5efa8b53f2e6","source":{"kind":"arxiv","id":"2206.12840","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.12840","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"2206.12840v1","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12840","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"A5HKX26NWKQQ","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"pith_short_16","alias_value":"A5HKX26NWKQQAZPP","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"pith_short_8","alias_value":"A5HKX26N","created_at":"2026-07-05T04:34:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:A5HKX26NWKQQAZPPQJI77TKPEQ","target":"record","payload":{"canonical_record":{"source":{"id":"2206.12840","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-26T10:58:41Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1c2dc94bf0f911fef4f00df495629c8cd8f307b183e051f23f5272d8452e96ea","abstract_canon_sha256":"3428a730b38ec5e9445d2b71459b08af08178aaa61c6847b22a8ff71fc97ad55"},"schema_version":"1.0"},"canonical_sha256":"074eabebcdb2a10065ef8251ffcd4f2403741c0ba8d703906fca5efa8b53f2e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:59.828858Z","signature_b64":"zjzVaoReXx1+m8/dSCtlQjOhsPGK4tbToAZV7y01fMPKuGSwm0YLPz1Wv5xor5BvOBpC2TclR76ea/7zJzdqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"074eabebcdb2a10065ef8251ffcd4f2403741c0ba8d703906fca5efa8b53f2e6","last_reissued_at":"2026-07-05T04:34:59.828380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:59.828380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.12840","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":"2026-07-05T04:34:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DihRcgRoJwGe72Vk3Xu/QHvCedCZ61YloJfJr7Z0wxOcQqgju+vGvD8RklAzE/h+7eJ8IWxmTG8YJfjel5/ODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:30:14.431654Z"},"content_sha256":"9827c276798eec680021c5dd2045c51dff8434d3135a5963ef58b34eb785be0d","schema_version":"1.0","event_id":"sha256:9827c276798eec680021c5dd2045c51dff8434d3135a5963ef58b34eb785be0d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:A5HKX26NWKQQAZPPQJI77TKPEQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Li, Dongsheng Li, Hengzhi Pei, Kaitao Song, Tong Che, Yezhen Wang, Yoshua Bengio","submitted_at":"2022-06-26T10:58:41Z","abstract_excerpt":"Autoregressive generative models are commonly used, especially for those tasks involving sequential data. They have, however, been plagued by a slew of inherent flaws due to the intrinsic characteristics of chain-style conditional modeling (e.g., exposure bias or lack of long-range coherence), severely limiting their ability to model distributions properly. In this paper, we propose a unique method termed E-ARM for training autoregressive generative models that takes advantage of a well-designed energy-based learning objective. By leveraging the extra degree of freedom of the softmax operation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12840","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/2206.12840/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":"2026-07-05T04:34:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vBkCvzWc6tl9C6s73QE0X/aoqvuZ7aHcGRJLN2IV0zz+Qo5R97UvY1FGlKRhFX0XN47Waoy6OTn2+lCvd+1uDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:30:14.432043Z"},"content_sha256":"de9414e1dca56a0e782bd2109cca4a7ce496773629a3bcea64a4ab6fd6229327","schema_version":"1.0","event_id":"sha256:de9414e1dca56a0e782bd2109cca4a7ce496773629a3bcea64a4ab6fd6229327"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A5HKX26NWKQQAZPPQJI77TKPEQ/bundle.json","state_url":"https://pith.science/pith/A5HKX26NWKQQAZPPQJI77TKPEQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A5HKX26NWKQQAZPPQJI77TKPEQ/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":"2026-07-05T09:30:14Z","links":{"resolver":"https://pith.science/pith/A5HKX26NWKQQAZPPQJI77TKPEQ","bundle":"https://pith.science/pith/A5HKX26NWKQQAZPPQJI77TKPEQ/bundle.json","state":"https://pith.science/pith/A5HKX26NWKQQAZPPQJI77TKPEQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A5HKX26NWKQQAZPPQJI77TKPEQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:A5HKX26NWKQQAZPPQJI77TKPEQ","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":"3428a730b38ec5e9445d2b71459b08af08178aaa61c6847b22a8ff71fc97ad55","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-26T10:58:41Z","title_canon_sha256":"1c2dc94bf0f911fef4f00df495629c8cd8f307b183e051f23f5272d8452e96ea"},"schema_version":"1.0","source":{"id":"2206.12840","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.12840","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"2206.12840v1","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12840","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"A5HKX26NWKQQ","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"pith_short_16","alias_value":"A5HKX26NWKQQAZPP","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"pith_short_8","alias_value":"A5HKX26N","created_at":"2026-07-05T04:34:59Z"}],"graph_snapshots":[{"event_id":"sha256:de9414e1dca56a0e782bd2109cca4a7ce496773629a3bcea64a4ab6fd6229327","target":"graph","created_at":"2026-07-05T04:34:59Z","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/2206.12840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive generative models are commonly used, especially for those tasks involving sequential data. They have, however, been plagued by a slew of inherent flaws due to the intrinsic characteristics of chain-style conditional modeling (e.g., exposure bias or lack of long-range coherence), severely limiting their ability to model distributions properly. In this paper, we propose a unique method termed E-ARM for training autoregressive generative models that takes advantage of a well-designed energy-based learning objective. By leveraging the extra degree of freedom of the softmax operation","authors_text":"Bo Li, Dongsheng Li, Hengzhi Pei, Kaitao Song, Tong Che, Yezhen Wang, Yoshua Bengio","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-26T10:58:41Z","title":"Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12840","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":"sha256:9827c276798eec680021c5dd2045c51dff8434d3135a5963ef58b34eb785be0d","target":"record","created_at":"2026-07-05T04:34:59Z","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":"3428a730b38ec5e9445d2b71459b08af08178aaa61c6847b22a8ff71fc97ad55","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-26T10:58:41Z","title_canon_sha256":"1c2dc94bf0f911fef4f00df495629c8cd8f307b183e051f23f5272d8452e96ea"},"schema_version":"1.0","source":{"id":"2206.12840","kind":"arxiv","version":1}},"canonical_sha256":"074eabebcdb2a10065ef8251ffcd4f2403741c0ba8d703906fca5efa8b53f2e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"074eabebcdb2a10065ef8251ffcd4f2403741c0ba8d703906fca5efa8b53f2e6","first_computed_at":"2026-07-05T04:34:59.828380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:34:59.828380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zjzVaoReXx1+m8/dSCtlQjOhsPGK4tbToAZV7y01fMPKuGSwm0YLPz1Wv5xor5BvOBpC2TclR76ea/7zJzdqBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:34:59.828858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.12840","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9827c276798eec680021c5dd2045c51dff8434d3135a5963ef58b34eb785be0d","sha256:de9414e1dca56a0e782bd2109cca4a7ce496773629a3bcea64a4ab6fd6229327"],"state_sha256":"1cb712e51da342383aca5493f9406676ee5bdf486d5005c062b9ed83333bd194"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WrPpw6fGVaZSR4ibgbMmSi0hsVuUTOkmDG1pvprpE40g+UInlSpTVZDw6pp/ajLFw4YaORXwbskt+FWUyNGsCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T09:30:14.434279Z","bundle_sha256":"f57336c2cb1dc3cc00db4eb5dc782d15476a93a5c32ef576080aec1b99aea915"}}