{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BSKVST3PACEUM4YPM3T67UICAN","short_pith_number":"pith:BSKVST3P","canonical_record":{"source":{"id":"2306.02697","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-05T08:38:25Z","cross_cats_sorted":[],"title_canon_sha256":"08ccd80236b37e5e8c91c323c7e9dfa50a6db0b7b8975bb96b5d057fb2e0cec0","abstract_canon_sha256":"eef7056f37856d7ec97fa6f15439f6f31b9be58e59955941f46c03e26b980d46"},"schema_version":"1.0"},"canonical_sha256":"0c95594f6f008946730f66e7efd10203565d328d84948491b93ea906e4f11f6a","source":{"kind":"arxiv","id":"2306.02697","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02697","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02697v1","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02697","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"BSKVST3PACEU","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"BSKVST3PACEUM4YP","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"BSKVST3P","created_at":"2026-07-05T06:17:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BSKVST3PACEUM4YPM3T67UICAN","target":"record","payload":{"canonical_record":{"source":{"id":"2306.02697","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-05T08:38:25Z","cross_cats_sorted":[],"title_canon_sha256":"08ccd80236b37e5e8c91c323c7e9dfa50a6db0b7b8975bb96b5d057fb2e0cec0","abstract_canon_sha256":"eef7056f37856d7ec97fa6f15439f6f31b9be58e59955941f46c03e26b980d46"},"schema_version":"1.0"},"canonical_sha256":"0c95594f6f008946730f66e7efd10203565d328d84948491b93ea906e4f11f6a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:30.300995Z","signature_b64":"hsz4eXQJbcjoWMD4vqV7BpAXTkyWEJWxRCEGOM2YEdzBb6XB+xiJVj3MvfLZx8Azd4ptwoohoTjSe075ZoOrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c95594f6f008946730f66e7efd10203565d328d84948491b93ea906e4f11f6a","last_reissued_at":"2026-07-05T06:17:30.300529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:30.300529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.02697","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":"2026-07-05T06:17:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bjVAH8pT5bbE0Ye4xFHttkllUeQiVLNFuiIqmuenqTr5YXzUxIveD0P5+1zXMieso0HdPAiqXBnrwkQrwSysAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T14:41:21.056891Z"},"content_sha256":"0ae94e25a0a45bf2083365f64180c60c9e9771f54fd1fc474a12bc085b2dd384","schema_version":"1.0","event_id":"sha256:0ae94e25a0a45bf2083365f64180c60c9e9771f54fd1fc474a12bc085b2dd384"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BSKVST3PACEUM4YPM3T67UICAN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient GPT Model Pre-training using Tensor Train Matrix Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Panchenko, Georgii Novikov, Ivan Oseledets, Julia Gusak, Viktoriia Chekalina","submitted_at":"2023-06-05T08:38:25Z","abstract_excerpt":"Large-scale transformer models have shown remarkable performance in language modelling tasks. However, such models feature billions of parameters, leading to difficulties in their deployment and prohibitive training costs from scratch. To reduce the number of the parameters in the GPT-2 architecture, we replace the matrices of fully-connected layers with the corresponding Tensor Train Matrix~(TTM) structure. Finally, we customize forward and backward operations through the TTM-based layer for simplicity and the stableness of further training. %\nThe resulting GPT-2-based model stores up to 40% "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02697","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/2306.02697/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":"2026-07-05T06:17:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dEIjfMuO0eKks3fYWQ9tZ8JMfus41FBGE1bm9LLhiIwARJQZhS6f5nd1ROm2Wl3AFBOsgf2qjuUimk8449cmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T14:41:21.057524Z"},"content_sha256":"36315b49124034687156764d02ec40de60ddbb37bf5e57c4f5985e325f59c169","schema_version":"1.0","event_id":"sha256:36315b49124034687156764d02ec40de60ddbb37bf5e57c4f5985e325f59c169"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BSKVST3PACEUM4YPM3T67UICAN/bundle.json","state_url":"https://pith.science