{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XFQLQ7NPPJ7MV4QT64R6V2CRQS","short_pith_number":"pith:XFQLQ7NP","canonical_record":{"source":{"id":"2310.09983","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-15T23:23:27Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"1f96aeb1c9af94eeec31d735cd9aa41c85a3992a0bf1b3b9e200227c39239a44","abstract_canon_sha256":"b8ea47cb5144209052ff0f3ce488e268ac054ccffcfad6e4d55f2bd984a848f4"},"schema_version":"1.0"},"canonical_sha256":"b960b87daf7a7ecaf213f723eae85184a55bf2b2dad04808ae2317df4768d80b","source":{"kind":"arxiv","id":"2310.09983","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.09983","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"arxiv_version","alias_value":"2310.09983v1","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09983","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"pith_short_12","alias_value":"XFQLQ7NPPJ7M","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"pith_short_16","alias_value":"XFQLQ7NPPJ7MV4QT","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"pith_short_8","alias_value":"XFQLQ7NP","created_at":"2026-07-05T07:01:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XFQLQ7NPPJ7MV4QT64R6V2CRQS","target":"record","payload":{"canonical_record":{"source":{"id":"2310.09983","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-15T23:23:27Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"1f96aeb1c9af94eeec31d735cd9aa41c85a3992a0bf1b3b9e200227c39239a44","abstract_canon_sha256":"b8ea47cb5144209052ff0f3ce488e268ac054ccffcfad6e4d55f2bd984a848f4"},"schema_version":"1.0"},"canonical_sha256":"b960b87daf7a7ecaf213f723eae85184a55bf2b2dad04808ae2317df4768d80b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:13.345375Z","signature_b64":"FdRVeHJVZvcx5eYmIEad+0f4DRCsI1HVFNRPMuxad9BSFE5inOokyLgQ5ILlw3za8FpCsTPWRn42SnL4xp5HCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b960b87daf7a7ecaf213f723eae85184a55bf2b2dad04808ae2317df4768d80b","last_reissued_at":"2026-07-05T07:01:13.344912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:13.344912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.09983","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":"2026-07-05T07:01:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zk0GFonmus28wE3GSIQeKtx7eC4t2vXBbS6AcHq/PbUFRhcSqc+ISPjBUjqo+3Q2c+L87nDjeh7w4ofpxGM/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:50:03.106295Z"},"content_sha256":"af64afdac5a464b1d338988d70e385b37f6fd08aedb35a773aa10a28ce0467d6","schema_version":"1.0","event_id":"sha256:af64afdac5a464b1d338988d70e385b37f6fd08aedb35a773aa10a28ce0467d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XFQLQ7NPPJ7MV4QT64R6V2CRQS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Farzi Data: Autoregressive Data Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Derek Zhiyuan Cheng, Jianmo Ni, Julian McAuley, Noveen Sachdeva, Wang-Cheng Kang, Zexue He","submitted_at":"2023-10-15T23:23:27Z","abstract_excerpt":"We study data distillation for auto-regressive machine learning tasks, where the input and output have a strict left-to-right causal structure. More specifically, we propose Farzi, which summarizes an event sequence dataset into a small number of synthetic sequences -- Farzi Data -- which are optimized to maintain (if not improve) model performance compared to training on the full dataset. Under the hood, Farzi conducts memory-efficient data distillation by (i) deriving efficient reverse-mode differentiation of the Adam optimizer by leveraging Hessian-Vector Products; and (ii) factorizing the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09983","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/2310.09983/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":"2026-07-05T07:01:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lpXTnYvz1D3/WU+7syurLwJed0KQ4Dm8vM9wLEO3GMMryfm37xvorVA2WFyxfdozWYpZHDR7mzUGb8PINZTQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:50:03.106803Z"},"content_sha256":"6f54149047cfd40e9c01acbe9d8698a506cfc6a4abe1d79ec612b08eaa89f020","schema_version":"1.0","event_id":"sha256:6f54149047cfd40e9c01acbe9d8698a506cfc6a4abe1d79ec612b08eaa89f020"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XFQLQ7NPPJ7MV4QT64R6V2CRQS/bundle.json","state_url":"https://pith.science