{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MQYNRGFBW7QCWVJKP6PC4FTFAP","short_pith_number":"pith:MQYNRGFB","canonical_record":{"source":{"id":"2202.03587","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-08T01:20:37Z","cross_cats_sorted":["cs.SD","eess.SP"],"title_canon_sha256":"231040d3b54b0aa62d77e8679d7be7bb9f8d13d5d9709f66b465413446e94952","abstract_canon_sha256":"7959f0f4376a514ffdb334158bea86eecd469aeccde5debbc9368eb33c2f5f9e"},"schema_version":"1.0"},"canonical_sha256":"6430d898a1b7e02b552a7f9e2e166503c29f96d51bcbe7d8292a766e647846bd","source":{"kind":"arxiv","id":"2202.03587","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.03587","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"arxiv_version","alias_value":"2202.03587v1","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03587","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"pith_short_12","alias_value":"MQYNRGFBW7QC","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"pith_short_16","alias_value":"MQYNRGFBW7QCWVJK","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"pith_short_8","alias_value":"MQYNRGFB","created_at":"2026-07-05T03:54:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MQYNRGFBW7QCWVJKP6PC4FTFAP","target":"record","payload":{"canonical_record":{"source":{"id":"2202.03587","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-08T01:20:37Z","cross_cats_sorted":["cs.SD","eess.SP"],"title_canon_sha256":"231040d3b54b0aa62d77e8679d7be7bb9f8d13d5d9709f66b465413446e94952","abstract_canon_sha256":"7959f0f4376a514ffdb334158bea86eecd469aeccde5debbc9368eb33c2f5f9e"},"schema_version":"1.0"},"canonical_sha256":"6430d898a1b7e02b552a7f9e2e166503c29f96d51bcbe7d8292a766e647846bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:45.751536Z","signature_b64":"nDo2sNIDSahdBlGVqEjabm21dfyoKouM57ef0s2lQWJIDWgQlOdjb3llFTrOZUBDnu+xUPVPDAnHzc/w0KkxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6430d898a1b7e02b552a7f9e2e166503c29f96d51bcbe7d8292a766e647846bd","last_reissued_at":"2026-07-05T03:54:45.751181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:45.751181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.03587","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":"2026-07-05T03:54:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NPnnwG2n6q2KcdKJ1A0N7Ot7+p5tvabqlfecllXYee0holLwsHDwAnLieamSHh1Hbh0NNKKCmsy1RTcB+SlqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:19:35.815243Z"},"content_sha256":"00fc65b0db483845e63f4ca2e7178f83973fa8bd282206dde83076ed3022120d","schema_version":"1.0","event_id":"sha256:00fc65b0db483845e63f4ca2e7178f83973fa8bd282206dde83076ed3022120d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MQYNRGFBW7QCWVJKP6PC4FTFAP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CALM: Contrastive Aligned Audio-Language Multirate and Multimodal Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Erik Marchi, Panayiotis Georgiou, Sachin Kajarekar, Shao-Yen Tseng, Vin Sachidananda","submitted_at":"2022-02-08T01:20:37Z","abstract_excerpt":"Deriving multimodal representations of audio and lexical inputs is a central problem in Natural Language Understanding (NLU). In this paper, we present Contrastive Aligned Audio-Language Multirate and Multimodal Representations (CALM), an approach for learning multimodal representations using contrastive and multirate information inherent in audio and lexical inputs. The proposed model aligns acoustic and lexical information in the input embedding space of a pretrained language-only contextual embedding model. By aligning audio representations to pretrained language representations and utilizi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03587","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/2202.03587/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":"2026-07-05T03:54:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ied2z9l9J+HboV8RMUf6ol1WrwlyCDQkNFqucXJgTT8pq+tD8mX6D4kGKLy0gIRcyqZNJ2BgyVRAoL46t2PCDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:19:35.815824Z"},"content_sha256":"53636d2dfedd24142c4b836bcdfbb5697ff38ed7377be703937c98a7568397ba","schema_version":"1.0","event_id":"sha256:53636d2dfedd24142c4b836bcdfbb5697ff38ed7377be703937c98a7568397ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MQYNRGFBW7QCWVJKP6PC4FTFAP/bundle.json","state_url":"https://pith.science/pith/MQYNRGFBW7QCWVJKP6PC4FTFAP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MQYNRGFBW7QCWVJKP6PC4FTFAP/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":"2026-08-12T22:19:35Z","links":{"resolver":"https://pith.science/pith/MQYNRGFBW7QCWVJKP6PC4FTFAP","bundle":"https://pith.science/pith/MQYNRGFBW7QCWVJKP6PC4FTFAP/bundle.json","state":"https://pith.science/pith/MQYNRGFBW7QCWVJKP6PC4FTFAP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MQYNRGFBW7QCWVJKP6PC4FTFAP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MQYNRGFBW7QCWVJKP6PC4FTFAP","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":"7959f0f4376a514ffdb334158bea86eecd469aeccde5debbc9368eb33c2f5f9e","cross_cats_sorted":["cs.SD","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-08T01:20:37Z","title_canon_sha256":"231040d3b54b0aa62d77e8679d7be7bb9f8d13d5d9709f66b465413446e94952"},"schema_version":"1.0","source":{"id":"2202.03587","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.03587","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"arxiv_version","alias_value":"2202.03587v1","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03587","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"pith_short_12","alias_value":"MQYNRGFBW7QC","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"pith_short_16","alias_value":"MQYNRGFBW7QCWVJK","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"pith_short_8","alias_value":"MQYNRGFB","created_at":"2026-07-05T03:54:45Z"}],"graph_snapshots":[{"event_id":"sha256:53636d2dfedd24142c4b836bcdfbb5697ff38ed7377be703937c98a7568397ba","target":"graph","created_at":"2026-07-05T03:54:45Z","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/2202.03587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deriving multimodal representations of audio and lexical inputs is a central problem in Natural Language Understanding (NLU). In this paper, we present Contrastive Aligned Audio-Language Multirate and Multimodal Representations (CALM), an approach for learning multimodal representations using contrastive and multirate information inherent in audio and lexical inputs. The proposed model aligns acoustic and lexical information in the input embedding space of a pretrained language-only contextual embedding model. By aligning audio representations to pretrained language representations and utilizi","authors_text":"Erik Marchi, Panayiotis Georgiou, Sachin Kajarekar, Shao-Yen Tseng, Vin Sachidananda","cross_cats":["cs.SD","eess.SP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-08T01:20:37Z","title":"CALM: Contrastive Aligned Audio-Language Multirate and Multimodal Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03587","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":"sha256:00fc65b0db483845e63f4ca2e7178f83973fa8bd282206dde83076ed3022120d","target":"record","created_at":"2026-07-05T03:54:45Z","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":"7959f0f4376a514ffdb334158bea86eecd469aeccde5debbc9368eb33c2f5f9e","cross_cats_sorted":["cs.SD","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-08T01:20:37Z","title_canon_sha256":"231040d3b54b0aa62d77e8679d7be7bb9f8d13d5d9709f66b465413446e94952"},"schema_version":"1.0","source":{"id":"2202.03587","kind":"arxiv","version":1}},"canonical_sha256":"6430d898a1b7e02b552a7f9e2e166503c29f96d51bcbe7d8292a766e647846bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6430d898a1b7e02b552a7f9e2e166503c29f96d51bcbe7d8292a766e647846bd","first_computed_at":"2026-07-05T03:54:45.751181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:54:45.751181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nDo2sNIDSahdBlGVqEjabm21dfyoKouM57ef0s2lQWJIDWgQlOdjb3llFTrOZUBDnu+xUPVPDAnHzc/w0KkxBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:54:45.751536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.03587","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00fc65b0db483845e63f4ca2e7178f83973fa8bd282206dde83076ed3022120d","sha256:53636d2dfedd24142c4b836bcdfbb5697ff38ed7377be703937c98a7568397ba"],"state_sha256":"23384d56f1176b172e308045f78eaf88e1bcd9e6785683c050b6f617a618b637"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+hhfat7JyVvjnhhdlmE3a4z9sLjg4buT4Ey+ptd5qPxuMayQC+Vq2oC69VV6mI8pB8fIvdu8+d5XQwA1vwCyDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T22:19:35.821415Z","bundle_sha256":"d0d3f1804d63d35c842d38b040e4c3be8cca61d00f6b386cb79c2b080576b190"}}