{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DZRQRTUPU4XQOGM7JDWC3HRWW4","short_pith_number":"pith:DZRQRTUP","schema_version":"1.0","canonical_sha256":"1e6308ce8fa72f07199f48ec2d9e36b7176875c5ef39dba8efabdb0d954967ec","source":{"kind":"arxiv","id":"2502.16627","version":4},"attestation_state":"computed","paper":{"title":"Energy-Efficient Transformer Inference: Optimization Strategies for Time Series Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PF"],"primary_cat":"cs.LG","authors_text":"Arshia Kermani, Ehsan Zeraatkar, Habib Irani","submitted_at":"2025-02-23T16:04:56Z","abstract_excerpt":"The increasing computational demands of transformer models in time series classification necessitate effective optimization strategies for energy-efficient deployment. Our study presents a systematic investigation of optimization techniques, focusing on structured pruning and quantization methods for transformer architectures. Through extensive experimentation on three distinct datasets (RefrigerationDevices, ElectricDevices, and PLAID), we quantitatively evaluate model performance and energy efficiency across different transformer configurations. Our experimental results demonstrate that stat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.16627","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-23T16:04:56Z","cross_cats_sorted":["cs.AI","cs.PF"],"title_canon_sha256":"d92563fa225073f163432ef1d031b5dc91aaf6dcce7c5b5edf0d5f1517c55a42","abstract_canon_sha256":"b812386efaabf69e98e7ad9d28c9f58a26deaf1049bee232b7bf3d7339505e50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:28.752548Z","signature_b64":"PavrdFkJr2InpdYmKq2kj5y+xZwKFOBGKkCba/7fWTTn5faqqgufmyGsAp0Kx3BY4A0mStE1wvgvtpUFgHLZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e6308ce8fa72f07199f48ec2d9e36b7176875c5ef39dba8efabdb0d954967ec","last_reissued_at":"2026-07-05T11:06:28.752011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:28.752011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-Efficient Transformer Inference: Optimization Strategies for Time Series Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PF"],"primary_cat":"cs.LG","authors_text":"Arshia Kermani, Ehsan Zeraatkar, Habib Irani","submitted_at":"2025-02-23T16:04:56Z","abstract_excerpt":"The increasing computational demands of transformer models in time series classification necessitate effective optimization strategies for energy-efficient deployment. Our study presents a systematic investigation of optimization techniques, focusing on structured pruning and quantization methods for transformer architectures. Through extensive experimentation on three distinct datasets (RefrigerationDevices, ElectricDevices, and PLAID), we quantitatively evaluate model performance and energy efficiency across different transformer configurations. Our experimental results demonstrate that stat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16627","kind":"arxiv","version":4},"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/2502.16627/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.16627","created_at":"2026-07-05T11:06:28.752072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16627v4","created_at":"2026-07-05T11:06:28.752072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16627","created_at":"2026-07-05T11:06:28.752072+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZRQRTUPU4XQ","created_at":"2026-07-05T11:06:28.752072+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZRQRTUPU4XQOGM7","created_at":"2026-07-05T11:06:28.752072+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZRQRTUP","created_at":"2026-07-05T11:06:28.752072+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11040","citing_title":"Large Language models for Time Series Analysis: Techniques, Applications, and Challenges","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZRQRTUPU4XQOGM7JDWC3HRWW4","json":"https://pith.science/pith/DZRQRTUPU4XQOGM7JDWC3HRWW4.json","graph_json":"https://pith.science/api/pith-number/DZRQRTUPU4XQOGM7JDWC3HRWW4/graph.json","events_json":"https://pith.science/api/pith-number/DZRQRTUPU4XQOGM7JDWC3HRWW4/events.json","paper":"https://pith.science/paper/DZRQRTUP"},"agent_actions":{"view_html":"https://pith.science/pith/DZRQRTUPU4XQOGM7JDWC3HRWW4","download_json":"https://pith.science/pith/DZRQRTUPU4XQOGM7JDWC3HRWW4.json","view_paper":"https://pith.science/paper/DZRQRTUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16627&json=true","fetch_graph":"https://pith.science/api/pith-number/DZRQRTUPU4XQOGM7JDWC3HRWW4/graph.json","fetch_events":"https://pith.science/api/pith-number/DZRQRTUPU4XQOGM7JDWC3HRWW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZRQRTUPU4XQOGM7JDWC3HRWW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZRQRTUPU4XQOGM7JDWC3HRWW4/action/storage_attestation","attest_author":"https://pith.science/pith/DZRQRTUPU4XQOGM7JDWC3HRWW4/action/author_attestation","sign_citation":"https://pith.science/pith/DZRQRTUPU4XQOGM7JDWC3HRWW4/action/citation_signature","submit_replication":"https://pith.science/pith/DZRQRTUPU4XQOGM7JDWC3HRWW4/action/replication_record"}},"created_at":"2026-07-05T11:06:28.752072+00:00","updated_at":"2026-07-05T11:06:28.752072+00:00"}