{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MSJSO73ZDMTYG7VC4C6POTFX55","short_pith_number":"pith:MSJSO73Z","canonical_record":{"source":{"id":"2406.04212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-06T16:11:39Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"01570ec4c5d3c80453f8e05785912a8ef508ad52a36eb9f81625a53ab7a755b4","abstract_canon_sha256":"f76c2aa0b4215b91ad1173eea43457f98bfdf19cb7adb68e582145426d0fbffc"},"schema_version":"1.0"},"canonical_sha256":"6493277f791b27837ea2e0bcf74cb7ef6b951ebc56816e26faf54cd75aa3c3f6","source":{"kind":"arxiv","id":"2406.04212","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04212","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04212v1","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04212","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"pith_short_12","alias_value":"MSJSO73ZDMTY","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"pith_short_16","alias_value":"MSJSO73ZDMTYG7VC","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"pith_short_8","alias_value":"MSJSO73Z","created_at":"2026-07-05T08:28:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MSJSO73ZDMTYG7VC4C6POTFX55","target":"record","payload":{"canonical_record":{"source":{"id":"2406.04212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-06T16:11:39Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"01570ec4c5d3c80453f8e05785912a8ef508ad52a36eb9f81625a53ab7a755b4","abstract_canon_sha256":"f76c2aa0b4215b91ad1173eea43457f98bfdf19cb7adb68e582145426d0fbffc"},"schema_version":"1.0"},"canonical_sha256":"6493277f791b27837ea2e0bcf74cb7ef6b951ebc56816e26faf54cd75aa3c3f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:27.933950Z","signature_b64":"wqFXXDos+UC55z8RTLrh50xvXxK2bFI8u9j6SyY3ctNSplb1d4f1WYlKkkBByhoqBalvS+bTUCrwqhQ98V47Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6493277f791b27837ea2e0bcf74cb7ef6b951ebc56816e26faf54cd75aa3c3f6","last_reissued_at":"2026-07-05T08:28:27.933494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:27.933494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.04212","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":"2026-07-05T08:28:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zhfqi8IH2C71nwbkXBJLR4m47rlZFWDeZzOzJDxJirDLKLfIeC6EQHb/sLbLQDphBRwPlsTSgVaXsPGLShDrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T20:49:58.241255Z"},"content_sha256":"234f7db58284a603218dce30a9ebd56a22cfec4e0c23b6a347bf46626a37d79b","schema_version":"1.0","event_id":"sha256:234f7db58284a603218dce30a9ebd56a22cfec4e0c23b6a347bf46626a37d79b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MSJSO73ZDMTYG7VC4C6POTFX55","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sound Event Bounding Boxes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Francois G. Germain, Gordon Wichern, Janek Ebbers, Jonathan Le Roux","submitted_at":"2024-06-06T16:11:39Z","abstract_excerpt":"Sound event detection is the task of recognizing sounds and determining their extent (onset/offset times) within an audio clip. Existing systems commonly predict sound presence confidence in short time frames. Then, thresholding produces binary frame-level presence decisions, with the extent of individual events determined by merging consecutive positive frames. In this paper, we show that frame-level thresholding degrades the prediction of the event extent by coupling it with the system's sound presence confidence. We propose to decouple the prediction of event extent and confidence by introd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04212","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/2406.04212/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":"2026-07-05T08:28:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0VOB6jFrfE8byEgEq4KpbYYhd39ep6+X/mCpzKfaBYeJOmL6MoqkftYClLQS9Uw/sfTekp6TzeuwmdDkHnZzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T20:49:58.241649Z"},"content_sha256":"c2f1ade486339f3a60b31b2fe96dc9bfbf567e6cea12e6a05d6f7eefe4fbb9fc","schema_version":"1.0","event_id":"sha256:c2f1ade486339f3a60b31b2fe96dc9bfbf567e6cea12e6a05d6f7eefe4fbb9fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MSJSO73ZDMTYG7VC4C6POTFX55/bundle.json","state_url":"https://pith.