{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WLTMAQLVM6GKFXG3J2CKRES6XO","short_pith_number":"pith:WLTMAQLV","canonical_record":{"source":{"id":"2605.27039","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-26T13:56:33Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"edc65622d9f3789f21065b7ceb869e093bbd3ac207123ad0da49efcaff24b3b5","abstract_canon_sha256":"880a70a9b5b6111233c7e448fe1877016f38ee18db94c2662d2895a7d4286417"},"schema_version":"1.0"},"canonical_sha256":"b2e6c04175678ca2dcdb4e84a8925ebbbbef276179363d75aa4fe8355ea93c50","source":{"kind":"arxiv","id":"2605.27039","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27039","created_at":"2026-05-27T01:06:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27039v1","created_at":"2026-05-27T01:06:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27039","created_at":"2026-05-27T01:06:25Z"},{"alias_kind":"pith_short_12","alias_value":"WLTMAQLVM6GK","created_at":"2026-05-27T01:06:25Z"},{"alias_kind":"pith_short_16","alias_value":"WLTMAQLVM6GKFXG3","created_at":"2026-05-27T01:06:25Z"},{"alias_kind":"pith_short_8","alias_value":"WLTMAQLV","created_at":"2026-05-27T01:06:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WLTMAQLVM6GKFXG3J2CKRES6XO","target":"record","payload":{"canonical_record":{"source":{"id":"2605.27039","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-26T13:56:33Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"edc65622d9f3789f21065b7ceb869e093bbd3ac207123ad0da49efcaff24b3b5","abstract_canon_sha256":"880a70a9b5b6111233c7e448fe1877016f38ee18db94c2662d2895a7d4286417"},"schema_version":"1.0"},"canonical_sha256":"b2e6c04175678ca2dcdb4e84a8925ebbbbef276179363d75aa4fe8355ea93c50","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:25.347939Z","signature_b64":"X/FSX++O5JJ875Q/b7zdVNme4UEaEANI71vlaaUo/KzCuvhOl4TQ4arG89stJ5VfsML01MFNwVcDqp8Gs6KiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2e6c04175678ca2dcdb4e84a8925ebbbbef276179363d75aa4fe8355ea93c50","last_reissued_at":"2026-05-27T01:06:25.347159Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:25.347159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.27039","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":"2026-05-27T01:06:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wmf3ahd26AW+L8/Rw/ueQNsKFfI7v4QvYMXyTH4vi80AFxe4Lh6cU/N/ornuygSySmxnSQRtcsGDCjajdMW1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:47:55.314766Z"},"content_sha256":"d7b3bce4357fcddc7f1ab47f997a8cd10b181d9c28974cd6fd1f5ad7058efa80","schema_version":"1.0","event_id":"sha256:d7b3bce4357fcddc7f1ab47f997a8cd10b181d9c28974cd6fd1f5ad7058efa80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WLTMAQLVM6GKFXG3J2CKRES6XO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Can't They Remember? Uncovering Representation and Retrieval Bottlenecks in Multi-Turn Acoustic Memory","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Eun-Jung Holden, Han Yin, Hong Jia, Siyi Wang, Ting Dang, Vidhyasaharan Sethu, Yang Xiao","submitted_at":"2026-05-26T13:56:33Z","abstract_excerpt":"Large audio language models (LALMs) process both speech and environmental acoustic cues, yet struggle to retain non-speech information across multi-turn interactions. The performance gap between semantic (speech) and acoustic (non-speech) understanding remains poorly understood, and the underlying mechanisms of representation and retrieval are still unclear. This work introduces EnvMem, a controlled multi-turn benchmark designed to study this gap and identify the root causes of failures at the representation (i.e., latent embeddings) and retrieval levels (i.e., attention allocation). We furthe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27039","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/2605.27039/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":"2026-05-27T01:06:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fZyl2Gm5lBBLc1/sOCLGP0FmtD+lBRRLA5okZ3L3TvREhou1kMQHSHZVO+s6m9Ty/174sarBbbvXwIhXw6K7Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:47:55.315469Z"},"content_sha256":"179aeef95efeb2a88f2cf07ff30e343be195489be36a67897b1a311abed65b1e","schema_version":"1.0","event_id":"sha256:179aeef95efeb2a88f2cf07ff30e343be195489be36a67897b1a311abed65b1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WLTMAQLVM6GKFXG3J2CKRES6XO/bundle.json","state_url":"https://pith.science