{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UY2U6RQ5FBNPC2AWO72Q25NTPG","short_pith_number":"pith:UY2U6RQ5","canonical_record":{"source":{"id":"2501.10687","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T07:51:29Z","cross_cats_sorted":[],"title_canon_sha256":"25db5ad499b95b81cc5750cb1557ba71824545c1374350396bd482204dfaf2cf","abstract_canon_sha256":"f7cb2173119adea2a690c7d4059121c8f6f8621893e167b42dbd02ed74d9d93c"},"schema_version":"1.0"},"canonical_sha256":"a6354f461d285af1681677f50d75b3799c2803a28211fb7c9ae3e6c36e0b6283","source":{"kind":"arxiv","id":"2501.10687","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.10687","created_at":"2026-07-05T10:02:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.10687v1","created_at":"2026-07-05T10:02:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10687","created_at":"2026-07-05T10:02:31Z"},{"alias_kind":"pith_short_12","alias_value":"UY2U6RQ5FBNP","created_at":"2026-07-05T10:02:31Z"},{"alias_kind":"pith_short_16","alias_value":"UY2U6RQ5FBNPC2AW","created_at":"2026-07-05T10:02:31Z"},{"alias_kind":"pith_short_8","alias_value":"UY2U6RQ5","created_at":"2026-07-05T10:02:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UY2U6RQ5FBNPC2AWO72Q25NTPG","target":"record","payload":{"canonical_record":{"source":{"id":"2501.10687","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T07:51:29Z","cross_cats_sorted":[],"title_canon_sha256":"25db5ad499b95b81cc5750cb1557ba71824545c1374350396bd482204dfaf2cf","abstract_canon_sha256":"f7cb2173119adea2a690c7d4059121c8f6f8621893e167b42dbd02ed74d9d93c"},"schema_version":"1.0"},"canonical_sha256":"a6354f461d285af1681677f50d75b3799c2803a28211fb7c9ae3e6c36e0b6283","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:31.920994Z","signature_b64":"kaYlPPW8dl7XUONWVAQ2gNkGTvBd/GvwP4yPd6xbOFnS30Mzz8gZrQJXoBCquq7Mrev+4PQSjmGmJhyFU7LPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6354f461d285af1681677f50d75b3799c2803a28211fb7c9ae3e6c36e0b6283","last_reissued_at":"2026-07-05T10:02:31.920459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:31.920459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.10687","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nx/DcynToalm8uadhXuNbYjcPXn+d1YWYjvPwoyF1pcFONjygWFa9MlAYU0pVIrjvNQvrzq4TkDdXQf9ll64DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:58:45.264595Z"},"content_sha256":"198ea29f6810086726b5108569ea19faf5e499dd33488a65425847576bb29a1e","schema_version":"1.0","event_id":"sha256:198ea29f6810086726b5108569ea19faf5e499dd33488a65425847576bb29a1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UY2U6RQ5FBNPC2AWO72Q25NTPG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EMO2: End-Effector Guided Audio-Driven Avatar Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Liefeng Bo, Linrui Tian, Qi Wang, Siqi Hu","submitted_at":"2025-01-18T07:51:29Z","abstract_excerpt":"In this paper, we propose a novel audio-driven talking head method capable of simultaneously generating highly expressive facial expressions and hand gestures. Unlike existing methods that focus on generating full-body or half-body poses, we investigate the challenges of co-speech gesture generation and identify the weak correspondence between audio features and full-body gestures as a key limitation. To address this, we redefine the task as a two-stage process. In the first stage, we generate hand poses directly from audio input, leveraging the strong correlation between audio signals and han"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10687","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/2501.10687/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":"2026-07-05T10:02:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zLnMYHuhr8G3JpjuxHQikmzyi3Rk+z40d9YhJWKhKW6colh9NkU16KsYFgLbb61WiY9edby1OKhdK2HubUu3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:58:45.265266Z"},"content_sha256":"ca34004b8d5b5688ac236041507e6a8fef778123825c5fc1b0f6fe8d6161e14a","schema_version":"1.0","event_id":"sha256:ca34004b8d5b5688ac236041507e6a8fef778123825c5fc1b0f6fe8d6161e14a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG/bundle.json","state_url":"https://pith.science/