{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:V33TZU25JQRQZ4225OE67AMTTU","short_pith_number":"pith:V33TZU25","canonical_record":{"source":{"id":"2606.23052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-22T09:03:45Z","cross_cats_sorted":[],"title_canon_sha256":"a94c680b6753e087b686b46a42ae9e53b83d1eb6946c06b0e2132c6065d30a95","abstract_canon_sha256":"49de5381c9688e16542a8e1274979a13c7a90148268d2261ae1e9c65edbd7c60"},"schema_version":"1.0"},"canonical_sha256":"aef73cd35d4c230cf35aeb89ef81939d1356c62b13477fe81d90d3f0e53a26a2","source":{"kind":"arxiv","id":"2606.23052","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23052","created_at":"2026-06-23T03:14:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23052v1","created_at":"2026-06-23T03:14:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23052","created_at":"2026-06-23T03:14:08Z"},{"alias_kind":"pith_short_12","alias_value":"V33TZU25JQRQ","created_at":"2026-06-23T03:14:08Z"},{"alias_kind":"pith_short_16","alias_value":"V33TZU25JQRQZ422","created_at":"2026-06-23T03:14:08Z"},{"alias_kind":"pith_short_8","alias_value":"V33TZU25","created_at":"2026-06-23T03:14:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:V33TZU25JQRQZ4225OE67AMTTU","target":"record","payload":{"canonical_record":{"source":{"id":"2606.23052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-22T09:03:45Z","cross_cats_sorted":[],"title_canon_sha256":"a94c680b6753e087b686b46a42ae9e53b83d1eb6946c06b0e2132c6065d30a95","abstract_canon_sha256":"49de5381c9688e16542a8e1274979a13c7a90148268d2261ae1e9c65edbd7c60"},"schema_version":"1.0"},"canonical_sha256":"aef73cd35d4c230cf35aeb89ef81939d1356c62b13477fe81d90d3f0e53a26a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:08.324915Z","signature_b64":"4/A80FC2U7LD42xjNOGsQnyMh2Gbyz01Fj72xNFR+MKWPPdJK2TmLu2kZyJo4pjVYZRmNkCgySLyKOazCCXsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aef73cd35d4c230cf35aeb89ef81939d1356c62b13477fe81d90d3f0e53a26a2","last_reissued_at":"2026-06-23T03:14:08.324506Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:08.324506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.23052","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":"2026-06-23T03:14:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iZu24yPiFr2dbqXCA88HdzfAvqfIgDKc/PbbLwKNowqMORdC/1QiYpHB2XeBsh7Yt8sdv2YMkcQb30sgEW5DAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T07:22:46.059199Z"},"content_sha256":"4eebbd9c4098a42310e26dafc635aed76a671dd24bd134ff6ad6789e2c42c962","schema_version":"1.0","event_id":"sha256:4eebbd9c4098a42310e26dafc635aed76a671dd24bd134ff6ad6789e2c42c962"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:V33TZU25JQRQZ4225OE67AMTTU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CAAD: Contrastive Audio-Aware Distillation for Efficient Speech Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chun-Wei Chen, Hung-yi Lee, Ke-Han Lu, Tzu-Quan Lin, Wei-Ping Huang","submitted_at":"2026-06-22T09:03:45Z","abstract_excerpt":"Speech Language Models achieve reasoning capabilities, but are often hindered by massive parameter counts and a tendency to prioritize linguistic priors over acoustic features. While contrastive decoding enhances grounding by contrasting audio-aware and text-only logits, it increases inference latency. We propose Contrastive Audio-Aware Distillation (CAAD), a framework that internalizes the teacher's contrastive reasoning into the student model's weights. To overcome the high computational training overhead in the dual-path token-by-token contrastive distillation process, we introduce a synchr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23052","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/2606.23052/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":"2026-06-23T03:14:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"113OIwc1Urt8WTWgy1badux9Far4dcmUIuLRjjJ1ihDkVW2G1u+4OR3JdPsfDdht610qFRKVEbsUsCsa7CgvDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T07:22:46.059581Z"},"content_sha256":"8ca175f1f3cf97cc644680ae8c1a5ba8a70af64ff8be9d5fc39f525d2e7e3de8","schema_version":"1.0","event_id":"sha256:8ca175f1f3cf97cc644680ae8c1a5ba8a70af64ff8be9d5fc39f525d2e7e3de8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V33TZU25JQRQZ4225OE67AMTTU/bundle