{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YNS7NYDDBADJ4XURHBQZTZH2CC","short_pith_number":"pith:YNS7NYDD","canonical_record":{"source":{"id":"2503.02769","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-03-04T16:34:14Z","cross_cats_sorted":["cs.CL","cs.HC","eess.AS"],"title_canon_sha256":"d6799b3ad990b82f17475654aadba728a3f0288fa6e9c0e2d0dc4f173bd21c71","abstract_canon_sha256":"d5029335d16e5e0b508ca907bb49cd2c5a2f80656fd77225c97081b5d4499595"},"schema_version":"1.0"},"canonical_sha256":"c365f6e06308069e5e91386199e4fa10b13e5c8a585d04411f07bb900dc3b930","source":{"kind":"arxiv","id":"2503.02769","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02769","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02769v2","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02769","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"YNS7NYDDBADJ","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"pith_short_16","alias_value":"YNS7NYDDBADJ4XUR","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"pith_short_8","alias_value":"YNS7NYDD","created_at":"2026-07-05T11:15:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YNS7NYDDBADJ4XURHBQZTZH2CC","target":"record","payload":{"canonical_record":{"source":{"id":"2503.02769","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-03-04T16:34:14Z","cross_cats_sorted":["cs.CL","cs.HC","eess.AS"],"title_canon_sha256":"d6799b3ad990b82f17475654aadba728a3f0288fa6e9c0e2d0dc4f173bd21c71","abstract_canon_sha256":"d5029335d16e5e0b508ca907bb49cd2c5a2f80656fd77225c97081b5d4499595"},"schema_version":"1.0"},"canonical_sha256":"c365f6e06308069e5e91386199e4fa10b13e5c8a585d04411f07bb900dc3b930","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:43.777818Z","signature_b64":"W60T7YQ2MVAvl0O0LqTtQWCbqt600bk8MefGuR05/3UPQphPvzq7owAjq8344Q6z5qeODIbnbzeMn9/JPwdvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c365f6e06308069e5e91386199e4fa10b13e5c8a585d04411f07bb900dc3b930","last_reissued_at":"2026-07-05T11:15:43.777258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:43.777258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.02769","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E4DSnI9ds16WAqjQVJ5sFsXcwGYZ8YRUpBUCNVFbTRYnNw75fniJYqzyItm7My4QCgrENEDZTPJ4I0k0iCUgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:10:05.410708Z"},"content_sha256":"127775113b742d2ee713fb51f1fde5467d2c5db5001a9f600b0328951c0aae74","schema_version":"1.0","event_id":"sha256:127775113b742d2ee713fb51f1fde5467d2c5db5001a9f600b0328951c0aae74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YNS7NYDDBADJ4XURHBQZTZH2CC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.HC","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dingdong Wang, Dongchao Yang, Jincenzi Wu, Jin Xu, Junyang Lin, Ruihang Chu, Shengpeng Ji, Xiong Wang, Zhifang Guo","submitted_at":"2025-03-04T16:34:14Z","abstract_excerpt":"Recent advancements in speech large language models (SpeechLLMs) have attracted considerable attention. Nonetheless, current methods exhibit suboptimal performance in adhering to speech instructions. Notably, the intelligence of models significantly diminishes when processing speech-form input as compared to direct text-form input. Prior work has attempted to mitigate this semantic inconsistency between speech and text representations through techniques such as representation and behavior alignment, which involve the meticulous design of data pairs during the post-training phase. In this paper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02769","kind":"arxiv","version":2},"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/2503.02769/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":"2026-07-05T11:15:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7jHkgkwlFnOFRqgPBjq0ODL5O0iDSnCTqDFcad7XYc4Qf5c4sWQbxLw//UQfuItqoentICAt4ILwJusbENGrCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:10:05.411596Z"},"content_sha256":"302d9cb37726cb0344c985ac271a99a1704b50071a77a79ee0f6ff2b9b406df3","schema_version":"1.0","event_id":"sha256:302d9cb37726cb0344c985ac271a99a1704b50071a77a79ee0f6ff2b9b406df3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YNS7NYDDBADJ4XURHBQZTZH2CC/bundle.json","state_url":"https://pith.science/pith/YNS7NYDDBADJ4XURHBQZTZH2CC