{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZI2F4MQERPLZXJNDOH6NFLSTTK","short_pith_number":"pith:ZI2F4MQE","canonical_record":{"source":{"id":"2110.13412","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-26T04:50:42Z","cross_cats_sorted":[],"title_canon_sha256":"87b7d9be98904ca89e34c1c91354ae7c70ff13acd2ecebfdfa66581d47e1ad4e","abstract_canon_sha256":"68396053bc54ed5c2a64865cc5c006cf7eeafe20186f5a3565bca37ce0e80aff"},"schema_version":"1.0"},"canonical_sha256":"ca345e32048bd79ba5a371fcd2ae539abb1a3581c3ec5ac6b5418dd571855e01","source":{"kind":"arxiv","id":"2110.13412","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.13412","created_at":"2026-07-05T03:25:38Z"},{"alias_kind":"arxiv_version","alias_value":"2110.13412v1","created_at":"2026-07-05T03:25:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13412","created_at":"2026-07-05T03:25:38Z"},{"alias_kind":"pith_short_12","alias_value":"ZI2F4MQERPLZ","created_at":"2026-07-05T03:25:38Z"},{"alias_kind":"pith_short_16","alias_value":"ZI2F4MQERPLZXJND","created_at":"2026-07-05T03:25:38Z"},{"alias_kind":"pith_short_8","alias_value":"ZI2F4MQE","created_at":"2026-07-05T03:25:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZI2F4MQERPLZXJNDOH6NFLSTTK","target":"record","payload":{"canonical_record":{"source":{"id":"2110.13412","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-26T04:50:42Z","cross_cats_sorted":[],"title_canon_sha256":"87b7d9be98904ca89e34c1c91354ae7c70ff13acd2ecebfdfa66581d47e1ad4e","abstract_canon_sha256":"68396053bc54ed5c2a64865cc5c006cf7eeafe20186f5a3565bca37ce0e80aff"},"schema_version":"1.0"},"canonical_sha256":"ca345e32048bd79ba5a371fcd2ae539abb1a3581c3ec5ac6b5418dd571855e01","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:38.556833Z","signature_b64":"6TczvvouxWmeHAD6DTlGUsgqQ4W1N67LkTo0rXrE7cy/rlDm1yPi3FzY3lizvPJIPbbp9L8/kYe5JukuMJZVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca345e32048bd79ba5a371fcd2ae539abb1a3581c3ec5ac6b5418dd571855e01","last_reissued_at":"2026-07-05T03:25:38.556483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:38.556483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.13412","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":"2026-07-05T03:25:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lv+CnIdN5zAJbhNOAFJoQ42vd+TjRwNzahs6t0pFg6RZVeqH8y/NvMDBj2p+TIs1EtoWrqyGXhc2SF4HF07wCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T04:23:27.807766Z"},"content_sha256":"f4a19c47f8e9a706f866f817dafca47fcade746b36a7d148d538a297321364e9","schema_version":"1.0","event_id":"sha256:f4a19c47f8e9a706f866f817dafca47fcade746b36a7d148d538a297321364e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZI2F4MQERPLZXJNDOH6NFLSTTK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Leonid Sigal, Mengyu Yang, Tanzila Rahman","submitted_at":"2021-10-26T04:50:42Z","abstract_excerpt":"The recent success of transformer models in language, such as BERT, has motivated the use of such architectures for multi-modal feature learning and tasks. However, most multi-modal variants (e.g., ViLBERT) have limited themselves to visual-linguistic data. Relatively few have explored its use in audio-visual modalities, and none, to our knowledge, illustrate them in the context of granular audio-visual detection or segmentation tasks such as sound source separation and localization. In this work, we introduce TriBERT -- a transformer-based architecture, inspired by ViLBERT, which enables cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13412","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/2110.13412/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":"2026-07-05T03:25:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d8oFs+GkW/2LZjL2W2Ses5KGsFJrnQfnE/y2nxWlJLbJmS1frR4kmY7SofNV4Bpp7KrD8Cw4ylqwJPOfAcqVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T04:23:27.808254Z"},"content_sha256":"4a175aae56832bfa5c3041dd515931b16e45b27032759f401b3f7efa3f829b0a","schema_version":"1.0","event_id":"sha256:4a175aae56832bfa5c3041dd515931b16e45b27032759f401b3f7efa3f829b0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK/bundle.json","state_url":"https://pith.science/