{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3YVNNRROQO5UHXJPI3ZCOZ5LE5","short_pith_number":"pith:3YVNNRRO","canonical_record":{"source":{"id":"1704.01985","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-03-22T08:39:32Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"c44361d10eea9ee57508133f422a080bea00a3fdb577008716bb5a82be1311f0","abstract_canon_sha256":"37cad79edcd5dca75ab86aad23f0c60b4a890e8f744ba77b5de0608da6d5cf14"},"schema_version":"1.0"},"canonical_sha256":"de2ad6c62e83bb43dd2f46f22767ab27696223ff06efd38f956490886bd44c87","source":{"kind":"arxiv","id":"1704.01985","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.01985","created_at":"2026-05-17T23:59:03Z"},{"alias_kind":"arxiv_version","alias_value":"1704.01985v4","created_at":"2026-05-17T23:59:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.01985","created_at":"2026-05-17T23:59:03Z"},{"alias_kind":"pith_short_12","alias_value":"3YVNNRROQO5U","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3YVNNRROQO5UHXJP","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3YVNNRRO","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3YVNNRROQO5UHXJPI3ZCOZ5LE5","target":"record","payload":{"canonical_record":{"source":{"id":"1704.01985","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-03-22T08:39:32Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"c44361d10eea9ee57508133f422a080bea00a3fdb577008716bb5a82be1311f0","abstract_canon_sha256":"37cad79edcd5dca75ab86aad23f0c60b4a890e8f744ba77b5de0608da6d5cf14"},"schema_version":"1.0"},"canonical_sha256":"de2ad6c62e83bb43dd2f46f22767ab27696223ff06efd38f956490886bd44c87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:03.774120Z","signature_b64":"633pfGyGH+qEJa6sROO7Z+wHZfuEfmIZFHlDKDFNcfbyBOw1Jmqw3ilh/NrANTdY2s61OII7Tfgjy/pQoNeIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de2ad6c62e83bb43dd2f46f22767ab27696223ff06efd38f956490886bd44c87","last_reissued_at":"2026-05-17T23:59:03.773612Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:03.773612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.01985","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VIo6hN+68BXWHfyMY84CkMXVVQC0gZ14n0fKC5Is8CvYGlZsqYqER+BtTErDgNLrAqVMj+xFnPtu6WCcodFmCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:02:48.217453Z"},"content_sha256":"48d72e724878670ca6a42281fb57eb0f7f8865285dd326ff9756b9fee9cd4ef6","schema_version":"1.0","event_id":"sha256:48d72e724878670ca6a42281fb57eb0f7f8865285dd326ff9756b9fee9cd4ef6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3YVNNRROQO5UHXJPI3ZCOZ5LE5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recognizing Multi-talker Speech with Permutation Invariant Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dong Yu, Xuankai Chang, Yanmin Qian","submitted_at":"2017-03-22T08:39:32Z","abstract_excerpt":"In this paper, we propose a novel technique for direct recognition of multiple speech streams given the single channel of mixed speech, without first separating them. Our technique is based on permutation invariant training (PIT) for automatic speech recognition (ASR). In PIT-ASR, we compute the average cross entropy (CE) over all frames in the whole utterance for each possible output-target assignment, pick the one with the minimum CE, and optimize for that assignment. PIT-ASR forces all the frames of the same speaker to be aligned with the same output layer. This strategy elegantly solves th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.01985","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:59:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"22ZD3w/8Bf65Sr1gPrle9FcZmtlqPGvzliMY4NVASeWBvBQ2+FpjFwuzxQP3wjk1rL42FzPN2xw3HfCE1EC/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:02:48.218115Z"},"content_sha256":"793350aa5fbbc92b347c95505404f878f76d492ff1dd18b844c0499735884fd6","schema_version":"1.0","event_id":"sha256:793350aa5fbbc92b347c95505404f878f76d492ff1dd18b844c0499735884fd6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3YVNNRROQO5UHXJPI3ZCOZ5LE5/bundle.json","state_url":"https://pith.science/pith/3YVNNRROQO5UHXJPI3ZCOZ5LE5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