{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:M65MRC6DXARJTGARPJXI4FDIEO","short_pith_number":"pith:M65MRC6D","canonical_record":{"source":{"id":"2306.05426","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-08T17:59:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"87dcc662754b82d36dfd173d1dc49fbf107df90ee861068ef3d20b87b667ef45","abstract_canon_sha256":"910bc06f40c565a48078a96c7752ebbbe81e84eb862270a530160acd1f8944bf"},"schema_version":"1.0"},"canonical_sha256":"67bac88bc3b8229998117a6e8e146823a3e8bfcfc42551be8a499e1c8d9f2cb1","source":{"kind":"arxiv","id":"2306.05426","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05426","created_at":"2026-07-05T08:15:37Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05426v3","created_at":"2026-07-05T08:15:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05426","created_at":"2026-07-05T08:15:37Z"},{"alias_kind":"pith_short_12","alias_value":"M65MRC6DXARJ","created_at":"2026-07-05T08:15:37Z"},{"alias_kind":"pith_short_16","alias_value":"M65MRC6DXARJTGAR","created_at":"2026-07-05T08:15:37Z"},{"alias_kind":"pith_short_8","alias_value":"M65MRC6D","created_at":"2026-07-05T08:15:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:M65MRC6DXARJTGARPJXI4FDIEO","target":"record","payload":{"canonical_record":{"source":{"id":"2306.05426","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-08T17:59:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"87dcc662754b82d36dfd173d1dc49fbf107df90ee861068ef3d20b87b667ef45","abstract_canon_sha256":"910bc06f40c565a48078a96c7752ebbbe81e84eb862270a530160acd1f8944bf"},"schema_version":"1.0"},"canonical_sha256":"67bac88bc3b8229998117a6e8e146823a3e8bfcfc42551be8a499e1c8d9f2cb1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:37.371538Z","signature_b64":"S0h3dIAITPSbMWgBDkI3bszOO4FqMPXjvLgW9nHyb7ipYOC8KSxmD7Endm5zg6V0muJmXpdBkZYMvHltERbIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67bac88bc3b8229998117a6e8e146823a3e8bfcfc42551be8a499e1c8d9f2cb1","last_reissued_at":"2026-07-05T08:15:37.371012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:37.371012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.05426","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:15:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QntumO0Hxf2Yat+GUUYo4lozjk7ELdJFU6JrBN7ROe0dwhczVlqzOiFI5fXn85dENoj9eD4fEiDyEifBj3FPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:33:56.274614Z"},"content_sha256":"3e6b983e40f69e29599596504114ca815bf48bcd8052827478d70a23fccd9e5b","schema_version":"1.0","event_id":"sha256:3e6b983e40f69e29599596504114ca815bf48bcd8052827478d70a23fccd9e5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:M65MRC6DXARJTGARPJXI4FDIEO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chris Cundy, Stefano Ermon","submitted_at":"2023-06-08T17:59:58Z","abstract_excerpt":"In many domains, autoregressive models can attain high likelihood on the task of predicting the next observation. However, this maximum-likelihood (MLE) objective does not necessarily match a downstream use-case of autoregressively generating high-quality sequences. The MLE objective weights sequences proportionally to their frequency under the data distribution, with no guidance for the model's behaviour out of distribution (OOD): leading to compounding error during autoregressive generation. In order to address this compounding error problem, we formulate sequence generation as an imitation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05426","kind":"arxiv","version":3},"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/2306.05426/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":"2026-07-05T08:15:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2zmLzc3EJccqcj3zo54hJsFwDxvZwkkwc4Yc0eQDmkNj3i6Ob/sUaf2Gy1vTZf1djopKUiO8HIfckYZhYFgyAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:33:56.275116Z"},"content_sha256":"517685ac8f6789c442d6a5edadc87212049e93b9631eb64d24aead362ab661f6","schema_version":"1.0","event_id":"sha256:517685ac8f6789c442d6a5edadc87212049e93b9631eb64d24aead362ab661f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M65MRC6DXARJTGARPJXI4FDIEO/bundle.json","state_url":"https://pith.science/pith/M65MRC6DXARJTGARPJXI4FDIEO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M65MRC6DXARJTGARPJXI4FDIEO/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":"2026-08-08T11:33:56Z","links":{"resolver":"https://pith.science/pith/M65MRC6DXARJTGARPJXI4FDIEO","bundle":"https://pith.science/pith/M65MRC6DXARJTGARPJXI4FDIEO/bundle.json","state":"https://pith.science/pith/M65MRC6DXARJTGARPJXI4FDIEO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M65MRC6DXARJTGARPJXI4FDIEO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:M65MRC6DXARJTGARPJXI4FDIEO","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":"910bc06f40c565a48078a96c7752ebbbe81e84eb862270a530160acd1f8944bf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-08T17:59:58Z","title_canon_sha256":"87dcc662754b82d36dfd173d1dc49fbf107df90ee861068ef3d20b87b667ef45"},"schema_version":"1.0","source":{"id":"2306.05426","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05426","created_at":"2026-07-05T08:15:37Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05426v3","created_at":"2026-07-05T08:15:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05426","created_at":"2026-07-05T08:15:37Z"},{"alias_kind":"pith_short_12","alias_value":"M65MRC6DXARJ","created_at":"2026-07-05T08:15:37Z"},{"alias_kind":"pith_short_16","alias_value":"M65MRC6DXARJTGAR","created_at":"2026-07-05T08:15:37Z"},{"alias_kind":"pith_short_8","alias_value":"M65MRC6D","created_at":"2026-07-05T08:15:37Z"}],"graph_snapshots":[{"event_id":"sha256:517685ac8f6789c442d6a5edadc87212049e93b9631eb64d24aead362ab661f6","target":"graph","created_at":"2026-07-05T08:15:37Z","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/2306.05426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many domains, autoregressive models can attain high likelihood on the task of predicting the next observation. However, this maximum-likelihood (MLE) objective does not necessarily match a downstream use-case of autoregressively generating high-quality sequences. The MLE objective weights sequences proportionally to their frequency under the data distribution, with no guidance for the model's behaviour out of distribution (OOD): leading to compounding error during autoregressive generation. In order to address this compounding error problem, we formulate sequence generation as an imitation ","authors_text":"Chris Cundy, Stefano Ermon","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-08T17:59:58Z","title":"SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05426","kind":"arxiv","version":3},"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":"sha256:3e6b983e40f69e29599596504114ca815bf48bcd8052827478d70a23fccd9e5b","target":"record","created_at":"2026-07-05T08:15:37Z","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":"910bc06f40c565a48078a96c7752ebbbe81e84eb862270a530160acd1f8944bf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-08T17:59:58Z","title_canon_sha256":"87dcc662754b82d36dfd173d1dc49fbf107df90ee861068ef3d20b87b667ef45"},"schema_version":"1.0","source":{"id":"2306.05426","kind":"arxiv","version":3}},"canonical_sha256":"67bac88bc3b8229998117a6e8e146823a3e8bfcfc42551be8a499e1c8d9f2cb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67bac88bc3b8229998117a6e8e146823a3e8bfcfc42551be8a499e1c8d9f2cb1","first_computed_at":"2026-07-05T08:15:37.371012Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:37.371012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S0h3dIAITPSbMWgBDkI3bszOO4FqMPXjvLgW9nHyb7ipYOC8KSxmD7Endm5zg6V0muJmXpdBkZYMvHltERbIBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:37.371538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05426","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e6b983e40f69e29599596504114ca815bf48bcd8052827478d70a23fccd9e5b","sha256:517685ac8f6789c442d6a5edadc87212049e93b9631eb64d24aead362ab661f6"],"state_sha256":"e13567b3c7e69fc56836563c669eda2d81f5d1f56d6ef078378fecaeb6901441"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qWxoDqU1m/1z6XUQNQ4LcFKG1nzzDaJ7VHss60FLpriSnJ50qh8bURHBx5k1YtvNSx6Urh1VDwkV8CCk3DWlBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:33:56.280533Z","bundle_sha256":"2aa3300bdc41dda2c3ddbe54d424c2c11e2185ceef689708874db7ceab38bf41"}}