{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VXT5XMDHWZ4VXLYB6E73GN7LEN","short_pith_number":"pith:VXT5XMDH","canonical_record":{"source":{"id":"2608.04378","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-05T02:38:20Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"e37dc857ee32b0ec2fc28a8f204e0dd58d118a10a600810062c6b441717dda6a","abstract_canon_sha256":"195e0a8acbcfb6344d857b4803fcb01dce1ac67c216a45e3fcbea04aea9fb88e"},"schema_version":"1.0"},"canonical_sha256":"ade7dbb067b6795baf01f13fb337eb2347707c51154f1d81fd8fe15aeb74238f","source":{"kind":"arxiv","id":"2608.04378","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04378","created_at":"2026-08-06T01:34:28Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04378v1","created_at":"2026-08-06T01:34:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04378","created_at":"2026-08-06T01:34:28Z"},{"alias_kind":"pith_short_12","alias_value":"VXT5XMDHWZ4V","created_at":"2026-08-06T01:34:28Z"},{"alias_kind":"pith_short_16","alias_value":"VXT5XMDHWZ4VXLYB","created_at":"2026-08-06T01:34:28Z"},{"alias_kind":"pith_short_8","alias_value":"VXT5XMDH","created_at":"2026-08-06T01:34:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VXT5XMDHWZ4VXLYB6E73GN7LEN","target":"record","payload":{"canonical_record":{"source":{"id":"2608.04378","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-05T02:38:20Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"e37dc857ee32b0ec2fc28a8f204e0dd58d118a10a600810062c6b441717dda6a","abstract_canon_sha256":"195e0a8acbcfb6344d857b4803fcb01dce1ac67c216a45e3fcbea04aea9fb88e"},"schema_version":"1.0"},"canonical_sha256":"ade7dbb067b6795baf01f13fb337eb2347707c51154f1d81fd8fe15aeb74238f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:34:28.586930Z","signature_b64":"AqEXZ/twSidV6WlMKuiUWILG2KwCLxXWmA5R9ObYk29Ri9xDHvdgjFuxXQs5eUCFERZwBwECT36aM7rIxq1aCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ade7dbb067b6795baf01f13fb337eb2347707c51154f1d81fd8fe15aeb74238f","last_reissued_at":"2026-08-06T01:34:28.585524Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:34:28.585524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.04378","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":"2026-08-06T01:34:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZI5RtEBVUuwHrbJpP6ezGAxhw0KKdIpzE8gm0MuWvKP8p4qZL3AcrfLZ/DnmjxOGFD3MRDJ1J/oRnFgbsXFJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:58:34.120662Z"},"content_sha256":"712dda3592094e7ed0cd48f7b26465faf62a092e2dfcd7e726e468ecf334732d","schema_version":"1.0","event_id":"sha256:712dda3592094e7ed0cd48f7b26465faf62a092e2dfcd7e726e468ecf334732d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VXT5XMDHWZ4VXLYB6E73GN7LEN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Helping Music Co-Creation Agents 'Listen' Well: Hierarchical Self-Supervised World Models for Understanding and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Scott H. Hawley","submitted_at":"2026-08-05T02:38:20Z","abstract_excerpt":"Collaborative music agents need internal representations rich enough to support both understanding and generation, yet flexible enough for a workflow where the human retains agency. We present a hierarchical self-supervised ``world model'' for symbolic music: a 2.55M-parameter Swin V2 encoder trained on MIDI piano-roll images with JEPA-style objectives (pitch- and time-shift equivariance, masked embedding prediction, and a distributional regularizer), using no labels and no music-theory vocabulary. Probing the frozen embeddings shows that the level at which a musical property becomes