{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:4NVG7ENXRCPLFGP35KT2MWVR75","short_pith_number":"pith:4NVG7ENX","canonical_record":{"source":{"id":"2109.05093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T20:14:08Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"43f7eab864bb79a4b6cdb2447778bfc1b2e2fb60a1f69b5c66920957dbdb046e","abstract_canon_sha256":"016cf22ed420560c5d3c6a69106503af2f485aa06b167cda6ffcdee56e294811"},"schema_version":"1.0"},"canonical_sha256":"e36a6f91b7889eb299fbeaa7a65ab1ff70c59c110fd6f8c1b331cdeb365d44ae","source":{"kind":"arxiv","id":"2109.05093","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.05093","created_at":"2026-07-05T03:13:34Z"},{"alias_kind":"arxiv_version","alias_value":"2109.05093v1","created_at":"2026-07-05T03:13:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05093","created_at":"2026-07-05T03:13:34Z"},{"alias_kind":"pith_short_12","alias_value":"4NVG7ENXRCPL","created_at":"2026-07-05T03:13:34Z"},{"alias_kind":"pith_short_16","alias_value":"4NVG7ENXRCPLFGP3","created_at":"2026-07-05T03:13:34Z"},{"alias_kind":"pith_short_8","alias_value":"4NVG7ENX","created_at":"2026-07-05T03:13:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:4NVG7ENXRCPLFGP35KT2MWVR75","target":"record","payload":{"canonical_record":{"source":{"id":"2109.05093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T20:14:08Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"43f7eab864bb79a4b6cdb2447778bfc1b2e2fb60a1f69b5c66920957dbdb046e","abstract_canon_sha256":"016cf22ed420560c5d3c6a69106503af2f485aa06b167cda6ffcdee56e294811"},"schema_version":"1.0"},"canonical_sha256":"e36a6f91b7889eb299fbeaa7a65ab1ff70c59c110fd6f8c1b331cdeb365d44ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:34.277895Z","signature_b64":"cVxSfgQ41wELIdGISJ2kTDkrMWwylh8atWvFE6oyqOksFM1UrS16razau7/UFrPKjyrg0rwdt69aolxJ5ulXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e36a6f91b7889eb299fbeaa7a65ab1ff70c59c110fd6f8c1b331cdeb365d44ae","last_reissued_at":"2026-07-05T03:13:34.277391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:34.277391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.05093","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":"2026-07-05T03:13:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dqALqs/DHYLfC6TZBbnEZAnM+kXG7CuubS3KFRcys4mPrWSTv8OGWt2EDyJHUFEPm1iZrtCW401t+AQiPYmJCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T10:07:51.569474Z"},"content_sha256":"a2c30ae3818c40d0fb7c731a34a0c8a1eec6a743a03f5b4ed63435b1bb4056e7","schema_version":"1.0","event_id":"sha256:a2c30ae3818c40d0fb7c731a34a0c8a1eec6a743a03f5b4ed63435b1bb4056e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:4NVG7ENXRCPLFGP35KT2MWVR75","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.CL","authors_text":"Dzmitry Bahdanau, Nathan Schucher, Torsten Scholak","submitted_at":"2021-09-10T20:14:08Z","abstract_excerpt":"Large pre-trained language models for textual data have an unconstrained output space; at each decoding step, they can produce any of 10,000s of sub-word tokens. When fine-tuned to target constrained formal languages like SQL, these models often generate invalid code, rendering it unusable. We propose PICARD (code and trained models available at https://github.com/ElementAI/picard), a method for constraining auto-regressive decoders of language models through incremental parsing. PICARD helps to find valid output sequences by rejecting inadmissible tokens at each decoding step. On the challeng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05093","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/2109.05093/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":"2026-07-05T03:13:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8SvqyF4+8VWL/0b6BsOOCiwWfS2SlMyKh+RmbJJzG8//h3Cm/9nWqFaC7hRKpZ35QidQNVkSVWGo1U+GOUPGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T10:07:51.570000Z"},"content_sha256":"76ca03858bcf10a76ddbffa8909fbd3922546fc7765dc0c29edd350425ce3bdd","schema_version":"1.0","event_id":"sha256:76ca03858bcf10a76ddbffa8909fbd3922546fc7765dc0c29edd350425ce3bdd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4NVG7ENXRCPLFGP35KT2MWVR75/bundle.json","state_url":"https://pith.science/pith/4NVG7ENXRCPLFGP35KT2MWVR75