{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4363D6Z62ZH4OYAPK5XRDC5RG7","short_pith_number":"pith:4363D6Z6","canonical_record":{"source":{"id":"2312.01897","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T13:51:16Z","cross_cats_sorted":[],"title_canon_sha256":"0e4970d29d864b65c2d8adc2dbfebb3b5b2df20fb2388221475ad364d28c1d43","abstract_canon_sha256":"fb6b307e1db10051b8a0940c2a6b067f9c18a10738126b3e8e945d6880939af9"},"schema_version":"1.0"},"canonical_sha256":"e6fdb1fb3ed64fc7600f576f118bb137fc7cc5e59b3d8a048505903040554394","source":{"kind":"arxiv","id":"2312.01897","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01897","created_at":"2026-07-05T08:08:00Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01897v2","created_at":"2026-07-05T08:08:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01897","created_at":"2026-07-05T08:08:00Z"},{"alias_kind":"pith_short_12","alias_value":"4363D6Z62ZH4","created_at":"2026-07-05T08:08:00Z"},{"alias_kind":"pith_short_16","alias_value":"4363D6Z62ZH4OYAP","created_at":"2026-07-05T08:08:00Z"},{"alias_kind":"pith_short_8","alias_value":"4363D6Z6","created_at":"2026-07-05T08:08:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4363D6Z62ZH4OYAPK5XRDC5RG7","target":"record","payload":{"canonical_record":{"source":{"id":"2312.01897","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T13:51:16Z","cross_cats_sorted":[],"title_canon_sha256":"0e4970d29d864b65c2d8adc2dbfebb3b5b2df20fb2388221475ad364d28c1d43","abstract_canon_sha256":"fb6b307e1db10051b8a0940c2a6b067f9c18a10738126b3e8e945d6880939af9"},"schema_version":"1.0"},"canonical_sha256":"e6fdb1fb3ed64fc7600f576f118bb137fc7cc5e59b3d8a048505903040554394","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:00.182095Z","signature_b64":"MViqp13cGRktOtJ66x3jpu+ZhuBkquqcuxVM+0XgMVSs+tkuV5tiPeZbe2t+cCSn+aLF5/RkiT8Co46mFlJoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6fdb1fb3ed64fc7600f576f118bb137fc7cc5e59b3d8a048505903040554394","last_reissued_at":"2026-07-05T08:08:00.181680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:00.181680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.01897","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:08:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hfW2uYu+xDgO4A8cTrfI4E4xN3OfrpLW6mTIkETCa1iNB7yt56lC2GVfHoC2t1GxFhqJ3fiDVRQwH1V340brAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:32:32.471894Z"},"content_sha256":"f3abc5ad49e24c28d788c6756f523e4bfb93aa24c9d84826e122eeddc53b1bcf","schema_version":"1.0","event_id":"sha256:f3abc5ad49e24c28d788c6756f523e4bfb93aa24c9d84826e122eeddc53b1bcf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4363D6Z62ZH4OYAPK5XRDC5RG7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adapting Short-Term Transformers for Action Detection in Untrimmed Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huan Gao, Limin Wang, Min Yang, Ping Guo","submitted_at":"2023-12-04T13:51:16Z","abstract_excerpt":"Vision Transformer (ViT) has shown high potential in video recognition, owing to its flexible design, adaptable self-attention mechanisms, and the efficacy of masked pre-training. Yet, it remains unclear how to adapt these pre-trained short-term ViTs for temporal action detection (TAD) in untrimmed videos. The existing works treat them as off-the-shelf feature extractors for each short-trimmed snippet without capturing the fine-grained relation among different snippets in a broader temporal context. To mitigate this issue, this paper focuses on designing a new mechanism for adapting these pre-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01897","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/2312.01897/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:08:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iuh5SlkEUWWv48wrzXdjAmY8r2x1acM4qnPxZ8UaFcqcjQ/YRGj4TF0btEDopWSLplSC6PPPpz/1QeI8sjBvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:32:32.472395Z"},"content_sha256":"9f460566c845c770d9f11ee6375bc046c24cfa276dbab216c36f7825ea816a67","schema_version":"1.0","event_id":"sha256:9f460566c845c770d9f11ee6375bc046c24cfa276dbab216c36f7825ea816a67"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4363D6Z62ZH4OYAPK5XRDC5RG7/bundle.json","state_url