{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HIP76JM5A5CK5CTBWVXVUPT5TJ","short_pith_number":"pith:HIP76JM5","schema_version":"1.0","canonical_sha256":"3a1fff259d0744ae8a61b56f5a3e7d9a4313e0e030e1c40930c1ab058a7ab485","source":{"kind":"arxiv","id":"2503.14112","version":1},"attestation_state":"computed","paper":{"title":"Condensing Action Segmentation Datasets via Generative Network Inversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Yao, Guodong Ding, Rongyu Chen","submitted_at":"2025-03-18T10:29:47Z","abstract_excerpt":"This work presents the first condensation approach for procedural video datasets used in temporal action segmentation. We propose a condensation framework that leverages generative prior learned from the dataset and network inversion to condense data into compact latent codes with significant storage reduced across temporal and channel aspects. Orthogonally, we propose sampling diverse and representative action sequences to minimize video-wise redundancy. Our evaluation on standard benchmarks demonstrates consistent effectiveness in condensing TAS datasets and achieving competitive performance"},"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":"2503.14112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T10:29:47Z","cross_cats_sorted":[],"title_canon_sha256":"f4233bcdbda8b387152a55b5acd009f050127504ed387c14c7b627269edfefe8","abstract_canon_sha256":"cb212295845a1f6117e41509e3f47247b966cb60e7c0ab4fffcd6b19fa70dfef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:55.388056Z","signature_b64":"N2gkUiGs2iWrUkysuKTHSPTIfqRHZRXKjFMAJ9otBlxFVP2cuAi0l6A5+3yOZCUbYfnnDagXuhRO9GQ9FPLkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a1fff259d0744ae8a61b56f5a3e7d9a4313e0e030e1c40930c1ab058a7ab485","last_reissued_at":"2026-07-05T10:33:55.387393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:55.387393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Condensing Action Segmentation Datasets via Generative Network Inversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Yao, Guodong Ding, Rongyu Chen","submitted_at":"2025-03-18T10:29:47Z","abstract_excerpt":"This work presents the first condensation approach for procedural video datasets used in temporal action segmentation. We propose a condensation framework that leverages generative prior learned from the dataset and network inversion to condense data into compact latent codes with significant storage reduced across temporal and channel aspects. Orthogonally, we propose sampling diverse and representative action sequences to minimize video-wise redundancy. Our evaluation on standard benchmarks demonstrates consistent effectiveness in condensing TAS datasets and achieving competitive performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14112","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/2503.14112/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":"2503.14112","created_at":"2026-07-05T10:33:55.387466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.14112v1","created_at":"2026-07-05T10:33:55.387466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14112","created_at":"2026-07-05T10:33:55.387466+00:00"},{"alias_kind":"pith_short_12","alias_value":"HIP76JM5A5CK","created_at":"2026-07-05T10:33:55.387466+00:00"},{"alias_kind":"pith_short_16","alias_value":"HIP76JM5A5CK5CTB","created_at":"2026-07-05T10:33:55.387466+00:00"},{"alias_kind":"pith_short_8","alias_value":"HIP76JM5","created_at":"2026-07-05T10:33:55.387466+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/HIP76JM5A5CK5CTBWVXVUPT5TJ","json":"https://pith.science/pith/HIP76JM5A5CK5CTBWVXVUPT5TJ.json","graph_json":"https://pith.science/api/pith-number/HIP76JM5A5CK5CTBWVXVUPT5TJ/graph.json","events_json":"https://pith.science/api/pith-number/HIP76JM5A5CK5CTBWVXVUPT5TJ/events.json","paper":"https://pith.science/paper/HIP76JM5"},"agent_actions":{"view_html":"https://pith.science/pith/HIP76JM5A5CK5CTBWVXVUPT5TJ","download_json":"https://pith.science/pith/HIP76JM5A5CK5CTBWVXVUPT5TJ.json","view_paper":"https://pith.science/paper/HIP76JM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.14112&json=true","fetch_graph":"https://pith.science/api/pith-number/HIP76JM5A5CK5CTBWVXVUPT5TJ/graph.json","fetch_events":"https://pith.science/api/pith-number/HIP76JM5A5CK5CTBWVXVUPT5TJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HIP76JM5A5CK5CTBWVXVUPT5TJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HIP76JM5A5CK5CTBWVXVUPT5TJ/action/storage_attestation","attest_author":"https://pith.science/pith/HIP76JM5A5CK5CTBWVXVUPT5TJ/action/author_attestation","sign_citation":"https://pith.science/pith/HIP76JM5A5CK5CTBWVXVUPT5TJ/action/citation_signature","submit_replication":"https://pith.science/pith/HIP76JM5A5CK5CTBWVXVUPT5TJ/action/replication_record"}},"created_at":"2026-07-05T10:33:55.387466+00:00","updated_at":"2026-07-05T10:33:55.387466+00:00"}