{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EXJSB4FEWWQ5HLPJDXS3TCAHAG","short_pith_number":"pith:EXJSB4FE","canonical_record":{"source":{"id":"2606.06615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T18:05:39Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"82d3b00d9f42be69d1f22b05ec58e13c6e4f21239cb1f34527a389da443ef742","abstract_canon_sha256":"6eb6d853295c1809ba78876200c35030da40f34ebdba25e1da63baf92fbf9985"},"schema_version":"1.0"},"canonical_sha256":"25d320f0a4b5a1d3ade91de5b988070193061f3096417bf84a9a7adcd62307bc","source":{"kind":"arxiv","id":"2606.06615","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06615","created_at":"2026-06-08T00:03:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06615v1","created_at":"2026-06-08T00:03:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06615","created_at":"2026-06-08T00:03:47Z"},{"alias_kind":"pith_short_12","alias_value":"EXJSB4FEWWQ5","created_at":"2026-06-08T00:03:47Z"},{"alias_kind":"pith_short_16","alias_value":"EXJSB4FEWWQ5HLPJ","created_at":"2026-06-08T00:03:47Z"},{"alias_kind":"pith_short_8","alias_value":"EXJSB4FE","created_at":"2026-06-08T00:03:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EXJSB4FEWWQ5HLPJDXS3TCAHAG","target":"record","payload":{"canonical_record":{"source":{"id":"2606.06615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T18:05:39Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"82d3b00d9f42be69d1f22b05ec58e13c6e4f21239cb1f34527a389da443ef742","abstract_canon_sha256":"6eb6d853295c1809ba78876200c35030da40f34ebdba25e1da63baf92fbf9985"},"schema_version":"1.0"},"canonical_sha256":"25d320f0a4b5a1d3ade91de5b988070193061f3096417bf84a9a7adcd62307bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T00:03:47.827089Z","signature_b64":"iv7oJBQSiNAKpdTLifUAQGzP1wlbatDZarHlpQfut27wKN9CWmx0kInIENYth4P3n9t71sftA4yV+VXuE07FAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25d320f0a4b5a1d3ade91de5b988070193061f3096417bf84a9a7adcd62307bc","last_reissued_at":"2026-06-08T00:03:47.826281Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T00:03:47.826281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.06615","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":"2026-06-08T00:03:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b0jBY18KqyHl/+8R4+kUz27FLwnh00HHfDQfdZTAxgn3R0nlGQm3EB3SVKawRmzI4tNClYVBMeRT+s8sDlJ9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T00:24:07.681007Z"},"content_sha256":"2d4c9b6e24ea406fe6234d494f963760cf510c6eff4580b63032d0b7aa3e84a1","schema_version":"1.0","event_id":"sha256:2d4c9b6e24ea406fe6234d494f963760cf510c6eff4580b63032d0b7aa3e84a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EXJSB4FEWWQ5HLPJDXS3TCAHAG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FIGMA: Towards FIne-Grained Music retrievAl","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ashish Seth, Dinesh Manocha, Nishit Anand, Ramani Duraiswami, Sreyan Ghosh","submitted_at":"2026-06-04T18:05:39Z","abstract_excerpt":"Retrieving music using natural language descriptions has improved with contrastive audio-text models such as CLAP, but current systems remain limited to coarse semantic queries. When descriptions specify fine-grained musical attributes such as tempo, key, chord progression, or rhythmic structure, existing models often fail to retrieve the correct audio. We show that this limitation stems from the contrastive learning objective itself: despite being trained on long captions, CLAP-based models effectively utilize only the first few tokens, discarding much of the information encoded in detailed p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06615","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/2606.06615/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":"2026-06-08T00:03:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2S5tu41yVTkwwTGeG+qIoO/c/2dMGEQb2MrSuridJmn4sd5EQ/mbcz+QQFNzaNpu9YiKCChJhE1MIhd3f+RNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T00:24:07.681708Z"},"content_sha256":"41153f689d5e97500d35a502988be910fc4b963769c9d16635b8b8161a6524d6","schema_version":"1.0","event_id":"sha256:41153f689d5e97500d35a502988be910fc4b963769c9d16635b8b8161a6524d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EXJSB4FEWWQ5HLPJDXS3TCAHAG/bundle.