":"https://pith.science/pith/4363D6Z62ZH4OYAPK5XRDC5RG7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4363D6Z62ZH4OYAPK5XRDC5RG7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T21:32:32Z","links":{"resolver":"https://pith.science/pith/4363D6Z62ZH4OYAPK5XRDC5RG7","bundle":"https://pith.science/pith/4363D6Z62ZH4OYAPK5XRDC5RG7/bundle.json","state":"https://pith.science/pith/4363D6Z62ZH4OYAPK5XRDC5RG7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4363D6Z62ZH4OYAPK5XRDC5RG7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4363D6Z62ZH4OYAPK5XRDC5RG7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fb6b307e1db10051b8a0940c2a6b067f9c18a10738126b3e8e945d6880939af9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T13:51:16Z","title_canon_sha256":"0e4970d29d864b65c2d8adc2dbfebb3b5b2df20fb2388221475ad364d28c1d43"},"schema_version":"1.0","source":{"id":"2312.01897","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01897","created_at":"2026-07-05T08:08:00Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01897v2","created_at":"2026-07-05T08:08:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01897","created_at":"2026-07-05T08:08:00Z"},{"alias_kind":"pith_short_12","alias_value":"4363D6Z62ZH4","created_at":"2026-07-05T08:08:00Z"},{"alias_kind":"pith_short_16","alias_value":"4363D6Z62ZH4OYAP","created_at":"2026-07-05T08:08:00Z"},{"alias_kind":"pith_short_8","alias_value":"4363D6Z6","created_at":"2026-07-05T08:08:00Z"}],"graph_snapshots":[{"event_id":"sha256:9f460566c845c770d9f11ee6375bc046c24cfa276dbab216c36f7825ea816a67","target":"graph","created_at":"2026-07-05T08:08:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.01897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Transformer (ViT) has shown high potential in video recognition, owing to its flexible design, adaptable self-attention mechanisms, and the efficacy of masked pre-training. Yet, it remains unclear how to adapt these pre-trained short-term ViTs for temporal action detection (TAD) in untrimmed videos. The existing works treat them as off-the-shelf feature extractors for each short-trimmed snippet without capturing the fine-grained relation among different snippets in a broader temporal context. To mitigate this issue, this paper focuses on designing a new mechanism for adapting these pre-","authors_text":"Huan Gao, Limin Wang, Min Yang, Ping Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T13:51:16Z","title":"Adapting Short-Term Transformers for Action Detection in Untrimmed Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01897","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f3abc5ad49e24c28d788c6756f523e4bfb93aa24c9d84826e122eeddc53b1bcf","target":"record","created_at":"2026-07-05T08:08:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fb6b307e1db10051b8a0940c2a6b067f9c18a10738126b3e8e945d6880939af9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T13:51:16Z","title_canon_sha256":"0e4970d29d864b65c2d8adc2dbfebb3b5b2df20fb2388221475ad364d28c1d43"},"schema_version":"1.0","source":{"id":"2312.01897","kind":"arxiv","version":2}},"canonical_sha256":"e6fdb1fb3ed64fc7600f576f118bb137fc7cc5e59b3d8a048505903040554394","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6fdb1fb3ed64fc7600f576f118bb137fc7cc5e59b3d8a048505903040554394","first_computed_at":"2026-07-05T08:08:00.181680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:00.181680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MViqp13cGRktOtJ66x3jpu+ZhuBkquqcuxVM+0XgMVSs+tkuV5tiPeZbe2t+cCSn+aLF5/RkiT8Co46mFlJoAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:00.182095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.01897","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3abc5ad49e24c28d788c6756f523e4bfb93aa24c9d84826e122eeddc53b1bcf","sha256:9f460566c845c770d9f11ee6375bc046c24cfa276dbab216c36f7825ea816a67"],"state_sha256":"0c71cd9088d80897824333b74e85262eae9b5c02e51183f402ca49f4935c7b9a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pgq2u7rr98//hqgljMQ8RBhXhQDNEXfYBOe1fQmcu+v6leVNW8MUGq6Eqh8iS3Qx6T/Ee0LZ60GzlezSW+K2Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:32:32.477508Z","bundle_sha256":"1b66f78e689bd6421cdf91c2126a14c1cf14fbc51067e116b5fd70f0315caae6"}}