{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UBETZXRPC3CBL2RVHP7YAJLNY3","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":"b3a02495bdc3f8ef4ca63a4d31e5b5d3c4a0ef3b3daa301a08d520f47a6fcc60","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-06T02:58:47Z","title_canon_sha256":"87f6561ed3d35d5dff86f059610ce56a79c9dad8d6252135779fb9c390e79768"},"schema_version":"1.0","source":{"id":"2607.04619","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04619","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04619v1","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04619","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"UBETZXRPC3CB","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"UBETZXRPC3CBL2RV","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"UBETZXRP","created_at":"2026-07-07T02:19:27Z"}],"graph_snapshots":[{"event_id":"sha256:c7d322adafa59d7c98d9cc968b8df634b14f115285b9fd94bdf6a152581175d5","target":"graph","created_at":"2026-07-07T02:19:27Z","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/2607.04619/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern automated audio captioning systems pair a frozen audio encoder with a large language model (LLM) via a trainable projector, incurring the encoder's inference cost and bottlenecking the model through its fixed acoustic features. We present CARD, an encoder-free audio captioning model that removes the encoder at inference: a 13.2M projector feeds a frozen LLM with merged LoRA adapters, while the teacher used to train it is discarded. CARD distills a pretrained audio teacher (CLAP-HTSAT) into the model, but rather than injecting it into the LLM alone, it routes the teacher's representation","authors_text":"Ganesh Pavan Kartikeya Bharadwaj Kolluri, Michael Kampouridis, Ravi Shekhar, Yuchen Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-06T02:58:47Z","title":"CARD: Cross-component Audio Representation Distillation for Encoder-Free Audio Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04619","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":"sha256:73cc199615481530568fefda1902ce48cf95a0557884ebb02bc3c67c771bf9e9","target":"record","created_at":"2026-07-07T02:19:27Z","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":"b3a02495bdc3f8ef4ca63a4d31e5b5d3c4a0ef3b3daa301a08d520f47a6fcc60","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-06T02:58:47Z","title_canon_sha256":"87f6561ed3d35d5dff86f059610ce56a79c9dad8d6252135779fb9c390e79768"},"schema_version":"1.0","source":{"id":"2607.04619","kind":"arxiv","version":1}},"canonical_sha256":"a0493cde2f16c415ea353bff80256dc6d9ee5221d4e9475882268b61c65fb0ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0493cde2f16c415ea353bff80256dc6d9ee5221d4e9475882268b61c65fb0ba","first_computed_at":"2026-07-07T02:19:27.813696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:27.813696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ND9e4fFfHDpZONFm7tGMSeELJPmJbeCtIrNmdsgooY+WKmiizl7A2Tz42pBdnhAy0QQm9RVRZNVIKs6Q2OncDQ==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:27.814411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04619","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73cc199615481530568fefda1902ce48cf95a0557884ebb02bc3c67c771bf9e9","sha256:c7d322adafa59d7c98d9cc968b8df634b14f115285b9fd94bdf6a152581175d5"],"state_sha256":"415f88a12b2ab0e96389fd4d3c867ef4fe2b037880cb3130fd6ca95173d8d9b7"}