json","state_url":"https://pith.science/pith/EXJSB4FEWWQ5HLPJDXS3TCAHAG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EXJSB4FEWWQ5HLPJDXS3TCAHAG/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":"2026-06-11T00:24:07Z","links":{"resolver":"https://pith.science/pith/EXJSB4FEWWQ5HLPJDXS3TCAHAG","bundle":"https://pith.science/pith/EXJSB4FEWWQ5HLPJDXS3TCAHAG/bundle.json","state":"https://pith.science/pith/EXJSB4FEWWQ5HLPJDXS3TCAHAG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EXJSB4FEWWQ5HLPJDXS3TCAHAG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EXJSB4FEWWQ5HLPJDXS3TCAHAG","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":"6eb6d853295c1809ba78876200c35030da40f34ebdba25e1da63baf92fbf9985","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T18:05:39Z","title_canon_sha256":"82d3b00d9f42be69d1f22b05ec58e13c6e4f21239cb1f34527a389da443ef742"},"schema_version":"1.0","source":{"id":"2606.06615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06615","created_at":"2026-06-08T00:03:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06615v1","created_at":"2026-06-08T00:03:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06615","created_at":"2026-06-08T00:03:47Z"},{"alias_kind":"pith_short_12","alias_value":"EXJSB4FEWWQ5","created_at":"2026-06-08T00:03:47Z"},{"alias_kind":"pith_short_16","alias_value":"EXJSB4FEWWQ5HLPJ","created_at":"2026-06-08T00:03:47Z"},{"alias_kind":"pith_short_8","alias_value":"EXJSB4FE","created_at":"2026-06-08T00:03:47Z"}],"graph_snapshots":[{"event_id":"sha256:41153f689d5e97500d35a502988be910fc4b963769c9d16635b8b8161a6524d6","target":"graph","created_at":"2026-06-08T00:03:47Z","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/2606.06615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieving music using natural language descriptions has improved with contrastive audio-text models such as CLAP, but current systems remain limited to coarse semantic queries. When descriptions specify fine-grained musical attributes such as tempo, key, chord progression, or rhythmic structure, existing models often fail to retrieve the correct audio. We show that this limitation stems from the contrastive learning objective itself: despite being trained on long captions, CLAP-based models effectively utilize only the first few tokens, discarding much of the information encoded in detailed p","authors_text":"Ashish Seth, Dinesh Manocha, Nishit Anand, Ramani Duraiswami, Sreyan Ghosh","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T18:05:39Z","title":"FIGMA: Towards FIne-Grained Music retrievAl"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06615","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":"sha256:2d4c9b6e24ea406fe6234d494f963760cf510c6eff4580b63032d0b7aa3e84a1","target":"record","created_at":"2026-06-08T00:03:47Z","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":"6eb6d853295c1809ba78876200c35030da40f34ebdba25e1da63baf92fbf9985","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T18:05:39Z","title_canon_sha256":"82d3b00d9f42be69d1f22b05ec58e13c6e4f21239cb1f34527a389da443ef742"},"schema_version":"1.0","source":{"id":"2606.06615","kind":"arxiv","version":1}},"canonical_sha256":"25d320f0a4b5a1d3ade91de5b988070193061f3096417bf84a9a7adcd62307bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25d320f0a4b5a1d3ade91de5b988070193061f3096417bf84a9a7adcd62307bc","first_computed_at":"2026-06-08T00:03:47.826281Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T00:03:47.826281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iv7oJBQSiNAKpdTLifUAQGzP1wlbatDZarHlpQfut27wKN9CWmx0kInIENYth4P3n9t71sftA4yV+VXuE07FAw==","signature_status":"signed_v1","signed_at":"2026-06-08T00:03:47.827089Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d4c9b6e24ea406fe6234d494f963760cf510c6eff4580b63032d0b7aa3e84a1","sha256:41153f689d5e97500d35a502988be910fc4b963769c9d16635b8b8161a6524d6"],"state_sha256":"2c5e65b871cf44385cc01faa60cdf6bb686c540dca63a726043f51dbbe33f437"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tYEb+ULSBoQQ5xDdevpiIFVdJFsah2NyPYYnXTc23sITRym83RcyjkhRpyRhGC4//uhGNjzWAxxJ/JfthvlGAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T00:24:07.685835Z","bundle_sha256":"c1cd94570e645744b2fa5e84f366a401111a2d6e66e4cde94152c300cff8917d"}}