/pith/BSKVST3PACEUM4YPM3T67UICAN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BSKVST3PACEUM4YPM3T67UICAN/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":"2026-07-08T14:41:21Z","links":{"resolver":"https://pith.science/pith/BSKVST3PACEUM4YPM3T67UICAN","bundle":"https://pith.science/pith/BSKVST3PACEUM4YPM3T67UICAN/bundle.json","state":"https://pith.science/pith/BSKVST3PACEUM4YPM3T67UICAN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BSKVST3PACEUM4YPM3T67UICAN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BSKVST3PACEUM4YPM3T67UICAN","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":"eef7056f37856d7ec97fa6f15439f6f31b9be58e59955941f46c03e26b980d46","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-05T08:38:25Z","title_canon_sha256":"08ccd80236b37e5e8c91c323c7e9dfa50a6db0b7b8975bb96b5d057fb2e0cec0"},"schema_version":"1.0","source":{"id":"2306.02697","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02697","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02697v1","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02697","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"BSKVST3PACEU","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"BSKVST3PACEUM4YP","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"BSKVST3P","created_at":"2026-07-05T06:17:30Z"}],"graph_snapshots":[{"event_id":"sha256:36315b49124034687156764d02ec40de60ddbb37bf5e57c4f5985e325f59c169","target":"graph","created_at":"2026-07-05T06:17:30Z","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/2306.02697/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale transformer models have shown remarkable performance in language modelling tasks. However, such models feature billions of parameters, leading to difficulties in their deployment and prohibitive training costs from scratch. To reduce the number of the parameters in the GPT-2 architecture, we replace the matrices of fully-connected layers with the corresponding Tensor Train Matrix~(TTM) structure. Finally, we customize forward and backward operations through the TTM-based layer for simplicity and the stableness of further training. %\nThe resulting GPT-2-based model stores up to 40% ","authors_text":"Alexander Panchenko, Georgii Novikov, Ivan Oseledets, Julia Gusak, Viktoriia Chekalina","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-05T08:38:25Z","title":"Efficient GPT Model Pre-training using Tensor Train Matrix Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02697","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":"sha256:0ae94e25a0a45bf2083365f64180c60c9e9771f54fd1fc474a12bc085b2dd384","target":"record","created_at":"2026-07-05T06:17:30Z","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":"eef7056f37856d7ec97fa6f15439f6f31b9be58e59955941f46c03e26b980d46","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-05T08:38:25Z","title_canon_sha256":"08ccd80236b37e5e8c91c323c7e9dfa50a6db0b7b8975bb96b5d057fb2e0cec0"},"schema_version":"1.0","source":{"id":"2306.02697","kind":"arxiv","version":1}},"canonical_sha256":"0c95594f6f008946730f66e7efd10203565d328d84948491b93ea906e4f11f6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c95594f6f008946730f66e7efd10203565d328d84948491b93ea906e4f11f6a","first_computed_at":"2026-07-05T06:17:30.300529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:30.300529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hsz4eXQJbcjoWMD4vqV7BpAXTkyWEJWxRCEGOM2YEdzBb6XB+xiJVj3MvfLZx8Azd4ptwoohoTjSe075ZoOrBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:30.300995Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02697","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ae94e25a0a45bf2083365f64180c60c9e9771f54fd1fc474a12bc085b2dd384","sha256:36315b49124034687156764d02ec40de60ddbb37bf5e57c4f5985e325f59c169"],"state_sha256":"197ca47b7633c05c0c07ab25a0675f503d014360d45a7ccdb6e48f7cee1bb2e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6RGht4eXVfihY+LLHj4EIRRryPDjbHRcF1eXH+mEEeZXY99zSQNPmDjro3kMPO6xIpJNGUbQixcqRg1x2Z2eDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T14:41:21.060616Z","bundle_sha256":"3ca7543e417008b773cacb0def91c57fdaa32f54fd085135c4d09f7bde2c6aef"}}