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG/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":"2026-08-05T09:58:45Z","links":{"resolver":"https://pith.science/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG","bundle":"https://pith.science/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG/bundle.json","state":"https://pith.science/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UY2U6RQ5FBNPC2AWO72Q25NTPG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UY2U6RQ5FBNPC2AWO72Q25NTPG","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":"f7cb2173119adea2a690c7d4059121c8f6f8621893e167b42dbd02ed74d9d93c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T07:51:29Z","title_canon_sha256":"25db5ad499b95b81cc5750cb1557ba71824545c1374350396bd482204dfaf2cf"},"schema_version":"1.0","source":{"id":"2501.10687","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.10687","created_at":"2026-07-05T10:02:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.10687v1","created_at":"2026-07-05T10:02:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10687","created_at":"2026-07-05T10:02:31Z"},{"alias_kind":"pith_short_12","alias_value":"UY2U6RQ5FBNP","created_at":"2026-07-05T10:02:31Z"},{"alias_kind":"pith_short_16","alias_value":"UY2U6RQ5FBNPC2AW","created_at":"2026-07-05T10:02:31Z"},{"alias_kind":"pith_short_8","alias_value":"UY2U6RQ5","created_at":"2026-07-05T10:02:31Z"}],"graph_snapshots":[{"event_id":"sha256:ca34004b8d5b5688ac236041507e6a8fef778123825c5fc1b0f6fe8d6161e14a","target":"graph","created_at":"2026-07-05T10:02:31Z","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/2501.10687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel audio-driven talking head method capable of simultaneously generating highly expressive facial expressions and hand gestures. Unlike existing methods that focus on generating full-body or half-body poses, we investigate the challenges of co-speech gesture generation and identify the weak correspondence between audio features and full-body gestures as a key limitation. To address this, we redefine the task as a two-stage process. In the first stage, we generate hand poses directly from audio input, leveraging the strong correlation between audio signals and han","authors_text":"Bang Zhang, Liefeng Bo, Linrui Tian, Qi Wang, Siqi Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T07:51:29Z","title":"EMO2: End-Effector Guided Audio-Driven Avatar Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10687","kind":"arxiv","version":1},"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":"sha256:198ea29f6810086726b5108569ea19faf5e499dd33488a65425847576bb29a1e","target":"record","created_at":"2026-07-05T10:02:31Z","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":"f7cb2173119adea2a690c7d4059121c8f6f8621893e167b42dbd02ed74d9d93c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T07:51:29Z","title_canon_sha256":"25db5ad499b95b81cc5750cb1557ba71824545c1374350396bd482204dfaf2cf"},"schema_version":"1.0","source":{"id":"2501.10687","kind":"arxiv","version":1}},"canonical_sha256":"a6354f461d285af1681677f50d75b3799c2803a28211fb7c9ae3e6c36e0b6283","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6354f461d285af1681677f50d75b3799c2803a28211fb7c9ae3e6c36e0b6283","first_computed_at":"2026-07-05T10:02:31.920459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:31.920459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kaYlPPW8dl7XUONWVAQ2gNkGTvBd/GvwP4yPd6xbOFnS30Mzz8gZrQJXoBCquq7Mrev+4PQSjmGmJhyFU7LPDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:31.920994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.10687","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:198ea29f6810086726b5108569ea19faf5e499dd33488a65425847576bb29a1e","sha256:ca34004b8d5b5688ac236041507e6a8fef778123825c5fc1b0f6fe8d6161e14a"],"state_sha256":"69e65297454b78bbf5cb117f46ca49150b21ee2100a6efbb6a60887a0f752cb7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S2+dHXRpGRhaxk9vst2eVWOOQUX9K1v0Waw5Um4cxvw9llKDjZP9kuZpzr/AmKrF16yu8Vm7xbztMXDCMPYjCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:58:45.271395Z","bundle_sha256":"3460fae7a79ed69219bdd55d560036879b9c138203e13e419d5c3aa867c7a781"}}