{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LYRLFXVIW7FXNGBSMJC5NEPDBR","short_pith_number":"pith:LYRLFXVI","canonical_record":{"source":{"id":"2507.07270","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-09T20:32:09Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"755d9713ff7890ddf438f8443b52e525ba0e5ecf8e48c5f140ed27ac40a5f61f","abstract_canon_sha256":"0042e33eca746a50e0db206a4ee285b227229f3ca3321b303eca6e4c40506768"},"schema_version":"1.0"},"canonical_sha256":"5e22b2dea8b7cb7698326245d691e30c50d3d6050c37800f2889956ed548aca7","source":{"kind":"arxiv","id":"2507.07270","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07270","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07270v1","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07270","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"pith_short_12","alias_value":"LYRLFXVIW7FX","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"pith_short_16","alias_value":"LYRLFXVIW7FXNGBS","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"pith_short_8","alias_value":"LYRLFXVI","created_at":"2026-07-05T11:34:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LYRLFXVIW7FXNGBSMJC5NEPDBR","target":"record","payload":{"canonical_record":{"source":{"id":"2507.07270","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-09T20:32:09Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"755d9713ff7890ddf438f8443b52e525ba0e5ecf8e48c5f140ed27ac40a5f61f","abstract_canon_sha256":"0042e33eca746a50e0db206a4ee285b227229f3ca3321b303eca6e4c40506768"},"schema_version":"1.0"},"canonical_sha256":"5e22b2dea8b7cb7698326245d691e30c50d3d6050c37800f2889956ed548aca7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:54.920322Z","signature_b64":"0Em7juNncGOXSEYXXAw8tpesgSI99elBWBVB4k3Ieav2dt+OD5d4aROQgDmk7L/vUHr+vO0geGdV8PtxQv2mCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e22b2dea8b7cb7698326245d691e30c50d3d6050c37800f2889956ed548aca7","last_reissued_at":"2026-07-05T11:34:54.919855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:54.919855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.07270","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":"2026-07-05T11:34:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZbDwGGzJf9IIFkxEIAbOGhZLAnYOg7SIhqnRWIl1pHoEn6obs4u6pDhSEkd/LnuA95gGq2uzLkxd7CuW5Vy/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:23:57.924101Z"},"content_sha256":"51fce032bcd3d77ccfb14a276f52121e6cb6d1a559faf6e3422646d090b64d45","schema_version":"1.0","event_id":"sha256:51fce032bcd3d77ccfb14a276f52121e6cb6d1a559faf6e3422646d090b64d45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LYRLFXVIW7FXNGBSMJC5NEPDBR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio-Visual Speech Separation via Bottleneck Iterative Network","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andrea Fanelli, Madalina Fiterau, Shiv Shankar, Sidong Zhang, Trang Nguyen","submitted_at":"2025-07-09T20:32:09Z","abstract_excerpt":"Integration of information from non-auditory cues can significantly improve the performance of speech-separation models. Often such models use deep modality-specific networks to obtain unimodal features, and risk being too costly or lightweight but lacking capacity. In this work, we present an iterative representation refinement approach called Bottleneck Iterative Network (BIN), a technique that repeatedly progresses through a lightweight fusion block, while bottlenecking fusion representations by fusion tokens. This helps improve the capacity of the model, while avoiding major increase in mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07270","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/2507.07270/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":"2026-07-05T11:34:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1HuS7nrAFio+YSXIqEUc9Q0M7g457vxPDhnYH+aGSQb545x+fZU7y3ISlu61Y1DjvTx5oR0RTGC7XU+cBWKcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:23:57.924482Z"},"content_sha256":"b5cae7d171702acf0caee5f4705ac65776381a3898fe7ce13b5335d4af6481b5","schema_version":"1.0","event_id":"sha256:b5cae7d171702acf0caee5f4705ac65776381a3898fe7ce13b5335d4af6481b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYRLFXVIW7FXNGBSMJC5NEPDBR/bundle.json","state_url":"https://pith.science