/pith/WLTMAQLVM6GKFXG3J2CKRES6XO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WLTMAQLVM6GKFXG3J2CKRES6XO/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":"2026-05-31T06:47:55Z","links":{"resolver":"https://pith.science/pith/WLTMAQLVM6GKFXG3J2CKRES6XO","bundle":"https://pith.science/pith/WLTMAQLVM6GKFXG3J2CKRES6XO/bundle.json","state":"https://pith.science/pith/WLTMAQLVM6GKFXG3J2CKRES6XO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WLTMAQLVM6GKFXG3J2CKRES6XO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WLTMAQLVM6GKFXG3J2CKRES6XO","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":"880a70a9b5b6111233c7e448fe1877016f38ee18db94c2662d2895a7d4286417","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-26T13:56:33Z","title_canon_sha256":"edc65622d9f3789f21065b7ceb869e093bbd3ac207123ad0da49efcaff24b3b5"},"schema_version":"1.0","source":{"id":"2605.27039","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27039","created_at":"2026-05-27T01:06:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27039v1","created_at":"2026-05-27T01:06:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27039","created_at":"2026-05-27T01:06:25Z"},{"alias_kind":"pith_short_12","alias_value":"WLTMAQLVM6GK","created_at":"2026-05-27T01:06:25Z"},{"alias_kind":"pith_short_16","alias_value":"WLTMAQLVM6GKFXG3","created_at":"2026-05-27T01:06:25Z"},{"alias_kind":"pith_short_8","alias_value":"WLTMAQLV","created_at":"2026-05-27T01:06:25Z"}],"graph_snapshots":[{"event_id":"sha256:179aeef95efeb2a88f2cf07ff30e343be195489be36a67897b1a311abed65b1e","target":"graph","created_at":"2026-05-27T01:06:25Z","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/2605.27039/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large audio language models (LALMs) process both speech and environmental acoustic cues, yet struggle to retain non-speech information across multi-turn interactions. The performance gap between semantic (speech) and acoustic (non-speech) understanding remains poorly understood, and the underlying mechanisms of representation and retrieval are still unclear. This work introduces EnvMem, a controlled multi-turn benchmark designed to study this gap and identify the root causes of failures at the representation (i.e., latent embeddings) and retrieval levels (i.e., attention allocation). We furthe","authors_text":"Eun-Jung Holden, Han Yin, Hong Jia, Siyi Wang, Ting Dang, Vidhyasaharan Sethu, Yang Xiao","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-26T13:56:33Z","title":"Why Can't They Remember? Uncovering Representation and Retrieval Bottlenecks in Multi-Turn Acoustic Memory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27039","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:d7b3bce4357fcddc7f1ab47f997a8cd10b181d9c28974cd6fd1f5ad7058efa80","target":"record","created_at":"2026-05-27T01:06:25Z","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":"880a70a9b5b6111233c7e448fe1877016f38ee18db94c2662d2895a7d4286417","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-26T13:56:33Z","title_canon_sha256":"edc65622d9f3789f21065b7ceb869e093bbd3ac207123ad0da49efcaff24b3b5"},"schema_version":"1.0","source":{"id":"2605.27039","kind":"arxiv","version":1}},"canonical_sha256":"b2e6c04175678ca2dcdb4e84a8925ebbbbef276179363d75aa4fe8355ea93c50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2e6c04175678ca2dcdb4e84a8925ebbbbef276179363d75aa4fe8355ea93c50","first_computed_at":"2026-05-27T01:06:25.347159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:06:25.347159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X/FSX++O5JJ875Q/b7zdVNme4UEaEANI71vlaaUo/KzCuvhOl4TQ4arG89stJ5VfsML01MFNwVcDqp8Gs6KiDA==","signature_status":"signed_v1","signed_at":"2026-05-27T01:06:25.347939Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27039","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7b3bce4357fcddc7f1ab47f997a8cd10b181d9c28974cd6fd1f5ad7058efa80","sha256:179aeef95efeb2a88f2cf07ff30e343be195489be36a67897b1a311abed65b1e"],"state_sha256":"483883ec2253c493f7fc3eeadea3a6bab78c8409f530c4d1c968fa2ebe7cc9f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+H53ypdqdefBXO5y7FOv5kMy2SHyQhqDAkQA7sdyPfKysEX7gqJOfe54pVGrWQ95K3TS2wWo6VUpuNE34d8FDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T06:47:55.322366Z","bundle_sha256":"65f3c277c4de944922606680189f36c9cda43b33eeee75af84a233e9380863c1"}}