{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:F3LTVFJPY232BMTYPZIB52DRR6","short_pith_number":"pith:F3LTVFJP","canonical_record":{"source":{"id":"2308.06942","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-14T05:22:33Z","cross_cats_sorted":["cs.CL","cs.IT","math.IT"],"title_canon_sha256":"f181cc4d53458cb71533230daf06c1d117e95879e269b6ee22ff57e224314a44","abstract_canon_sha256":"b41e4e13356cda823e31e104a81689c122cdacf171686bf8a6dcecc25e2a0ddf"},"schema_version":"1.0"},"canonical_sha256":"2ed73a952fc6b7a0b2787e501ee8718faf48f5ec3df9ee0e93baa6e3d56ecbeb","source":{"kind":"arxiv","id":"2308.06942","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.06942","created_at":"2026-07-05T06:40:47Z"},{"alias_kind":"arxiv_version","alias_value":"2308.06942v1","created_at":"2026-07-05T06:40:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06942","created_at":"2026-07-05T06:40:47Z"},{"alias_kind":"pith_short_12","alias_value":"F3LTVFJPY232","created_at":"2026-07-05T06:40:47Z"},{"alias_kind":"pith_short_16","alias_value":"F3LTVFJPY232BMTY","created_at":"2026-07-05T06:40:47Z"},{"alias_kind":"pith_short_8","alias_value":"F3LTVFJP","created_at":"2026-07-05T06:40:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:F3LTVFJPY232BMTYPZIB52DRR6","target":"record","payload":{"canonical_record":{"source":{"id":"2308.06942","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-14T05:22:33Z","cross_cats_sorted":["cs.CL","cs.IT","math.IT"],"title_canon_sha256":"f181cc4d53458cb71533230daf06c1d117e95879e269b6ee22ff57e224314a44","abstract_canon_sha256":"b41e4e13356cda823e31e104a81689c122cdacf171686bf8a6dcecc25e2a0ddf"},"schema_version":"1.0"},"canonical_sha256":"2ed73a952fc6b7a0b2787e501ee8718faf48f5ec3df9ee0e93baa6e3d56ecbeb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:47.487459Z","signature_b64":"pPuoy6tCSDN77GYgtrHk4uTnAX68k4oPuI+jyWI1jUsUig7BvCk0CUy7/gl253oO1BwtZXelbCl1WD1xB58EAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ed73a952fc6b7a0b2787e501ee8718faf48f5ec3df9ee0e93baa6e3d56ecbeb","last_reissued_at":"2026-07-05T06:40:47.487032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:47.487032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.06942","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":"2026-07-05T06:40:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nX1x+0Ak978dgZFQfpnXDt9fuV3PT2fMatTz3UMVip+6aL1DGZ3du1QBkG9bobM6r66Sx5AaHSeAuK8hGulTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:20:29.731715Z"},"content_sha256":"b6d8c09e49d9662f6a95b7bdfbcb5c09d8f841d12a85471b89bf11331943eb0a","schema_version":"1.0","event_id":"sha256:b6d8c09e49d9662f6a95b7bdfbcb5c09d8f841d12a85471b89bf11331943eb0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:F3LTVFJPY232BMTYPZIB52DRR6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximating Human-Like Few-shot Learning with GPT-based Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IT","math.IT"],"primary_cat":"cs.AI","authors_text":"Cynthia Huang, Jimmy Lin, Ming Li, Yuqing Xie, Zhiying Jiang","submitted_at":"2023-08-14T05:22:33Z","abstract_excerpt":"In this work, we conceptualize the learning process as information compression. We seek to equip generative pre-trained models with human-like learning capabilities that enable data compression during inference. We present a novel approach that utilizes the Generative Pre-trained Transformer (GPT) to approximate Kolmogorov complexity, with the aim of estimating the optimal Information Distance for few-shot learning. We first propose using GPT as a prior for lossless text compression, achieving a noteworthy compression ratio. Experiment with LLAMA2-7B backbone achieves a compression ratio of 15"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06942","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/2308.06942/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":"2026-07-05T06:40:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gCYxJ4NtjNJJ63SWOyeVy2lDR8H9cIyIMbz/wGNH4TmafcuYP4xuW4GVSaC83il3a5exYAv4oZjytK8iMqLKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:20:29.732102Z"},"content_sha256":"30c92ce2004bdad2dfb093bdb5a56998d42e9109a385f49dd8ae755d38264020","schema_version":"1.0","event_id":"sha256:30c92ce2004bdad2dfb093bdb5a56998d42e9109a385f49dd8ae755d38264020"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F3LTVFJPY232BMTYPZIB52DRR6/bundle.json","state_url":"https