.json","state_url":"https://pith.science/pith/V33TZU25JQRQZ4225OE67AMTTU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V33TZU25JQRQZ4225OE67AMTTU/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":"2026-07-05T07:22:46Z","links":{"resolver":"https://pith.science/pith/V33TZU25JQRQZ4225OE67AMTTU","bundle":"https://pith.science/pith/V33TZU25JQRQZ4225OE67AMTTU/bundle.json","state":"https://pith.science/pith/V33TZU25JQRQZ4225OE67AMTTU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V33TZU25JQRQZ4225OE67AMTTU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V33TZU25JQRQZ4225OE67AMTTU","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":"49de5381c9688e16542a8e1274979a13c7a90148268d2261ae1e9c65edbd7c60","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-22T09:03:45Z","title_canon_sha256":"a94c680b6753e087b686b46a42ae9e53b83d1eb6946c06b0e2132c6065d30a95"},"schema_version":"1.0","source":{"id":"2606.23052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23052","created_at":"2026-06-23T03:14:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23052v1","created_at":"2026-06-23T03:14:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23052","created_at":"2026-06-23T03:14:08Z"},{"alias_kind":"pith_short_12","alias_value":"V33TZU25JQRQ","created_at":"2026-06-23T03:14:08Z"},{"alias_kind":"pith_short_16","alias_value":"V33TZU25JQRQZ422","created_at":"2026-06-23T03:14:08Z"},{"alias_kind":"pith_short_8","alias_value":"V33TZU25","created_at":"2026-06-23T03:14:08Z"}],"graph_snapshots":[{"event_id":"sha256:8ca175f1f3cf97cc644680ae8c1a5ba8a70af64ff8be9d5fc39f525d2e7e3de8","target":"graph","created_at":"2026-06-23T03:14:08Z","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/2606.23052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech Language Models achieve reasoning capabilities, but are often hindered by massive parameter counts and a tendency to prioritize linguistic priors over acoustic features. While contrastive decoding enhances grounding by contrasting audio-aware and text-only logits, it increases inference latency. We propose Contrastive Audio-Aware Distillation (CAAD), a framework that internalizes the teacher's contrastive reasoning into the student model's weights. To overcome the high computational training overhead in the dual-path token-by-token contrastive distillation process, we introduce a synchr","authors_text":"Chun-Wei Chen, Hung-yi Lee, Ke-Han Lu, Tzu-Quan Lin, Wei-Ping Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-22T09:03:45Z","title":"CAAD: Contrastive Audio-Aware Distillation for Efficient Speech Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23052","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":"sha256:4eebbd9c4098a42310e26dafc635aed76a671dd24bd134ff6ad6789e2c42c962","target":"record","created_at":"2026-06-23T03:14:08Z","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":"49de5381c9688e16542a8e1274979a13c7a90148268d2261ae1e9c65edbd7c60","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-22T09:03:45Z","title_canon_sha256":"a94c680b6753e087b686b46a42ae9e53b83d1eb6946c06b0e2132c6065d30a95"},"schema_version":"1.0","source":{"id":"2606.23052","kind":"arxiv","version":1}},"canonical_sha256":"aef73cd35d4c230cf35aeb89ef81939d1356c62b13477fe81d90d3f0e53a26a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aef73cd35d4c230cf35aeb89ef81939d1356c62b13477fe81d90d3f0e53a26a2","first_computed_at":"2026-06-23T03:14:08.324506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:08.324506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4/A80FC2U7LD42xjNOGsQnyMh2Gbyz01Fj72xNFR+MKWPPdJK2TmLu2kZyJo4pjVYZRmNkCgySLyKOazCCXsBQ==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:08.324915Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4eebbd9c4098a42310e26dafc635aed76a671dd24bd134ff6ad6789e2c42c962","sha256:8ca175f1f3cf97cc644680ae8c1a5ba8a70af64ff8be9d5fc39f525d2e7e3de8"],"state_sha256":"b61e8a7546763805ff5fdc41f66bb9b94c54f30ffa7e0900bff2e118f5d63d4b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+hvZ7veZym+eVjQXdar7W9zO+T4m+3GqavgmQ/QSrHmm2R8t5XW3xg1pMWjEA5OZ8LHeYnTMPKC30ccamMunCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T07:22:46.062710Z","bundle_sha256":"fdbce7b4c55f9024ea2dc66ceff38b8f9c1b6d8372205f4569011d6294cfb93d"}}