/pith/XFQLQ7NPPJ7MV4QT64R6V2CRQS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XFQLQ7NPPJ7MV4QT64R6V2CRQS/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":"2026-08-06T03:50:03Z","links":{"resolver":"https://pith.science/pith/XFQLQ7NPPJ7MV4QT64R6V2CRQS","bundle":"https://pith.science/pith/XFQLQ7NPPJ7MV4QT64R6V2CRQS/bundle.json","state":"https://pith.science/pith/XFQLQ7NPPJ7MV4QT64R6V2CRQS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XFQLQ7NPPJ7MV4QT64R6V2CRQS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XFQLQ7NPPJ7MV4QT64R6V2CRQS","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":"b8ea47cb5144209052ff0f3ce488e268ac054ccffcfad6e4d55f2bd984a848f4","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-15T23:23:27Z","title_canon_sha256":"1f96aeb1c9af94eeec31d735cd9aa41c85a3992a0bf1b3b9e200227c39239a44"},"schema_version":"1.0","source":{"id":"2310.09983","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.09983","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"arxiv_version","alias_value":"2310.09983v1","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09983","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"pith_short_12","alias_value":"XFQLQ7NPPJ7M","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"pith_short_16","alias_value":"XFQLQ7NPPJ7MV4QT","created_at":"2026-07-05T07:01:13Z"},{"alias_kind":"pith_short_8","alias_value":"XFQLQ7NP","created_at":"2026-07-05T07:01:13Z"}],"graph_snapshots":[{"event_id":"sha256:6f54149047cfd40e9c01acbe9d8698a506cfc6a4abe1d79ec612b08eaa89f020","target":"graph","created_at":"2026-07-05T07:01:13Z","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/2310.09983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study data distillation for auto-regressive machine learning tasks, where the input and output have a strict left-to-right causal structure. More specifically, we propose Farzi, which summarizes an event sequence dataset into a small number of synthetic sequences -- Farzi Data -- which are optimized to maintain (if not improve) model performance compared to training on the full dataset. Under the hood, Farzi conducts memory-efficient data distillation by (i) deriving efficient reverse-mode differentiation of the Adam optimizer by leveraging Hessian-Vector Products; and (ii) factorizing the ","authors_text":"Derek Zhiyuan Cheng, Jianmo Ni, Julian McAuley, Noveen Sachdeva, Wang-Cheng Kang, Zexue He","cross_cats":["cs.AI","cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-15T23:23:27Z","title":"Farzi Data: Autoregressive Data Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09983","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:af64afdac5a464b1d338988d70e385b37f6fd08aedb35a773aa10a28ce0467d6","target":"record","created_at":"2026-07-05T07:01:13Z","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":"b8ea47cb5144209052ff0f3ce488e268ac054ccffcfad6e4d55f2bd984a848f4","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-15T23:23:27Z","title_canon_sha256":"1f96aeb1c9af94eeec31d735cd9aa41c85a3992a0bf1b3b9e200227c39239a44"},"schema_version":"1.0","source":{"id":"2310.09983","kind":"arxiv","version":1}},"canonical_sha256":"b960b87daf7a7ecaf213f723eae85184a55bf2b2dad04808ae2317df4768d80b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b960b87daf7a7ecaf213f723eae85184a55bf2b2dad04808ae2317df4768d80b","first_computed_at":"2026-07-05T07:01:13.344912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:13.344912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FdRVeHJVZvcx5eYmIEad+0f4DRCsI1HVFNRPMuxad9BSFE5inOokyLgQ5ILlw3za8FpCsTPWRn42SnL4xp5HCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:13.345375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.09983","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af64afdac5a464b1d338988d70e385b37f6fd08aedb35a773aa10a28ce0467d6","sha256:6f54149047cfd40e9c01acbe9d8698a506cfc6a4abe1d79ec612b08eaa89f020"],"state_sha256":"f773a318a0f9c9f5a5119f2c58b0dd08a1cc871af17555a76f8c8e58c8a9fb3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"maYRtN838wNj51HBKaiNI9pR69B+lkPKf1sBFoiDloqak0jYOz58bqkogMcnicmMV9qtXfaIJAxDYICqhlZRDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:50:03.110427Z","bundle_sha256":"c717ac77b7899b27430138a072eee2b24f0e7382a0353ae82ae840927e3a233e"}}