{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YG6NYVBBFDE6KMWHHSDIYBZUEM","short_pith_number":"pith:YG6NYVBB","schema_version":"1.0","canonical_sha256":"c1bcdc542128c9e532c73c868c07342337c8354354fa9fdaef68f70c7b0b3549","source":{"kind":"arxiv","id":"2309.01270","version":2},"attestation_state":"computed","paper":{"title":"COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Astrid Orcesi, Jaonary Rabarisoa, Julien Denize, Mykola Liashuha, Romain H\\'erault","submitted_at":"2023-09-03T20:50:53Z","abstract_excerpt":"We present COMEDIAN, a novel pipeline to initialize spatiotemporal transformers for action spotting, which involves self-supervised learning and knowledge distillation. Action spotting is a timestamp-level temporal action detection task. Our pipeline consists of three steps, with two initialization stages. First, we perform self-supervised initialization of a spatial transformer using short videos as input. Additionally, we initialize a temporal transformer that enhances the spatial transformer's outputs with global context through knowledge distillation from a pre-computed feature bank aligne"},"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":"2309.01270","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-03T20:50:53Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"785666e310937dd350aaf2f8b64c580e34e4c513e14c2a34a908466a125db1ad","abstract_canon_sha256":"ce46e98a66d1878f02470b1c619af9460a146a647ea60f964cc3e0ffd08df3d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:13.391087Z","signature_b64":"FJ6w0keMIEj76L3xt//QwJ2SFwVrJ+/5/54oj04QsCxBGctq5oXmAd3xz4Cd/wA+rJuBfST0uTjQTO31077nAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1bcdc542128c9e532c73c868c07342337c8354354fa9fdaef68f70c7b0b3549","last_reissued_at":"2026-07-05T07:05:13.390595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:13.390595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Astrid Orcesi, Jaonary Rabarisoa, Julien Denize, Mykola Liashuha, Romain H\\'erault","submitted_at":"2023-09-03T20:50:53Z","abstract_excerpt":"We present COMEDIAN, a novel pipeline to initialize spatiotemporal transformers for action spotting, which involves self-supervised learning and knowledge distillation. Action spotting is a timestamp-level temporal action detection task. Our pipeline consists of three steps, with two initialization stages. First, we perform self-supervised initialization of a spatial transformer using short videos as input. Additionally, we initialize a temporal transformer that enhances the spatial transformer's outputs with global context through knowledge distillation from a pre-computed feature bank aligne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01270","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/2309.01270/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":"2309.01270","created_at":"2026-07-05T07:05:13.390650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01270v2","created_at":"2026-07-05T07:05:13.390650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01270","created_at":"2026-07-05T07:05:13.390650+00:00"},{"alias_kind":"pith_short_12","alias_value":"YG6NYVBBFDE6","created_at":"2026-07-05T07:05:13.390650+00:00"},{"alias_kind":"pith_short_16","alias_value":"YG6NYVBBFDE6KMWH","created_at":"2026-07-05T07:05:13.390650+00:00"},{"alias_kind":"pith_short_8","alias_value":"YG6NYVBB","created_at":"2026-07-05T07:05:13.390650+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/YG6NYVBBFDE6KMWHHSDIYBZUEM","json":"https://pith.science/pith/YG6NYVBBFDE6KMWHHSDIYBZUEM.json","graph_json":"https://pith.science/api/pith-number/YG6NYVBBFDE6KMWHHSDIYBZUEM/graph.json","events_json":"https://pith.science/api/pith-number/YG6NYVBBFDE6KMWHHSDIYBZUEM/events.json","paper":"https://pith.science/paper/YG6NYVBB"},"agent_actions":{"view_html":"https://pith.science/pith/YG6NYVBBFDE6KMWHHSDIYBZUEM","download_json":"https://pith.science/pith/YG6NYVBBFDE6KMWHHSDIYBZUEM.json","view_paper":"https://pith.science/paper/YG6NYVBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01270&json=true","fetch_graph":"https://pith.science/api/pith-number/YG6NYVBBFDE6KMWHHSDIYBZUEM/graph.json","fetch_events":"https://pith.science/api/pith-number/YG6NYVBBFDE6KMWHHSDIYBZUEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YG6NYVBBFDE6KMWHHSDIYBZUEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YG6NYVBBFDE6KMWHHSDIYBZUEM/action/storage_attestation","attest_author":"https://pith.science/pith/YG6NYVBBFDE6KMWHHSDIYBZUEM/action/author_attestation","sign_citation":"https://pith.science/pith/YG6NYVBBFDE6KMWHHSDIYBZUEM/action/citation_signature","submit_replication":"https://pith.science/pith/YG6NYVBBFDE6KMWHHSDIYBZUEM/action/replication_record"}},"created_at":"2026-07-05T07:05:13.390650+00:00","updated_at":"2026-07-05T07:05:13.390650+00:00"}