/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4NVG7ENXRCPLFGP35KT2MWVR75/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":"2026-08-02T10:07:51Z","links":{"resolver":"https://pith.science/pith/4NVG7ENXRCPLFGP35KT2MWVR75","bundle":"https://pith.science/pith/4NVG7ENXRCPLFGP35KT2MWVR75/bundle.json","state":"https://pith.science/pith/4NVG7ENXRCPLFGP35KT2MWVR75/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4NVG7ENXRCPLFGP35KT2MWVR75/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4NVG7ENXRCPLFGP35KT2MWVR75","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":"016cf22ed420560c5d3c6a69106503af2f485aa06b167cda6ffcdee56e294811","cross_cats_sorted":["cs.PL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T20:14:08Z","title_canon_sha256":"43f7eab864bb79a4b6cdb2447778bfc1b2e2fb60a1f69b5c66920957dbdb046e"},"schema_version":"1.0","source":{"id":"2109.05093","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.05093","created_at":"2026-07-05T03:13:34Z"},{"alias_kind":"arxiv_version","alias_value":"2109.05093v1","created_at":"2026-07-05T03:13:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05093","created_at":"2026-07-05T03:13:34Z"},{"alias_kind":"pith_short_12","alias_value":"4NVG7ENXRCPL","created_at":"2026-07-05T03:13:34Z"},{"alias_kind":"pith_short_16","alias_value":"4NVG7ENXRCPLFGP3","created_at":"2026-07-05T03:13:34Z"},{"alias_kind":"pith_short_8","alias_value":"4NVG7ENX","created_at":"2026-07-05T03:13:34Z"}],"graph_snapshots":[{"event_id":"sha256:76ca03858bcf10a76ddbffa8909fbd3922546fc7765dc0c29edd350425ce3bdd","target":"graph","created_at":"2026-07-05T03:13:34Z","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/2109.05093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pre-trained language models for textual data have an unconstrained output space; at each decoding step, they can produce any of 10,000s of sub-word tokens. When fine-tuned to target constrained formal languages like SQL, these models often generate invalid code, rendering it unusable. We propose PICARD (code and trained models available at https://github.com/ElementAI/picard), a method for constraining auto-regressive decoders of language models through incremental parsing. PICARD helps to find valid output sequences by rejecting inadmissible tokens at each decoding step. On the challeng","authors_text":"Dzmitry Bahdanau, Nathan Schucher, Torsten Scholak","cross_cats":["cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T20:14:08Z","title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05093","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:a2c30ae3818c40d0fb7c731a34a0c8a1eec6a743a03f5b4ed63435b1bb4056e7","target":"record","created_at":"2026-07-05T03:13:34Z","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":"016cf22ed420560c5d3c6a69106503af2f485aa06b167cda6ffcdee56e294811","cross_cats_sorted":["cs.PL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T20:14:08Z","title_canon_sha256":"43f7eab864bb79a4b6cdb2447778bfc1b2e2fb60a1f69b5c66920957dbdb046e"},"schema_version":"1.0","source":{"id":"2109.05093","kind":"arxiv","version":1}},"canonical_sha256":"e36a6f91b7889eb299fbeaa7a65ab1ff70c59c110fd6f8c1b331cdeb365d44ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e36a6f91b7889eb299fbeaa7a65ab1ff70c59c110fd6f8c1b331cdeb365d44ae","first_computed_at":"2026-07-05T03:13:34.277391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:34.277391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cVxSfgQ41wELIdGISJ2kTDkrMWwylh8atWvFE6oyqOksFM1UrS16razau7/UFrPKjyrg0rwdt69aolxJ5ulXDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:34.277895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.05093","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2c30ae3818c40d0fb7c731a34a0c8a1eec6a743a03f5b4ed63435b1bb4056e7","sha256:76ca03858bcf10a76ddbffa8909fbd3922546fc7765dc0c29edd350425ce3bdd"],"state_sha256":"74a0a847e9b456e729809445d8b8febb4296008e9baa39bdd318162f611cc355"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vv3ThakVVKgHYK6kX/QYP0+g6prXNPU+duQtT/JDBfc7X4KFjJ6LN76qQ6LQx3ycUsrBby57oF+o6pjFJE0BCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T10:07:51.574080Z","bundle_sha256":"b76beb1e3d04273ddec47c17ba07d889718475853147693416531bf908172219"}}