{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GHFBJ72HW77P35ZLCKFANMSKPO","short_pith_number":"pith:GHFBJ72H","canonical_record":{"source":{"id":"2606.17160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T18:01:08Z","cross_cats_sorted":[],"title_canon_sha256":"1e264cad5089da870415e3ac2e642d0e8d01ac86decc1e3bf9a5792561cec7c7","abstract_canon_sha256":"b63b5a31c147e5a2b529e55bb375213189d0a18d46593d218e730eb572dc6a51"},"schema_version":"1.0"},"canonical_sha256":"31ca14ff47b7fefdf72b128a06b24a7b9e0fd06dd47e3f6b2b371f55c8792588","source":{"kind":"arxiv","id":"2606.17160","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17160","created_at":"2026-06-19T16:10:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17160v1","created_at":"2026-06-19T16:10:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17160","created_at":"2026-06-19T16:10:04Z"},{"alias_kind":"pith_short_12","alias_value":"GHFBJ72HW77P","created_at":"2026-06-19T16:10:04Z"},{"alias_kind":"pith_short_16","alias_value":"GHFBJ72HW77P35ZL","created_at":"2026-06-19T16:10:04Z"},{"alias_kind":"pith_short_8","alias_value":"GHFBJ72H","created_at":"2026-06-19T16:10:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GHFBJ72HW77P35ZLCKFANMSKPO","target":"record","payload":{"canonical_record":{"source":{"id":"2606.17160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T18:01:08Z","cross_cats_sorted":[],"title_canon_sha256":"1e264cad5089da870415e3ac2e642d0e8d01ac86decc1e3bf9a5792561cec7c7","abstract_canon_sha256":"b63b5a31c147e5a2b529e55bb375213189d0a18d46593d218e730eb572dc6a51"},"schema_version":"1.0"},"canonical_sha256":"31ca14ff47b7fefdf72b128a06b24a7b9e0fd06dd47e3f6b2b371f55c8792588","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:04.707948Z","signature_b64":"DzCg5iHMiQH3Kx3DQyoDfp8uugZnmF9xQT6zPV4GRlTdgQz2ErvOTYNlCUFYRVltwsuN+KlvY1mR5+W37DrKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31ca14ff47b7fefdf72b128a06b24a7b9e0fd06dd47e3f6b2b371f55c8792588","last_reissued_at":"2026-06-19T16:10:04.707611Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:04.707611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.17160","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":"2026-06-19T16:10:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gPei/eIytnyUAqKvk+oG0jUczBQZp5eF2hBX0A+vcJ4uSxnx0afYvjsrB0N9Qk/IbJQZF3Svjo2pyAA7oKT0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T21:54:48.154394Z"},"content_sha256":"26dbece7e03ebf11b0ff15e34d0db996427392ebd2d59660c07a435c6ad6edac","schema_version":"1.0","event_id":"sha256:26dbece7e03ebf11b0ff15e34d0db996427392ebd2d59660c07a435c6ad6edac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GHFBJ72HW77P35ZLCKFANMSKPO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transductive Zero-Shot Audio Classification with Audio-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Jingwen Zhou, Mingzhe Wang","submitted_at":"2026-06-15T18:01:08Z","abstract_excerpt":"Contrastive language-audio pretraining (CLAP) enables zero-shot audio classification, but standard inference classifies each clip in isolation and ignores the structure of the unlabeled test set. We present the first systematic study of TransCLIP-style transductive inference for CLAP: a text-anchored spherical Gaussian-mixture EM that refines zero-shot posteriors using the audio-embedding statistics of the test batch, with no labels, no gradients, and negligible compute (about 15 ms on one CPU core for 2,000 clips). Across ESC-50, UrbanSound8K, and VocalSound, this consistently improves top-1 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17160","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/2606.17160/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":"2026-06-19T16:10:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zAUmyvAJEssJKcWhE8CbY6lcsAII0fVlBbLT1pMaqlN+4OPs24qLurdGdfSqGQFlDCQdb5dhYVU314MmpptiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T21:54:48.154761Z"},"content_sha256":"b43cb80fe45281b21df2194772dd0f74741addf78ff1c00eb9e287da97de1c43","schema_version":"1.0","event_id":"sha256:b43cb80fe45281b21df2194772dd0f74741addf78ff1c00eb9e287da97de1c43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GHFBJ72HW77P35ZLCKFANMSKPO/bundle.json","state_url":"https://pith