{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:H6LHXAT75EVJ4LRYHCSLREZ4TS","short_pith_number":"pith:H6LHXAT7","schema_version":"1.0","canonical_sha256":"3f967b827fe92a9e2e3838a4b8933c9c88adbb310c06ebe33f87a996a2fceada","source":{"kind":"arxiv","id":"2110.08568","version":1},"attestation_state":"computed","paper":{"title":"ASFormer: Transformer for Action Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangqiu Yi, Hongyu Wen, Tingting Jiang","submitted_at":"2021-10-16T13:07:20Z","abstract_excerpt":"Algorithms for the action segmentation task typically use temporal models to predict what action is occurring at each frame for a minute-long daily activity. Recent studies have shown the potential of Transformer in modeling the relations among elements in sequential data. However, there are several major concerns when directly applying the Transformer to the action segmentation task, such as the lack of inductive biases with small training sets, the deficit in processing long input sequence, and the limitation of the decoder architecture to utilize temporal relations among multiple action seg"},"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":"2110.08568","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-16T13:07:20Z","cross_cats_sorted":[],"title_canon_sha256":"a36cc147fc93dd2139c7c784c10609e3bbb316e254c8d1e026a465556c22536e","abstract_canon_sha256":"e99291345062ba250923c6aa4a5ba355252b0694f57ac7f1425ef8a5c8fe1785"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:18.356575Z","signature_b64":"e7zFgLZLwgnhc230H9yENinZkP8sglZ0eV2YLKWs5pnC9iVKiU3eC7+TAVGPePsWjdnAdJANKKXI2bEq1XRfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f967b827fe92a9e2e3838a4b8933c9c88adbb310c06ebe33f87a996a2fceada","last_reissued_at":"2026-07-05T03:23:18.356220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:18.356220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ASFormer: Transformer for Action Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangqiu Yi, Hongyu Wen, Tingting Jiang","submitted_at":"2021-10-16T13:07:20Z","abstract_excerpt":"Algorithms for the action segmentation task typically use temporal models to predict what action is occurring at each frame for a minute-long daily activity. Recent studies have shown the potential of Transformer in modeling the relations among elements in sequential data. However, there are several major concerns when directly applying the Transformer to the action segmentation task, such as the lack of inductive biases with small training sets, the deficit in processing long input sequence, and the limitation of the decoder architecture to utilize temporal relations among multiple action seg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08568","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/2110.08568/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":"2110.08568","created_at":"2026-07-05T03:23:18.356269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.08568v1","created_at":"2026-07-05T03:23:18.356269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08568","created_at":"2026-07-05T03:23:18.356269+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6LHXAT75EVJ","created_at":"2026-07-05T03:23:18.356269+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6LHXAT75EVJ4LRY","created_at":"2026-07-05T03:23:18.356269+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6LHXAT7","created_at":"2026-07-05T03:23:18.356269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23256","citing_title":"P-JEPA: Procedural Video Representation Learning via Joint Embedding Predictive Architecture","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26227","citing_title":"HOI-aware Adaptive Network for Weakly-supervised Action Segmentation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01668","citing_title":"IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09051","citing_title":"Fine-Grained Action Segmentation for Renorrhaphy in Robot-Assisted Partial Nephrectomy","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15173","citing_title":"Boundary-Centric Active Learning for Temporal Action Segmentation","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6LHXAT75EVJ4LRYHCSLREZ4TS","json":"https://pith.science/pith/H6LHXAT75EVJ4LRYHCSLREZ4TS.json","graph_json":"https://pith.science/api/pith-number/H6LHXAT75EVJ4LRYHCSLREZ4TS/graph.json","events_json":"https://pith.science/api/pith-number/H6LHXAT75EVJ4LRYHCSLREZ4TS/events.json","paper":"https://pith.science/paper/H6LHXAT7"},"agent_actions":{"view_html":"https://pith.science/pith/H6LHXAT75EVJ4LRYHCSLREZ4TS","download_json":"https://pith.science/pith/H6LHXAT75EVJ4LRYHCSLREZ4TS.json","view_paper":"https://pith.science/paper/H6LHXAT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.08568&json=true","fetch_graph":"https://pith.science/api/pith-number/H6LHXAT75EVJ4LRYHCSLREZ4TS/graph.json","fetch_events":"https://pith.science/api/pith-number/H6LHXAT75EVJ4LRYHCSLREZ4TS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6LHXAT75EVJ4LRYHCSLREZ4TS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6LHXAT75EVJ4LRYHCSLREZ4TS/action/storage_attestation","attest_author":"https://pith.science/pith/H6LHXAT75EVJ4LRYHCSLREZ4TS/action/author_attestation","sign_citation":"https://pith.science/pith/H6LHXAT75EVJ4LRYHCSLREZ4TS/action/citation_signature","submit_replication":"https://pith.science/pith/H6LHXAT75EVJ4LRYHCSLREZ4TS/action/replication_record"}},"created_at":"2026-07-05T03:23:18.356269+00:00","updated_at":"2026-07-05T03:23:18.356269+00:00"}