://pith.science/pith/F3LTVFJPY232BMTYPZIB52DRR6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F3LTVFJPY232BMTYPZIB52DRR6/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":"2026-07-07T10:20:29Z","links":{"resolver":"https://pith.science/pith/F3LTVFJPY232BMTYPZIB52DRR6","bundle":"https://pith.science/pith/F3LTVFJPY232BMTYPZIB52DRR6/bundle.json","state":"https://pith.science/pith/F3LTVFJPY232BMTYPZIB52DRR6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F3LTVFJPY232BMTYPZIB52DRR6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:F3LTVFJPY232BMTYPZIB52DRR6","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":"b41e4e13356cda823e31e104a81689c122cdacf171686bf8a6dcecc25e2a0ddf","cross_cats_sorted":["cs.CL","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-14T05:22:33Z","title_canon_sha256":"f181cc4d53458cb71533230daf06c1d117e95879e269b6ee22ff57e224314a44"},"schema_version":"1.0","source":{"id":"2308.06942","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.06942","created_at":"2026-07-05T06:40:47Z"},{"alias_kind":"arxiv_version","alias_value":"2308.06942v1","created_at":"2026-07-05T06:40:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06942","created_at":"2026-07-05T06:40:47Z"},{"alias_kind":"pith_short_12","alias_value":"F3LTVFJPY232","created_at":"2026-07-05T06:40:47Z"},{"alias_kind":"pith_short_16","alias_value":"F3LTVFJPY232BMTY","created_at":"2026-07-05T06:40:47Z"},{"alias_kind":"pith_short_8","alias_value":"F3LTVFJP","created_at":"2026-07-05T06:40:47Z"}],"graph_snapshots":[{"event_id":"sha256:30c92ce2004bdad2dfb093bdb5a56998d42e9109a385f49dd8ae755d38264020","target":"graph","created_at":"2026-07-05T06:40:47Z","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/2308.06942/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we conceptualize the learning process as information compression. We seek to equip generative pre-trained models with human-like learning capabilities that enable data compression during inference. We present a novel approach that utilizes the Generative Pre-trained Transformer (GPT) to approximate Kolmogorov complexity, with the aim of estimating the optimal Information Distance for few-shot learning. We first propose using GPT as a prior for lossless text compression, achieving a noteworthy compression ratio. Experiment with LLAMA2-7B backbone achieves a compression ratio of 15","authors_text":"Cynthia Huang, Jimmy Lin, Ming Li, Yuqing Xie, Zhiying Jiang","cross_cats":["cs.CL","cs.IT","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-14T05:22:33Z","title":"Approximating Human-Like Few-shot Learning with GPT-based Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06942","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:b6d8c09e49d9662f6a95b7bdfbcb5c09d8f841d12a85471b89bf11331943eb0a","target":"record","created_at":"2026-07-05T06:40:47Z","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":"b41e4e13356cda823e31e104a81689c122cdacf171686bf8a6dcecc25e2a0ddf","cross_cats_sorted":["cs.CL","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-14T05:22:33Z","title_canon_sha256":"f181cc4d53458cb71533230daf06c1d117e95879e269b6ee22ff57e224314a44"},"schema_version":"1.0","source":{"id":"2308.06942","kind":"arxiv","version":1}},"canonical_sha256":"2ed73a952fc6b7a0b2787e501ee8718faf48f5ec3df9ee0e93baa6e3d56ecbeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ed73a952fc6b7a0b2787e501ee8718faf48f5ec3df9ee0e93baa6e3d56ecbeb","first_computed_at":"2026-07-05T06:40:47.487032Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:40:47.487032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pPuoy6tCSDN77GYgtrHk4uTnAX68k4oPuI+jyWI1jUsUig7BvCk0CUy7/gl253oO1BwtZXelbCl1WD1xB58EAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:40:47.487459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.06942","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6d8c09e49d9662f6a95b7bdfbcb5c09d8f841d12a85471b89bf11331943eb0a","sha256:30c92ce2004bdad2dfb093bdb5a56998d42e9109a385f49dd8ae755d38264020"],"state_sha256":"3f1eca0c2ed878de1dd70f4d032e15485a8bf94aacfc6c687a8559dd2ce3fabd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sKx6YW8RaGfJg/IeA9JUsPGUcGVQU/KstqhFMRv/fc5iPXz15hcMycWKtwa5IorUQ+KIfF1QrzEg3F3iSIPmDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:20:29.734054Z","bundle_sha256":"8481d4af9a731eef0f2ef1297ac57ee666252837e711b19c4629ede31774d23e"}}