/pith/LYRLFXVIW7FXNGBSMJC5NEPDBR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYRLFXVIW7FXNGBSMJC5NEPDBR/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":"2026-07-07T13:23:57Z","links":{"resolver":"https://pith.science/pith/LYRLFXVIW7FXNGBSMJC5NEPDBR","bundle":"https://pith.science/pith/LYRLFXVIW7FXNGBSMJC5NEPDBR/bundle.json","state":"https://pith.science/pith/LYRLFXVIW7FXNGBSMJC5NEPDBR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYRLFXVIW7FXNGBSMJC5NEPDBR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LYRLFXVIW7FXNGBSMJC5NEPDBR","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":"0042e33eca746a50e0db206a4ee285b227229f3ca3321b303eca6e4c40506768","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-09T20:32:09Z","title_canon_sha256":"755d9713ff7890ddf438f8443b52e525ba0e5ecf8e48c5f140ed27ac40a5f61f"},"schema_version":"1.0","source":{"id":"2507.07270","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07270","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07270v1","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07270","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"pith_short_12","alias_value":"LYRLFXVIW7FX","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"pith_short_16","alias_value":"LYRLFXVIW7FXNGBS","created_at":"2026-07-05T11:34:54Z"},{"alias_kind":"pith_short_8","alias_value":"LYRLFXVI","created_at":"2026-07-05T11:34:54Z"}],"graph_snapshots":[{"event_id":"sha256:b5cae7d171702acf0caee5f4705ac65776381a3898fe7ce13b5335d4af6481b5","target":"graph","created_at":"2026-07-05T11:34:54Z","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/2507.07270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Integration of information from non-auditory cues can significantly improve the performance of speech-separation models. Often such models use deep modality-specific networks to obtain unimodal features, and risk being too costly or lightweight but lacking capacity. In this work, we present an iterative representation refinement approach called Bottleneck Iterative Network (BIN), a technique that repeatedly progresses through a lightweight fusion block, while bottlenecking fusion representations by fusion tokens. This helps improve the capacity of the model, while avoiding major increase in mo","authors_text":"Andrea Fanelli, Madalina Fiterau, Shiv Shankar, Sidong Zhang, Trang Nguyen","cross_cats":["cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-09T20:32:09Z","title":"Audio-Visual Speech Separation via Bottleneck Iterative Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07270","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":"sha256:51fce032bcd3d77ccfb14a276f52121e6cb6d1a559faf6e3422646d090b64d45","target":"record","created_at":"2026-07-05T11:34:54Z","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":"0042e33eca746a50e0db206a4ee285b227229f3ca3321b303eca6e4c40506768","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-09T20:32:09Z","title_canon_sha256":"755d9713ff7890ddf438f8443b52e525ba0e5ecf8e48c5f140ed27ac40a5f61f"},"schema_version":"1.0","source":{"id":"2507.07270","kind":"arxiv","version":1}},"canonical_sha256":"5e22b2dea8b7cb7698326245d691e30c50d3d6050c37800f2889956ed548aca7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e22b2dea8b7cb7698326245d691e30c50d3d6050c37800f2889956ed548aca7","first_computed_at":"2026-07-05T11:34:54.919855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:54.919855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Em7juNncGOXSEYXXAw8tpesgSI99elBWBVB4k3Ieav2dt+OD5d4aROQgDmk7L/vUHr+vO0geGdV8PtxQv2mCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:54.920322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07270","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51fce032bcd3d77ccfb14a276f52121e6cb6d1a559faf6e3422646d090b64d45","sha256:b5cae7d171702acf0caee5f4705ac65776381a3898fe7ce13b5335d4af6481b5"],"state_sha256":"33b06d4827c4d96411952539b9e6f8df08d530cc970c069e7b3eb9e84ff14f07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lbOlprnusYiyFS0EpFTyKYT/NJuabSExTWs8jo2KkM8yOo/Yrca7s2KDklVVmy+ZjXixGOb5qWyodwM5wE/pBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:23:57.926423Z","bundle_sha256":"ef2fca5b89e2a166a89954b69d9bde5de08c5c27257cd221bdc6246e1eb079c6"}}