{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PUQAIJANZK6QN2VX2XYBQYXEJ6","short_pith_number":"pith:PUQAIJAN","schema_version":"1.0","canonical_sha256":"7d2004240dcabd06eab7d5f01862e44f908f0c8ed649174f4c10749f9b9e84a9","source":{"kind":"arxiv","id":"2412.04353","version":1},"attestation_state":"computed","paper":{"title":"ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dayoung Gong, Minsu Cho, Suha Kwak","submitted_at":"2024-12-05T17:12:35Z","abstract_excerpt":"Temporal action segmentation and long-term action anticipation are two popular vision tasks for the temporal analysis of actions in videos. Despite apparent relevance and potential complementarity, these two problems have been investigated as separate and distinct tasks. In this work, we tackle these two problems, action segmentation and action anticipation, jointly using a unified diffusion model dubbed ActFusion. The key idea to unification is to train the model to effectively handle both visible and invisible parts of the sequence in an integrated manner; the visible part is for temporal se"},"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":"2412.04353","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:12:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a4175cd85be1204c275150d80e70a6f1b079f70c49d0e7e4f3b9299f9647db9a","abstract_canon_sha256":"70abbfafd6c29a1cda6a289089f4d1621e0530e32071003dd14786943a37df75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:02.691000Z","signature_b64":"Xq2oNJ545otT341AUYIOYqjPsDcqz4OL4KNxJt7BFiLvgOh2OkZHM/M2WDgiUy2KX+4tTujxs4h0YtdcFAfZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d2004240dcabd06eab7d5f01862e44f908f0c8ed649174f4c10749f9b9e84a9","last_reissued_at":"2026-07-05T09:45:02.690555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:02.690555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dayoung Gong, Minsu Cho, Suha Kwak","submitted_at":"2024-12-05T17:12:35Z","abstract_excerpt":"Temporal action segmentation and long-term action anticipation are two popular vision tasks for the temporal analysis of actions in videos. Despite apparent relevance and potential complementarity, these two problems have been investigated as separate and distinct tasks. In this work, we tackle these two problems, action segmentation and action anticipation, jointly using a unified diffusion model dubbed ActFusion. The key idea to unification is to train the model to effectively handle both visible and invisible parts of the sequence in an integrated manner; the visible part is for temporal se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04353","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/2412.04353/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":"2412.04353","created_at":"2026-07-05T09:45:02.690609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04353v1","created_at":"2026-07-05T09:45:02.690609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04353","created_at":"2026-07-05T09:45:02.690609+00:00"},{"alias_kind":"pith_short_12","alias_value":"PUQAIJANZK6Q","created_at":"2026-07-05T09:45:02.690609+00:00"},{"alias_kind":"pith_short_16","alias_value":"PUQAIJANZK6QN2VX","created_at":"2026-07-05T09:45:02.690609+00:00"},{"alias_kind":"pith_short_8","alias_value":"PUQAIJAN","created_at":"2026-07-05T09:45:02.690609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02382","citing_title":"Multi-level and Multi-modal Action Anticipation","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PUQAIJANZK6QN2VX2XYBQYXEJ6","json":"https://pith.science/pith/PUQAIJANZK6QN2VX2XYBQYXEJ6.json","graph_json":"https://pith.science/api/pith-number/PUQAIJANZK6QN2VX2XYBQYXEJ6/graph.json","events_json":"https://pith.science/api/pith-number/PUQAIJANZK6QN2VX2XYBQYXEJ6/events.json","paper":"https://pith.science/paper/PUQAIJAN"},"agent_actions":{"view_html":"https://pith.science/pith/PUQAIJANZK6QN2VX2XYBQYXEJ6","download_json":"https://pith.science/pith/PUQAIJANZK6QN2VX2XYBQYXEJ6.json","view_paper":"https://pith.science/paper/PUQAIJAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04353&json=true","fetch_graph":"https://pith.science/api/pith-number/PUQAIJANZK6QN2VX2XYBQYXEJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/PUQAIJANZK6QN2VX2XYBQYXEJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PUQAIJANZK6QN2VX2XYBQYXEJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PUQAIJANZK6QN2VX2XYBQYXEJ6/action/storage_attestation","attest_author":"https://pith.science/pith/PUQAIJANZK6QN2VX2XYBQYXEJ6/action/author_attestation","sign_citation":"https://pith.science/pith/PUQAIJANZK6QN2VX2XYBQYXEJ6/action/citation_signature","submit_replication":"https://pith.science/pith/PUQAIJANZK6QN2VX2XYBQYXEJ6/action/replication_record"}},"created_at":"2026-07-05T09:45:02.690609+00:00","updated_at":"2026-07-05T09:45:02.690609+00:00"}