{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5V5HEBYI2PZ4C6I2JIS5QWFEHM","short_pith_number":"pith:5V5HEBYI","schema_version":"1.0","canonical_sha256":"ed7a720708d3f3c1791a4a25d858a43b3ac0dc4e1e86a67c44c664c15deedade","source":{"kind":"arxiv","id":"2605.31115","version":1},"attestation_state":"computed","paper":{"title":"Polyphony: Diffusion-based Dual-Hand Action Segmentation with Alternating Vision Transformer and Semantic Conditioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zheng, Hu Wang, Prajjwal Bhattarai, Tiantian Zheng, Tuka Alhanai","submitted_at":"2026-05-29T10:26:50Z","abstract_excerpt":"Dual-hand action segmentation, densely predicting actions for both hands from untrimmed videos, is essential for understanding complex bimanual activities. However, it poses several unique challenges: complex inter-hand dependencies, visual asymmetry between hands, representation conflicts where the dominant hand monopolizes gradients, and semantic ambiguity in fine-grained actions. We propose Polyphony, a three-stage method to address these challenges through: (1) an Alternating Dual-Hand Vision Transformer that alternates training between left- and right-hand mini-batches to ensure balanced "},"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":"2605.31115","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T10:26:50Z","cross_cats_sorted":[],"title_canon_sha256":"d7e0931f74109fc04edf72ff0860136825bc3d154bef8f856273d34a099aa93a","abstract_canon_sha256":"72fb4a08118a2630d83ade81d79b4374001e16f6d56a839ecbd1a88912dd80b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:58.720611Z","signature_b64":"CGFNN833qajjhbHqbS15OMxoOZCebcGRgo/zuHfQPnJpXipXX8W/pMvDh22/+bRXq/8Ty9TSk5JFtktmO136Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed7a720708d3f3c1791a4a25d858a43b3ac0dc4e1e86a67c44c664c15deedade","last_reissued_at":"2026-06-01T01:03:58.719509Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:58.719509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Polyphony: Diffusion-based Dual-Hand Action Segmentation with Alternating Vision Transformer and Semantic Conditioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zheng, Hu Wang, Prajjwal Bhattarai, Tiantian Zheng, Tuka Alhanai","submitted_at":"2026-05-29T10:26:50Z","abstract_excerpt":"Dual-hand action segmentation, densely predicting actions for both hands from untrimmed videos, is essential for understanding complex bimanual activities. However, it poses several unique challenges: complex inter-hand dependencies, visual asymmetry between hands, representation conflicts where the dominant hand monopolizes gradients, and semantic ambiguity in fine-grained actions. We propose Polyphony, a three-stage method to address these challenges through: (1) an Alternating Dual-Hand Vision Transformer that alternates training between left- and right-hand mini-batches to ensure balanced "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31115","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/2605.31115/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":"2605.31115","created_at":"2026-06-01T01:03:58.719811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31115v1","created_at":"2026-06-01T01:03:58.719811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31115","created_at":"2026-06-01T01:03:58.719811+00:00"},{"alias_kind":"pith_short_12","alias_value":"5V5HEBYI2PZ4","created_at":"2026-06-01T01:03:58.719811+00:00"},{"alias_kind":"pith_short_16","alias_value":"5V5HEBYI2PZ4C6I2","created_at":"2026-06-01T01:03:58.719811+00:00"},{"alias_kind":"pith_short_8","alias_value":"5V5HEBYI","created_at":"2026-06-01T01:03:58.719811+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/5V5HEBYI2PZ4C6I2JIS5QWFEHM","json":"https://pith.science/pith/5V5HEBYI2PZ4C6I2JIS5QWFEHM.json","graph_json":"https://pith.science/api/pith-number/5V5HEBYI2PZ4C6I2JIS5QWFEHM/graph.json","events_json":"https://pith.science/api/pith-number/5V5HEBYI2PZ4C6I2JIS5QWFEHM/events.json","paper":"https://pith.science/paper/5V5HEBYI"},"agent_actions":{"view_html":"https://pith.science/pith/5V5HEBYI2PZ4C6I2JIS5QWFEHM","download_json":"https://pith.science/pith/5V5HEBYI2PZ4C6I2JIS5QWFEHM.json","view_paper":"https://pith.science/paper/5V5HEBYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31115&json=true","fetch_graph":"https://pith.science/api/pith-number/5V5HEBYI2PZ4C6I2JIS5QWFEHM/graph.json","fetch_events":"https://pith.science/api/pith-number/5V5HEBYI2PZ4C6I2JIS5QWFEHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5V5HEBYI2PZ4C6I2JIS5QWFEHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5V5HEBYI2PZ4C6I2JIS5QWFEHM/action/storage_attestation","attest_author":"https://pith.science/pith/5V5HEBYI2PZ4C6I2JIS5QWFEHM/action/author_attestation","sign_citation":"https://pith.science/pith/5V5HEBYI2PZ4C6I2JIS5QWFEHM/action/citation_signature","submit_replication":"https://pith.science/pith/5V5HEBYI2PZ4C6I2JIS5QWFEHM/action/replication_record"}},"created_at":"2026-06-01T01:03:58.719811+00:00","updated_at":"2026-06-01T01:03:58.719811+00:00"}