{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KRERIWPVO7G2WTFV6BOYL5H4AS","short_pith_number":"pith:KRERIWPV","schema_version":"1.0","canonical_sha256":"54491459f577cdab4cb5f05d85f4fc049a97746aedab9e91c5f9becb4ba9db68","source":{"kind":"arxiv","id":"2408.12293","version":1},"attestation_state":"computed","paper":{"title":"AT-SNN: Adaptive Tokens for Vision Transformer on Spiking Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Brent Kang, Donghwa Kang, Eun-Kyu Lee, Hyeongboo Baek, Jinkyu Lee, Youngmoon Lee","submitted_at":"2024-08-22T11:06:18Z","abstract_excerpt":"In the training and inference of spiking neural networks (SNNs), direct training and lightweight computation methods have been orthogonally developed, aimed at reducing power consumption. However, only a limited number of approaches have applied these two mechanisms simultaneously and failed to fully leverage the advantages of SNN-based vision transformers (ViTs) since they were originally designed for convolutional neural networks (CNNs). In this paper, we propose AT-SNN designed to dynamically adjust the number of tokens processed during inference in SNN-based ViTs with direct training, wher"},"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":"2408.12293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-22T11:06:18Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1cab73232ecf2701e6737b04dfbe3ffb72c471494a75168d1e99cbcd6e656941","abstract_canon_sha256":"945c04ae5f0aeb9b78c8555e30639954421d3c22ec3e581681f9272199fa9834"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:07.141855Z","signature_b64":"3ngT5m9kOjYplE3es6xkmXZsjuPtC1HhsceVQ/H8DoPKvrFWB4YUmMpAGW9AqYMB7snf4Ih9URT28/z+phn7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54491459f577cdab4cb5f05d85f4fc049a97746aedab9e91c5f9becb4ba9db68","last_reissued_at":"2026-07-05T08:58:07.141371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:07.141371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AT-SNN: Adaptive Tokens for Vision Transformer on Spiking Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Brent Kang, Donghwa Kang, Eun-Kyu Lee, Hyeongboo Baek, Jinkyu Lee, Youngmoon Lee","submitted_at":"2024-08-22T11:06:18Z","abstract_excerpt":"In the training and inference of spiking neural networks (SNNs), direct training and lightweight computation methods have been orthogonally developed, aimed at reducing power consumption. However, only a limited number of approaches have applied these two mechanisms simultaneously and failed to fully leverage the advantages of SNN-based vision transformers (ViTs) since they were originally designed for convolutional neural networks (CNNs). In this paper, we propose AT-SNN designed to dynamically adjust the number of tokens processed during inference in SNN-based ViTs with direct training, wher"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12293","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/2408.12293/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":"2408.12293","created_at":"2026-07-05T08:58:07.141430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12293v1","created_at":"2026-07-05T08:58:07.141430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12293","created_at":"2026-07-05T08:58:07.141430+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRERIWPVO7G2","created_at":"2026-07-05T08:58:07.141430+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRERIWPVO7G2WTFV","created_at":"2026-07-05T08:58:07.141430+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRERIWPV","created_at":"2026-07-05T08:58:07.141430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09276","citing_title":"Uncertainty-Aware Token Importance Estimation in Spiking Transformers","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KRERIWPVO7G2WTFV6BOYL5H4AS","json":"https://pith.science/pith/KRERIWPVO7G2WTFV6BOYL5H4AS.json","graph_json":"https://pith.science/api/pith-number/KRERIWPVO7G2WTFV6BOYL5H4AS/graph.json","events_json":"https://pith.science/api/pith-number/KRERIWPVO7G2WTFV6BOYL5H4AS/events.json","paper":"https://pith.science/paper/KRERIWPV"},"agent_actions":{"view_html":"https://pith.science/pith/KRERIWPVO7G2WTFV6BOYL5H4AS","download_json":"https://pith.science/pith/KRERIWPVO7G2WTFV6BOYL5H4AS.json","view_paper":"https://pith.science/paper/KRERIWPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12293&json=true","fetch_graph":"https://pith.science/api/pith-number/KRERIWPVO7G2WTFV6BOYL5H4AS/graph.json","fetch_events":"https://pith.science/api/pith-number/KRERIWPVO7G2WTFV6BOYL5H4AS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRERIWPVO7G2WTFV6BOYL5H4AS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRERIWPVO7G2WTFV6BOYL5H4AS/action/storage_attestation","attest_author":"https://pith.science/pith/KRERIWPVO7G2WTFV6BOYL5H4AS/action/author_attestation","sign_citation":"https://pith.science/pith/KRERIWPVO7G2WTFV6BOYL5H4AS/action/citation_signature","submit_replication":"https://pith.science/pith/KRERIWPVO7G2WTFV6BOYL5H4AS/action/replication_record"}},"created_at":"2026-07-05T08:58:07.141430+00:00","updated_at":"2026-07-05T08:58:07.141430+00:00"}