{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:35GK6FLMXWNX66MLB2U6FPVLCV","short_pith_number":"pith:35GK6FLM","schema_version":"1.0","canonical_sha256":"df4caf156cbd9b7f798b0ea9e2beab156b3484d04e3a66513b2981b51854771b","source":{"kind":"arxiv","id":"2607.05263","version":1},"attestation_state":"computed","paper":{"title":"Learning Probabilistic Embeddings for Unsupervised Action Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duc Manh Vu, Juergen Gall, Shuai Li","submitted_at":"2026-07-06T16:10:25Z","abstract_excerpt":"This paper concerns the problem of unsupervised temporal action segmentation for long, untrimmed videos. Recent successful approaches follow a joint representation learning and clustering paradigm, where optimal transport (OT) is adopted to produce pseudo labels for learning frame representations. These approaches alternate between estimating pseudo labels using OT and optimizing the parameters with gradient descent during training, where OT is used for obtaining the final temporal action segmentation. A major limitation of these works is that they learn a deterministic embedding for frame rep"},"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":"2607.05263","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-06T16:10:25Z","cross_cats_sorted":[],"title_canon_sha256":"4e3ea74817903b8418d546435e45fa59f1b7fe747bbe44bb0903d1d01c178d3d","abstract_canon_sha256":"c5b150959cd5f0032305105e2248670c337cde499062bcc1dbb59c16fffd897b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T03:19:21.390217Z","signature_b64":"RapZ248jHSVtvR1vwvgkZPAc0WjIkhcDpSvTbLbjQ6bTPO/mXUmj7yg/SOyHhEL6+Tc8otX1wpsf6yj8GaH7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df4caf156cbd9b7f798b0ea9e2beab156b3484d04e3a66513b2981b51854771b","last_reissued_at":"2026-07-07T03:19:21.389762Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T03:19:21.389762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Probabilistic Embeddings for Unsupervised Action Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duc Manh Vu, Juergen Gall, Shuai Li","submitted_at":"2026-07-06T16:10:25Z","abstract_excerpt":"This paper concerns the problem of unsupervised temporal action segmentation for long, untrimmed videos. Recent successful approaches follow a joint representation learning and clustering paradigm, where optimal transport (OT) is adopted to produce pseudo labels for learning frame representations. These approaches alternate between estimating pseudo labels using OT and optimizing the parameters with gradient descent during training, where OT is used for obtaining the final temporal action segmentation. A major limitation of these works is that they learn a deterministic embedding for frame rep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05263","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/2607.05263/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":"2607.05263","created_at":"2026-07-07T03:19:21.389817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.05263v1","created_at":"2026-07-07T03:19:21.389817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05263","created_at":"2026-07-07T03:19:21.389817+00:00"},{"alias_kind":"pith_short_12","alias_value":"35GK6FLMXWNX","created_at":"2026-07-07T03:19:21.389817+00:00"},{"alias_kind":"pith_short_16","alias_value":"35GK6FLMXWNX66ML","created_at":"2026-07-07T03:19:21.389817+00:00"},{"alias_kind":"pith_short_8","alias_value":"35GK6FLM","created_at":"2026-07-07T03:19:21.389817+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/35GK6FLMXWNX66MLB2U6FPVLCV","json":"https://pith.science/pith/35GK6FLMXWNX66MLB2U6FPVLCV.json","graph_json":"https://pith.science/api/pith-number/35GK6FLMXWNX66MLB2U6FPVLCV/graph.json","events_json":"https://pith.science/api/pith-number/35GK6FLMXWNX66MLB2U6FPVLCV/events.json","paper":"https://pith.science/paper/35GK6FLM"},"agent_actions":{"view_html":"https://pith.science/pith/35GK6FLMXWNX66MLB2U6FPVLCV","download_json":"https://pith.science/pith/35GK6FLMXWNX66MLB2U6FPVLCV.json","view_paper":"https://pith.science/paper/35GK6FLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.05263&json=true","fetch_graph":"https://pith.science/api/pith-number/35GK6FLMXWNX66MLB2U6FPVLCV/graph.json","fetch_events":"https://pith.science/api/pith-number/35GK6FLMXWNX66MLB2U6FPVLCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35GK6FLMXWNX66MLB2U6FPVLCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35GK6FLMXWNX66MLB2U6FPVLCV/action/storage_attestation","attest_author":"https://pith.science/pith/35GK6FLMXWNX66MLB2U6FPVLCV/action/author_attestation","sign_citation":"https://pith.science/pith/35GK6FLMXWNX66MLB2U6FPVLCV/action/citation_signature","submit_replication":"https://pith.science/pith/35GK6FLMXWNX66MLB2U6FPVLCV/action/replication_record"}},"created_at":"2026-07-07T03:19:21.389817+00:00","updated_at":"2026-07-07T03:19:21.389817+00:00"}