{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:HCKOYBOU5VSWJPAETW3JLPLZGC","short_pith_number":"pith:HCKOYBOU","canonical_record":{"source":{"id":"2207.12504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-25T20:07:14Z","cross_cats_sorted":[],"title_canon_sha256":"ea279313f2a5e7a3a4b074a0e6b2edaad36a341c564edb921788eb503c0b2fc7","abstract_canon_sha256":"72d4524a56508b2a98b99c987ba40be3ba870d1d612f174b278d047b04125b9f"},"schema_version":"1.0"},"canonical_sha256":"3894ec05d4ed6564bc049db695bd7930acccd6f0fabad995a45290db6f90c7e8","source":{"kind":"arxiv","id":"2207.12504","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.12504","created_at":"2026-07-05T04:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"2207.12504v1","created_at":"2026-07-05T04:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12504","created_at":"2026-07-05T04:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"HCKOYBOU5VSW","created_at":"2026-07-05T04:43:23Z"},{"alias_kind":"pith_short_16","alias_value":"HCKOYBOU5VSWJPAE","created_at":"2026-07-05T04:43:23Z"},{"alias_kind":"pith_short_8","alias_value":"HCKOYBOU","created_at":"2026-07-05T04:43:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:HCKOYBOU5VSWJPAETW3JLPLZGC","target":"record","payload":{"canonical_record":{"source":{"id":"2207.12504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-25T20:07:14Z","cross_cats_sorted":[],"title_canon_sha256":"ea279313f2a5e7a3a4b074a0e6b2edaad36a341c564edb921788eb503c0b2fc7","abstract_canon_sha256":"72d4524a56508b2a98b99c987ba40be3ba870d1d612f174b278d047b04125b9f"},"schema_version":"1.0"},"canonical_sha256":"3894ec05d4ed6564bc049db695bd7930acccd6f0fabad995a45290db6f90c7e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:43:23.023242Z","signature_b64":"Ab5dLsD70T9pshlyxVEGSbketf95WW8w8CK9in5fwKTcMD2UP4OJgO30pyuw0L5IgS2Y+396/JfFVRSFJuJdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3894ec05d4ed6564bc049db695bd7930acccd6f0fabad995a45290db6f90c7e8","last_reissued_at":"2026-07-05T04:43:23.022905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:43:23.022905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.12504","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":"2026-07-05T04:43:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"29SZMn9YvE4V9etN5eC/WCqUe+JJO/qUxmSuVL3uQTCr7rm/x0hGhE8LEloZvFYPpsY1VVEUY2ylDox3fyJZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:43:09.167117Z"},"content_sha256":"05722611ba93b70ae48a53469ee225260e438340558de4489a1cbc7a94cfd5bd","schema_version":"1.0","event_id":"sha256:05722611ba93b70ae48a53469ee225260e438340558de4489a1cbc7a94cfd5bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:HCKOYBOU5VSWJPAETW3JLPLZGC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Speaker Diarization that is Agnostic to Language, Overlap-Aware, and Tuning Free","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Diego Casabuena, Jussi Karlgren, M. Iftekhar Tanveer, Rosie Jones","submitted_at":"2022-07-25T20:07:14Z","abstract_excerpt":"Podcasts are conversational in nature and speaker changes are frequent -- requiring speaker diarization for content understanding. We propose an unsupervised technique for speaker diarization without relying on language-specific components. The algorithm is overlap-aware and does not require information about the number of speakers. Our approach shows 79% improvement on purity scores (34% on F-score) against the Google Cloud Platform solution on podcast data."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12504","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/2207.12504/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":"2026-07-05T04:43:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"peX38UTl7Wn96mpXsqvxUzX++1KWDYEqFZo8bJonzBJtF1tY/KdyAxPiivRsMmJqWoBYc06IOeX1B/ST4bIDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:43:09.167509Z"},"content_sha256":"e44ef63eccc040ca552b502f1e38307a3d01baf6eeccf7c52e0672fa9e16f72c","schema_version":"1.0","event_id":"sha256:e44ef63eccc040ca552b502f1e38307a3d01baf6eeccf7c52e0672fa9e16f72c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HCKOYBOU5VSWJPAETW3JLPLZGC/bundle.json","state_url":"https://pith.science/pith/HCKOYBOU5VSWJPAETW3JLPLZGC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HCKOYBOU5VSWJPAETW3JLPLZGC/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":"2026-07-06T12:43:09Z","links":{"resolver":"https://pith.science/pith/HCKOYBOU5VSWJPAETW3JLPLZGC","bundle":"https://pith.science/pith/HCKOYBOU5VSWJPAETW3JLPLZGC/bundle.json","state":"https://pith.science/pith/HCKOYBOU5VSWJPAETW3JLPLZGC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HCKOYBOU5VSWJPAETW3JLPLZGC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HCKOYBOU5VSWJPAETW3JLPLZGC","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":"72d4524a56508b2a98b99c987ba40be3ba870d1d612f174b278d047b04125b9f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-25T20:07:14Z","title_canon_sha256":"ea279313f2a5e7a3a4b074a0e6b2edaad36a341c564edb921788eb503c0b2fc7"},"schema_version":"1.0","source":{"id":"2207.12504","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.12504","created_at":"2026-07-05T04:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"2207.12504v1","created_at":"2026-07-05T04:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12504","created_at":"2026-07-05T04:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"HCKOYBOU5VSW","created_at":"2026-07-05T04:43:23Z"},{"alias_kind":"pith_short_16","alias_value":"HCKOYBOU5VSWJPAE","created_at":"2026-07-05T04:43:23Z"},{"alias_kind":"pith_short_8","alias_value":"HCKOYBOU","created_at":"2026-07-05T04:43:23Z"}],"graph_snapshots":[{"event_id":"sha256:e44ef63eccc040ca552b502f1e38307a3d01baf6eeccf7c52e0672fa9e16f72c","target":"graph","created_at":"2026-07-05T04:43:23Z","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/2207.12504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Podcasts are conversational in nature and speaker changes are frequent -- requiring speaker diarization for content understanding. We propose an unsupervised technique for speaker diarization without relying on language-specific components. The algorithm is overlap-aware and does not require information about the number of speakers. Our approach shows 79% improvement on purity scores (34% on F-score) against the Google Cloud Platform solution on podcast data.","authors_text":"Diego Casabuena, Jussi Karlgren, M. Iftekhar Tanveer, Rosie Jones","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-25T20:07:14Z","title":"Unsupervised Speaker Diarization that is Agnostic to Language, Overlap-Aware, and Tuning Free"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12504","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":"sha256:05722611ba93b70ae48a53469ee225260e438340558de4489a1cbc7a94cfd5bd","target":"record","created_at":"2026-07-05T04:43:23Z","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":"72d4524a56508b2a98b99c987ba40be3ba870d1d612f174b278d047b04125b9f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-25T20:07:14Z","title_canon_sha256":"ea279313f2a5e7a3a4b074a0e6b2edaad36a341c564edb921788eb503c0b2fc7"},"schema_version":"1.0","source":{"id":"2207.12504","kind":"arxiv","version":1}},"canonical_sha256":"3894ec05d4ed6564bc049db695bd7930acccd6f0fabad995a45290db6f90c7e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3894ec05d4ed6564bc049db695bd7930acccd6f0fabad995a45290db6f90c7e8","first_computed_at":"2026-07-05T04:43:23.022905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:43:23.022905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ab5dLsD70T9pshlyxVEGSbketf95WW8w8CK9in5fwKTcMD2UP4OJgO30pyuw0L5IgS2Y+396/JfFVRSFJuJdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:43:23.023242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.12504","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05722611ba93b70ae48a53469ee225260e438340558de4489a1cbc7a94cfd5bd","sha256:e44ef63eccc040ca552b502f1e38307a3d01baf6eeccf7c52e0672fa9e16f72c"],"state_sha256":"65dca4e90b4a27830f970b16739bece254cb7f56fbcc065e317ab93486adc2d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KsZxRorwywEHmZRWknATeWY/4wjJ5zAkPVNqxS1uu1GRETSf+H0P1FHNC3B6pCCZ1hPFgoflm+dj2aVMP875AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T12:43:09.169472Z","bundle_sha256":"91db5ca5f21c7bcf6e8ac65d2421daea59f55b99251b733defcae7dcd1286678"}}