{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:J3TIP23K4PWEPTNU7RCUE3RJV6","short_pith_number":"pith:J3TIP23K","schema_version":"1.0","canonical_sha256":"4ee687eb6ae3ec47cdb4fc45426e29afa6b604b7e0562c5b9092c4430a257eca","source":{"kind":"arxiv","id":"2103.14636","version":2},"attestation_state":"computed","paper":{"title":"A Practical Survey on Faster and Lighter Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Aloise, Ga\\'etan Marceau Caron, Quentin Fournier","submitted_at":"2021-03-26T17:54:47Z","abstract_excerpt":"Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model solely based on the attention mechanism that is able to relate any two positions of the input sequence, hence modelling arbitrary long dependencies. The Transformer has improved the state-of-the-art across numerous sequence modelling tasks. However, its effectiveness comes at the expense of a quadratic computational and memory complexity with respect to the seq"},"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":"2103.14636","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-26T17:54:47Z","cross_cats_sorted":[],"title_canon_sha256":"1626329e5f2cc24a7d201972a40ae13f47100a9e10425304e038a91cbd7b987c","abstract_canon_sha256":"188bb9d9a5f603acd26441a26a89d6e326d230abd388f2f83f20f904d319816f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:53.241643Z","signature_b64":"lGIwdKsFpL4sCBAjVwn49LgEo/q0d4GGRj7d/ZwcsF/tOUmK0R9lmPV+pk2ldTdoyPLvn8J8GXXpK6Ag6dQEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ee687eb6ae3ec47cdb4fc45426e29afa6b604b7e0562c5b9092c4430a257eca","last_reissued_at":"2026-07-05T05:54:53.241247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:53.241247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Practical Survey on Faster and Lighter Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Aloise, Ga\\'etan Marceau Caron, Quentin Fournier","submitted_at":"2021-03-26T17:54:47Z","abstract_excerpt":"Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model solely based on the attention mechanism that is able to relate any two positions of the input sequence, hence modelling arbitrary long dependencies. The Transformer has improved the state-of-the-art across numerous sequence modelling tasks. However, its effectiveness comes at the expense of a quadratic computational and memory complexity with respect to the seq"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14636","kind":"arxiv","version":2},"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/2103.14636/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":"2103.14636","created_at":"2026-07-05T05:54:53.241303+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.14636v2","created_at":"2026-07-05T05:54:53.241303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14636","created_at":"2026-07-05T05:54:53.241303+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3TIP23K4PWE","created_at":"2026-07-05T05:54:53.241303+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3TIP23K4PWEPTNU","created_at":"2026-07-05T05:54:53.241303+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3TIP23K","created_at":"2026-07-05T05:54:53.241303+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J3TIP23K4PWEPTNU7RCUE3RJV6","json":"https://pith.science/pith/J3TIP23K4PWEPTNU7RCUE3RJV6.json","graph_json":"https://pith.science/api/pith-number/J3TIP23K4PWEPTNU7RCUE3RJV6/graph.json","events_json":"https://pith.science/api/pith-number/J3TIP23K4PWEPTNU7RCUE3RJV6/events.json","paper":"https://pith.science/paper/J3TIP23K"},"agent_actions":{"view_html":"https://pith.science/pith/J3TIP23K4PWEPTNU7RCUE3RJV6","download_json":"https://pith.science/pith/J3TIP23K4PWEPTNU7RCUE3RJV6.json","view_paper":"https://pith.science/paper/J3TIP23K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.14636&json=true","fetch_graph":"https://pith.science/api/pith-number/J3TIP23K4PWEPTNU7RCUE3RJV6/graph.json","fetch_events":"https://pith.science/api/pith-number/J3TIP23K4PWEPTNU7RCUE3RJV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3TIP23K4PWEPTNU7RCUE3RJV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3TIP23K4PWEPTNU7RCUE3RJV6/action/storage_attestation","attest_author":"https://pith.science/pith/J3TIP23K4PWEPTNU7RCUE3RJV6/action/author_attestation","sign_citation":"https://pith.science/pith/J3TIP23K4PWEPTNU7RCUE3RJV6/action/citation_signature","submit_replication":"https://pith.science/pith/J3TIP23K4PWEPTNU7RCUE3RJV6/action/replication_record"}},"created_at":"2026-07-05T05:54:53.241303+00:00","updated_at":"2026-07-05T05:54:53.241303+00:00"}