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK/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":"2026-08-21T04:23:27Z","links":{"resolver":"https://pith.science/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK","bundle":"https://pith.science/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK/bundle.json","state":"https://pith.science/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZI2F4MQERPLZXJNDOH6NFLSTTK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZI2F4MQERPLZXJNDOH6NFLSTTK","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":"68396053bc54ed5c2a64865cc5c006cf7eeafe20186f5a3565bca37ce0e80aff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-26T04:50:42Z","title_canon_sha256":"87b7d9be98904ca89e34c1c91354ae7c70ff13acd2ecebfdfa66581d47e1ad4e"},"schema_version":"1.0","source":{"id":"2110.13412","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.13412","created_at":"2026-07-05T03:25:38Z"},{"alias_kind":"arxiv_version","alias_value":"2110.13412v1","created_at":"2026-07-05T03:25:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13412","created_at":"2026-07-05T03:25:38Z"},{"alias_kind":"pith_short_12","alias_value":"ZI2F4MQERPLZ","created_at":"2026-07-05T03:25:38Z"},{"alias_kind":"pith_short_16","alias_value":"ZI2F4MQERPLZXJND","created_at":"2026-07-05T03:25:38Z"},{"alias_kind":"pith_short_8","alias_value":"ZI2F4MQE","created_at":"2026-07-05T03:25:38Z"}],"graph_snapshots":[{"event_id":"sha256:4a175aae56832bfa5c3041dd515931b16e45b27032759f401b3f7efa3f829b0a","target":"graph","created_at":"2026-07-05T03:25:38Z","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/2110.13412/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent success of transformer models in language, such as BERT, has motivated the use of such architectures for multi-modal feature learning and tasks. However, most multi-modal variants (e.g., ViLBERT) have limited themselves to visual-linguistic data. Relatively few have explored its use in audio-visual modalities, and none, to our knowledge, illustrate them in the context of granular audio-visual detection or segmentation tasks such as sound source separation and localization. In this work, we introduce TriBERT -- a transformer-based architecture, inspired by ViLBERT, which enables cont","authors_text":"Leonid Sigal, Mengyu Yang, Tanzila Rahman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-26T04:50:42Z","title":"TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13412","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:f4a19c47f8e9a706f866f817dafca47fcade746b36a7d148d538a297321364e9","target":"record","created_at":"2026-07-05T03:25:38Z","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":"68396053bc54ed5c2a64865cc5c006cf7eeafe20186f5a3565bca37ce0e80aff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-26T04:50:42Z","title_canon_sha256":"87b7d9be98904ca89e34c1c91354ae7c70ff13acd2ecebfdfa66581d47e1ad4e"},"schema_version":"1.0","source":{"id":"2110.13412","kind":"arxiv","version":1}},"canonical_sha256":"ca345e32048bd79ba5a371fcd2ae539abb1a3581c3ec5ac6b5418dd571855e01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca345e32048bd79ba5a371fcd2ae539abb1a3581c3ec5ac6b5418dd571855e01","first_computed_at":"2026-07-05T03:25:38.556483Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:25:38.556483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6TczvvouxWmeHAD6DTlGUsgqQ4W1N67LkTo0rXrE7cy/rlDm1yPi3FzY3lizvPJIPbbp9L8/kYe5JukuMJZVBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:25:38.556833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.13412","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4a19c47f8e9a706f866f817dafca47fcade746b36a7d148d538a297321364e9","sha256:4a175aae56832bfa5c3041dd515931b16e45b27032759f401b3f7efa3f829b0a"],"state_sha256":"de5b9a078b2ead41289322f212ceabbbc78ba2e3f1a8a0c7fabcb9ace9ad2bfb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HsSfYPDkp+Tvw0QyQN3dDmR49/6dOya0VCYDn0OWGIds0CBNGWunqiUhfhAobx+OZbDhRzdv419UBFgdWFzmDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T04:23:27.812820Z","bundle_sha256":"33b4b4691266479afa1678b4e8816214a2d28220bbeb13ce087f764ed52c5a3d"}}