.science/pith/GHFBJ72HW77P35ZLCKFANMSKPO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GHFBJ72HW77P35ZLCKFANMSKPO/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":"2026-06-29T21:54:48Z","links":{"resolver":"https://pith.science/pith/GHFBJ72HW77P35ZLCKFANMSKPO","bundle":"https://pith.science/pith/GHFBJ72HW77P35ZLCKFANMSKPO/bundle.json","state":"https://pith.science/pith/GHFBJ72HW77P35ZLCKFANMSKPO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GHFBJ72HW77P35ZLCKFANMSKPO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GHFBJ72HW77P35ZLCKFANMSKPO","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":"b63b5a31c147e5a2b529e55bb375213189d0a18d46593d218e730eb572dc6a51","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T18:01:08Z","title_canon_sha256":"1e264cad5089da870415e3ac2e642d0e8d01ac86decc1e3bf9a5792561cec7c7"},"schema_version":"1.0","source":{"id":"2606.17160","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17160","created_at":"2026-06-19T16:10:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17160v1","created_at":"2026-06-19T16:10:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17160","created_at":"2026-06-19T16:10:04Z"},{"alias_kind":"pith_short_12","alias_value":"GHFBJ72HW77P","created_at":"2026-06-19T16:10:04Z"},{"alias_kind":"pith_short_16","alias_value":"GHFBJ72HW77P35ZL","created_at":"2026-06-19T16:10:04Z"},{"alias_kind":"pith_short_8","alias_value":"GHFBJ72H","created_at":"2026-06-19T16:10:04Z"}],"graph_snapshots":[{"event_id":"sha256:b43cb80fe45281b21df2194772dd0f74741addf78ff1c00eb9e287da97de1c43","target":"graph","created_at":"2026-06-19T16:10:04Z","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/2606.17160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive language-audio pretraining (CLAP) enables zero-shot audio classification, but standard inference classifies each clip in isolation and ignores the structure of the unlabeled test set. We present the first systematic study of TransCLIP-style transductive inference for CLAP: a text-anchored spherical Gaussian-mixture EM that refines zero-shot posteriors using the audio-embedding statistics of the test batch, with no labels, no gradients, and negligible compute (about 15 ms on one CPU core for 2,000 clips). Across ESC-50, UrbanSound8K, and VocalSound, this consistently improves top-1 ","authors_text":"Jingwen Zhou, Mingzhe Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T18:01:08Z","title":"Transductive Zero-Shot Audio Classification with Audio-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17160","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":"sha256:26dbece7e03ebf11b0ff15e34d0db996427392ebd2d59660c07a435c6ad6edac","target":"record","created_at":"2026-06-19T16:10:04Z","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":"b63b5a31c147e5a2b529e55bb375213189d0a18d46593d218e730eb572dc6a51","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T18:01:08Z","title_canon_sha256":"1e264cad5089da870415e3ac2e642d0e8d01ac86decc1e3bf9a5792561cec7c7"},"schema_version":"1.0","source":{"id":"2606.17160","kind":"arxiv","version":1}},"canonical_sha256":"31ca14ff47b7fefdf72b128a06b24a7b9e0fd06dd47e3f6b2b371f55c8792588","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31ca14ff47b7fefdf72b128a06b24a7b9e0fd06dd47e3f6b2b371f55c8792588","first_computed_at":"2026-06-19T16:10:04.707611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:04.707611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DzCg5iHMiQH3Kx3DQyoDfp8uugZnmF9xQT6zPV4GRlTdgQz2ErvOTYNlCUFYRVltwsuN+KlvY1mR5+W37DrKDQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:04.707948Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17160","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26dbece7e03ebf11b0ff15e34d0db996427392ebd2d59660c07a435c6ad6edac","sha256:b43cb80fe45281b21df2194772dd0f74741addf78ff1c00eb9e287da97de1c43"],"state_sha256":"b63474bc85bb81f5283becabd8270cc4a7f33b6b87bcff94c9adf3db01c8e946"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/9HSwMUj6mU1zjnKWRKaVtAW80ulxpCfMX7MKm9OgCLLQciSZgH01sHnLfkMhoI7dGQBMyTD6NGOnfoj/MtVDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T21:54:48.156749Z","bundle_sha256":"4fe6b54134158125daa73371fd68d6d9c84ab962578179e7429a8d1352af745c"}}