{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F337O7KYNJYEFAJJSSJUPOG7KN","short_pith_number":"pith:F337O7KY","canonical_record":{"source":{"id":"2410.00168","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T19:17:46Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"df58092098e269f57bcdcd51b45d6c3a8537638378e78ad104ad6431b447feeb","abstract_canon_sha256":"024b535e61aed8fec2f2c1cba691c20d567ca703a6f27d14e56c3ed657745574"},"schema_version":"1.0"},"canonical_sha256":"2ef7f77d586a70428129949347b8df535e8bdb8b419f9e0922fb68c63a0a2923","source":{"kind":"arxiv","id":"2410.00168","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00168","created_at":"2026-07-05T11:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00168v2","created_at":"2026-07-05T11:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00168","created_at":"2026-07-05T11:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"F337O7KYNJYE","created_at":"2026-07-05T11:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"F337O7KYNJYEFAJJ","created_at":"2026-07-05T11:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"F337O7KY","created_at":"2026-07-05T11:04:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F337O7KYNJYEFAJJSSJUPOG7KN","target":"record","payload":{"canonical_record":{"source":{"id":"2410.00168","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T19:17:46Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"df58092098e269f57bcdcd51b45d6c3a8537638378e78ad104ad6431b447feeb","abstract_canon_sha256":"024b535e61aed8fec2f2c1cba691c20d567ca703a6f27d14e56c3ed657745574"},"schema_version":"1.0"},"canonical_sha256":"2ef7f77d586a70428129949347b8df535e8bdb8b419f9e0922fb68c63a0a2923","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:40.154811Z","signature_b64":"HbYmSv7Z8K7dGzfb4YaD5fFDfBL+mkRX30bYJEb+24uyyzSxyi/rr8Jy4vOvYkY5bSwSjq2Zvv0nuVYKWS7/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ef7f77d586a70428129949347b8df535e8bdb8b419f9e0922fb68c63a0a2923","last_reissued_at":"2026-07-05T11:04:40.154306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:40.154306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.00168","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":"2026-07-05T11:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gJAsJucYxzwMxR563XfOhxHOiOss+vCH22mKzPTZy2Tji1xX2u7SqgLvimbKzriVp+iS0PFrdpPgqKAH1V9YAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:34:00.455801Z"},"content_sha256":"6db6abe25c0a4a9c4aa23a2ba71edfd627e2333c355d29d9d14818254b24163e","schema_version":"1.0","event_id":"sha256:6db6abe25c0a4a9c4aa23a2ba71edfd627e2333c355d29d9d14818254b24163e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F337O7KYNJYEFAJJSSJUPOG7KN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SSR: Alignment-Aware Modality Connector for Speech Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hirofumi Inaguma, Ning Dong, Paden Tomasello, Weiting Tan, Xutai Ma","submitted_at":"2024-09-30T19:17:46Z","abstract_excerpt":"Fusing speech into pre-trained language model (SpeechLM) usually suffers from inefficient encoding of long-form speech and catastrophic forgetting of pre-trained text modality. We propose SSR-Connector (Segmented Speech Representation Connector) for better modality fusion. Leveraging speech-text alignments, our approach segments and compresses speech features to match the granularity of text embeddings. Additionally, we introduce a two-stage training pipeline that includes the distillation and fine-tuning phases to mitigate catastrophic forgetting. SSR-Connector outperforms existing mechanism "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00168","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/2410.00168/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":"2026-07-05T11:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jtK2q8IzM6llbNwewMi5AyoWCiFRTWy2U62Jkx7M1XjiPie1f3NslldPjhJa+gSN6AflpVzOSHoMjy10V4JIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:34:00.456371Z"},"content_sha256":"9b452bf6e23f7ba4efba1929d9063c9297a29885d7efd43e90595fa248dcc737","schema_version":"1.0","event_id":"sha256:9b452bf6e23f7ba4efba1929d9063c9297a29885d7efd43e90595fa248dcc737"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F337O7KYNJYEFAJJSSJUPOG7KN/bundle.json","state_url":"https://pith.science