science/pith/MSJSO73ZDMTYG7VC4C6POTFX55/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MSJSO73ZDMTYG7VC4C6POTFX55/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":"2026-07-08T20:49:58Z","links":{"resolver":"https://pith.science/pith/MSJSO73ZDMTYG7VC4C6POTFX55","bundle":"https://pith.science/pith/MSJSO73ZDMTYG7VC4C6POTFX55/bundle.json","state":"https://pith.science/pith/MSJSO73ZDMTYG7VC4C6POTFX55/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MSJSO73ZDMTYG7VC4C6POTFX55/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MSJSO73ZDMTYG7VC4C6POTFX55","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":"f76c2aa0b4215b91ad1173eea43457f98bfdf19cb7adb68e582145426d0fbffc","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-06T16:11:39Z","title_canon_sha256":"01570ec4c5d3c80453f8e05785912a8ef508ad52a36eb9f81625a53ab7a755b4"},"schema_version":"1.0","source":{"id":"2406.04212","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04212","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04212v1","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04212","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"pith_short_12","alias_value":"MSJSO73ZDMTY","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"pith_short_16","alias_value":"MSJSO73ZDMTYG7VC","created_at":"2026-07-05T08:28:27Z"},{"alias_kind":"pith_short_8","alias_value":"MSJSO73Z","created_at":"2026-07-05T08:28:27Z"}],"graph_snapshots":[{"event_id":"sha256:c2f1ade486339f3a60b31b2fe96dc9bfbf567e6cea12e6a05d6f7eefe4fbb9fc","target":"graph","created_at":"2026-07-05T08:28:27Z","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/2406.04212/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sound event detection is the task of recognizing sounds and determining their extent (onset/offset times) within an audio clip. Existing systems commonly predict sound presence confidence in short time frames. Then, thresholding produces binary frame-level presence decisions, with the extent of individual events determined by merging consecutive positive frames. In this paper, we show that frame-level thresholding degrades the prediction of the event extent by coupling it with the system's sound presence confidence. We propose to decouple the prediction of event extent and confidence by introd","authors_text":"Francois G. Germain, Gordon Wichern, Janek Ebbers, Jonathan Le Roux","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-06T16:11:39Z","title":"Sound Event Bounding Boxes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04212","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":"sha256:234f7db58284a603218dce30a9ebd56a22cfec4e0c23b6a347bf46626a37d79b","target":"record","created_at":"2026-07-05T08:28:27Z","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":"f76c2aa0b4215b91ad1173eea43457f98bfdf19cb7adb68e582145426d0fbffc","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-06T16:11:39Z","title_canon_sha256":"01570ec4c5d3c80453f8e05785912a8ef508ad52a36eb9f81625a53ab7a755b4"},"schema_version":"1.0","source":{"id":"2406.04212","kind":"arxiv","version":1}},"canonical_sha256":"6493277f791b27837ea2e0bcf74cb7ef6b951ebc56816e26faf54cd75aa3c3f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6493277f791b27837ea2e0bcf74cb7ef6b951ebc56816e26faf54cd75aa3c3f6","first_computed_at":"2026-07-05T08:28:27.933494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:27.933494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wqFXXDos+UC55z8RTLrh50xvXxK2bFI8u9j6SyY3ctNSplb1d4f1WYlKkkBByhoqBalvS+bTUCrwqhQ98V47Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:27.933950Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04212","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:234f7db58284a603218dce30a9ebd56a22cfec4e0c23b6a347bf46626a37d79b","sha256:c2f1ade486339f3a60b31b2fe96dc9bfbf567e6cea12e6a05d6f7eefe4fbb9fc"],"state_sha256":"8fef62ca9ab231d5aa09d4f3a3b20124d556d556fb58118a38ea21706bc0726f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OzMHxjHyp2ndUVWizbpwmdz3/GmQ0YCM0LklkhwF92PEJAxiQeG8okiYl9UWgxwY2RR+p0g5M5610IHZOmbQBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T20:49:58.243778Z","bundle_sha256":"2d02794972c3c054ca446de6056e991c7eec24632845e05c4c99585970bbe54a"}}