3YVNNRROQO5UHXJPI3ZCOZ5LE5/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":"2026-08-09T22:02:48Z","links":{"resolver":"https://pith.science/pith/3YVNNRROQO5UHXJPI3ZCOZ5LE5","bundle":"https://pith.science/pith/3YVNNRROQO5UHXJPI3ZCOZ5LE5/bundle.json","state":"https://pith.science/pith/3YVNNRROQO5UHXJPI3ZCOZ5LE5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3YVNNRROQO5UHXJPI3ZCOZ5LE5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3YVNNRROQO5UHXJPI3ZCOZ5LE5","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":"37cad79edcd5dca75ab86aad23f0c60b4a890e8f744ba77b5de0608da6d5cf14","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-03-22T08:39:32Z","title_canon_sha256":"c44361d10eea9ee57508133f422a080bea00a3fdb577008716bb5a82be1311f0"},"schema_version":"1.0","source":{"id":"1704.01985","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.01985","created_at":"2026-05-17T23:59:03Z"},{"alias_kind":"arxiv_version","alias_value":"1704.01985v4","created_at":"2026-05-17T23:59:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.01985","created_at":"2026-05-17T23:59:03Z"},{"alias_kind":"pith_short_12","alias_value":"3YVNNRROQO5U","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3YVNNRROQO5UHXJP","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3YVNNRRO","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:793350aa5fbbc92b347c95505404f878f76d492ff1dd18b844c0499735884fd6","target":"graph","created_at":"2026-05-17T23:59:03Z","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"},"paper":{"abstract_excerpt":"In this paper, we propose a novel technique for direct recognition of multiple speech streams given the single channel of mixed speech, without first separating them. Our technique is based on permutation invariant training (PIT) for automatic speech recognition (ASR). In PIT-ASR, we compute the average cross entropy (CE) over all frames in the whole utterance for each possible output-target assignment, pick the one with the minimum CE, and optimize for that assignment. PIT-ASR forces all the frames of the same speaker to be aligned with the same output layer. This strategy elegantly solves th","authors_text":"Dong Yu, Xuankai Chang, Yanmin Qian","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-03-22T08:39:32Z","title":"Recognizing Multi-talker Speech with Permutation Invariant Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.01985","kind":"arxiv","version":4},"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":"sha256:48d72e724878670ca6a42281fb57eb0f7f8865285dd326ff9756b9fee9cd4ef6","target":"record","created_at":"2026-05-17T23:59:03Z","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":"37cad79edcd5dca75ab86aad23f0c60b4a890e8f744ba77b5de0608da6d5cf14","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-03-22T08:39:32Z","title_canon_sha256":"c44361d10eea9ee57508133f422a080bea00a3fdb577008716bb5a82be1311f0"},"schema_version":"1.0","source":{"id":"1704.01985","kind":"arxiv","version":4}},"canonical_sha256":"de2ad6c62e83bb43dd2f46f22767ab27696223ff06efd38f956490886bd44c87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de2ad6c62e83bb43dd2f46f22767ab27696223ff06efd38f956490886bd44c87","first_computed_at":"2026-05-17T23:59:03.773612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:03.773612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"633pfGyGH+qEJa6sROO7Z+wHZfuEfmIZFHlDKDFNcfbyBOw1Jmqw3ilh/NrANTdY2s61OII7Tfgjy/pQoNeIBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:03.774120Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.01985","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48d72e724878670ca6a42281fb57eb0f7f8865285dd326ff9756b9fee9cd4ef6","sha256:793350aa5fbbc92b347c95505404f878f76d492ff1dd18b844c0499735884fd6"],"state_sha256":"c9f9ec89442d3797e6c4e29c8ebc4ed0f2f8684ffc735c7d5f083006d35d9bfc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZMxh3Q/ttOE1ETDvMsdDELHdOPNRZ6c4dIbDvTc5IelFXyD9H0AScr0/sGZmtb/tBSkpWSif+slaK2KtSyYACQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:02:48.225595Z","bundle_sha256":"aa1b01a12177d8241167e849d9b1231a802935a2b51ae765e9fecf845314fa47"}}