/pith/F337O7KYNJYEFAJJSSJUPOG7KN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F337O7KYNJYEFAJJSSJUPOG7KN/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":"2026-08-08T08:34:00Z","links":{"resolver":"https://pith.science/pith/F337O7KYNJYEFAJJSSJUPOG7KN","bundle":"https://pith.science/pith/F337O7KYNJYEFAJJSSJUPOG7KN/bundle.json","state":"https://pith.science/pith/F337O7KYNJYEFAJJSSJUPOG7KN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F337O7KYNJYEFAJJSSJUPOG7KN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F337O7KYNJYEFAJJSSJUPOG7KN","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":"024b535e61aed8fec2f2c1cba691c20d567ca703a6f27d14e56c3ed657745574","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T19:17:46Z","title_canon_sha256":"df58092098e269f57bcdcd51b45d6c3a8537638378e78ad104ad6431b447feeb"},"schema_version":"1.0","source":{"id":"2410.00168","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00168","created_at":"2026-07-05T11:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00168v2","created_at":"2026-07-05T11:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00168","created_at":"2026-07-05T11:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"F337O7KYNJYE","created_at":"2026-07-05T11:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"F337O7KYNJYEFAJJ","created_at":"2026-07-05T11:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"F337O7KY","created_at":"2026-07-05T11:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:9b452bf6e23f7ba4efba1929d9063c9297a29885d7efd43e90595fa248dcc737","target":"graph","created_at":"2026-07-05T11:04:40Z","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/2410.00168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fusing speech into pre-trained language model (SpeechLM) usually suffers from inefficient encoding of long-form speech and catastrophic forgetting of pre-trained text modality. We propose SSR-Connector (Segmented Speech Representation Connector) for better modality fusion. Leveraging speech-text alignments, our approach segments and compresses speech features to match the granularity of text embeddings. Additionally, we introduce a two-stage training pipeline that includes the distillation and fine-tuning phases to mitigate catastrophic forgetting. SSR-Connector outperforms existing mechanism ","authors_text":"Hirofumi Inaguma, Ning Dong, Paden Tomasello, Weiting Tan, Xutai Ma","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T19:17:46Z","title":"SSR: Alignment-Aware Modality Connector for Speech Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00168","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":"sha256:6db6abe25c0a4a9c4aa23a2ba71edfd627e2333c355d29d9d14818254b24163e","target":"record","created_at":"2026-07-05T11:04:40Z","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":"024b535e61aed8fec2f2c1cba691c20d567ca703a6f27d14e56c3ed657745574","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T19:17:46Z","title_canon_sha256":"df58092098e269f57bcdcd51b45d6c3a8537638378e78ad104ad6431b447feeb"},"schema_version":"1.0","source":{"id":"2410.00168","kind":"arxiv","version":2}},"canonical_sha256":"2ef7f77d586a70428129949347b8df535e8bdb8b419f9e0922fb68c63a0a2923","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ef7f77d586a70428129949347b8df535e8bdb8b419f9e0922fb68c63a0a2923","first_computed_at":"2026-07-05T11:04:40.154306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:40.154306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HbYmSv7Z8K7dGzfb4YaD5fFDfBL+mkRX30bYJEb+24uyyzSxyi/rr8Jy4vOvYkY5bSwSjq2Zvv0nuVYKWS7/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:40.154811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.00168","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6db6abe25c0a4a9c4aa23a2ba71edfd627e2333c355d29d9d14818254b24163e","sha256:9b452bf6e23f7ba4efba1929d9063c9297a29885d7efd43e90595fa248dcc737"],"state_sha256":"d24754ff4cc2d3f408ad227afd3195c3528103baaab7fbab2ba1792ba97cb192"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SteribSj4C0OEt6gi8vyV+5bAVk3m6yOAq56l+x11rL/puisNZvaNPtc2zREmVvySfLnv5OaM1baALT2UFV5Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:34:00.462251Z","bundle_sha256":"dec485948dd143a6be05e55ed782725a0ca147b61bc45dfb1488a863a2b3c1cc"}}