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YNS7NYDDBADJ4XURHBQZTZH2CC/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":"2026-08-09T22:10:05Z","links":{"resolver":"https://pith.science/pith/YNS7NYDDBADJ4XURHBQZTZH2CC","bundle":"https://pith.science/pith/YNS7NYDDBADJ4XURHBQZTZH2CC/bundle.json","state":"https://pith.science/pith/YNS7NYDDBADJ4XURHBQZTZH2CC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YNS7NYDDBADJ4XURHBQZTZH2CC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YNS7NYDDBADJ4XURHBQZTZH2CC","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":"d5029335d16e5e0b508ca907bb49cd2c5a2f80656fd77225c97081b5d4499595","cross_cats_sorted":["cs.CL","cs.HC","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-03-04T16:34:14Z","title_canon_sha256":"d6799b3ad990b82f17475654aadba728a3f0288fa6e9c0e2d0dc4f173bd21c71"},"schema_version":"1.0","source":{"id":"2503.02769","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02769","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02769v2","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02769","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"YNS7NYDDBADJ","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"pith_short_16","alias_value":"YNS7NYDDBADJ4XUR","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"pith_short_8","alias_value":"YNS7NYDD","created_at":"2026-07-05T11:15:43Z"}],"graph_snapshots":[{"event_id":"sha256:302d9cb37726cb0344c985ac271a99a1704b50071a77a79ee0f6ff2b9b406df3","target":"graph","created_at":"2026-07-05T11:15:43Z","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/2503.02769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in speech large language models (SpeechLLMs) have attracted considerable attention. Nonetheless, current methods exhibit suboptimal performance in adhering to speech instructions. Notably, the intelligence of models significantly diminishes when processing speech-form input as compared to direct text-form input. Prior work has attempted to mitigate this semantic inconsistency between speech and text representations through techniques such as representation and behavior alignment, which involve the meticulous design of data pairs during the post-training phase. In this paper","authors_text":"Dingdong Wang, Dongchao Yang, Jincenzi Wu, Jin Xu, Junyang Lin, Ruihang Chu, Shengpeng Ji, Xiong Wang, Zhifang Guo","cross_cats":["cs.CL","cs.HC","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-03-04T16:34:14Z","title":"InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02769","kind":"arxiv","version":2},"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":"sha256:127775113b742d2ee713fb51f1fde5467d2c5db5001a9f600b0328951c0aae74","target":"record","created_at":"2026-07-05T11:15:43Z","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":"d5029335d16e5e0b508ca907bb49cd2c5a2f80656fd77225c97081b5d4499595","cross_cats_sorted":["cs.CL","cs.HC","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-03-04T16:34:14Z","title_canon_sha256":"d6799b3ad990b82f17475654aadba728a3f0288fa6e9c0e2d0dc4f173bd21c71"},"schema_version":"1.0","source":{"id":"2503.02769","kind":"arxiv","version":2}},"canonical_sha256":"c365f6e06308069e5e91386199e4fa10b13e5c8a585d04411f07bb900dc3b930","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c365f6e06308069e5e91386199e4fa10b13e5c8a585d04411f07bb900dc3b930","first_computed_at":"2026-07-05T11:15:43.777258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:43.777258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W60T7YQ2MVAvl0O0LqTtQWCbqt600bk8MefGuR05/3UPQphPvzq7owAjq8344Q6z5qeODIbnbzeMn9/JPwdvBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:43.777818Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.02769","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:127775113b742d2ee713fb51f1fde5467d2c5db5001a9f600b0328951c0aae74","sha256:302d9cb37726cb0344c985ac271a99a1704b50071a77a79ee0f6ff2b9b406df3"],"state_sha256":"25471a0f057624401d0b0cc9344fea42fe97bbe5647fa34096d6a7c9b46d559d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aSPzuGlGu6FqP6RtarAyUi60GRfr9DRDWZg5SvCIe8QFrB+kEgfRFRJOQ1McYHvLOAk4ZP6UZ2c1OXQq05cwCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:10:05.419117Z","bundle_sha256":"e731cd30afe8cf4ff8be36a1b53d6cc4f04879dfe2a93cbcf60dca06ddd78f18"}}