decodable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04378","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/2608.04378/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":"2026-08-06T01:34:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mckwdu9shW9itaID4TVThkGYuPKFc4czbLdhnhPc3uFv5wqbcDIYaox8+E1uUqtcaEv4axS2LGbnQK4wmbajAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:58:34.121138Z"},"content_sha256":"e98f9ba94c285b1e6c378d758163bc24388c8af3becd4bd974c549db1936fc9b","schema_version":"1.0","event_id":"sha256:e98f9ba94c285b1e6c378d758163bc24388c8af3becd4bd974c549db1936fc9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VXT5XMDHWZ4VXLYB6E73GN7LEN/bundle.json","state_url":"https://pith.science/pith/VXT5XMDHWZ4VXLYB6E73GN7LEN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VXT5XMDHWZ4VXLYB6E73GN7LEN/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":"2026-08-18T18:58:34Z","links":{"resolver":"https://pith.science/pith/VXT5XMDHWZ4VXLYB6E73GN7LEN","bundle":"https://pith.science/pith/VXT5XMDHWZ4VXLYB6E73GN7LEN/bundle.json","state":"https://pith.science/pith/VXT5XMDHWZ4VXLYB6E73GN7LEN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VXT5XMDHWZ4VXLYB6E73GN7LEN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VXT5XMDHWZ4VXLYB6E73GN7LEN","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":"195e0a8acbcfb6344d857b4803fcb01dce1ac67c216a45e3fcbea04aea9fb88e","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-05T02:38:20Z","title_canon_sha256":"e37dc857ee32b0ec2fc28a8f204e0dd58d118a10a600810062c6b441717dda6a"},"schema_version":"1.0","source":{"id":"2608.04378","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04378","created_at":"2026-08-06T01:34:28Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04378v1","created_at":"2026-08-06T01:34:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04378","created_at":"2026-08-06T01:34:28Z"},{"alias_kind":"pith_short_12","alias_value":"VXT5XMDHWZ4V","created_at":"2026-08-06T01:34:28Z"},{"alias_kind":"pith_short_16","alias_value":"VXT5XMDHWZ4VXLYB","created_at":"2026-08-06T01:34:28Z"},{"alias_kind":"pith_short_8","alias_value":"VXT5XMDH","created_at":"2026-08-06T01:34:28Z"}],"graph_snapshots":[{"event_id":"sha256:e98f9ba94c285b1e6c378d758163bc24388c8af3becd4bd974c549db1936fc9b","target":"graph","created_at":"2026-08-06T01:34:28Z","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/2608.04378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Collaborative music agents need internal representations rich enough to support both understanding and generation, yet flexible enough for a workflow where the human retains agency. We present a hierarchical self-supervised ``world model'' for symbolic music: a 2.55M-parameter Swin V2 encoder trained on MIDI piano-roll images with JEPA-style objectives (pitch- and time-shift equivariance, masked embedding prediction, and a distributional regularizer), using no labels and no music-theory vocabulary. Probing the frozen embeddings shows that the level at which a musical property becomes decodable","authors_text":"Scott H. Hawley","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-05T02:38:20Z","title":"Helping Music Co-Creation Agents 'Listen' Well: Hierarchical Self-Supervised World Models for Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04378","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":"sha256:712dda3592094e7ed0cd48f7b26465faf62a092e2dfcd7e726e468ecf334732d","target":"record","created_at":"2026-08-06T01:34:28Z","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":"195e0a8acbcfb6344d857b4803fcb01dce1ac67c216a45e3fcbea04aea9fb88e","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-05T02:38:20Z","title_canon_sha256":"e37dc857ee32b0ec2fc28a8f204e0dd58d118a10a600810062c6b441717dda6a"},"schema_version":"1.0","source":{"id":"2608.04378","kind":"arxiv","version":1}},"canonical_sha256":"ade7dbb067b6795baf01f13fb337eb2347707c51154f1d81fd8fe15aeb74238f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ade7dbb067b6795baf01f13fb337eb2347707c51154f1d81fd8fe15aeb74238f","first_computed_at":"2026-08-06T01:34:28.585524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:34:28.585524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AqEXZ/twSidV6WlMKuiUWILG2KwCLxXWmA5R9ObYk29Ri9xDHvdgjFuxXQs5eUCFERZwBwECT36aM7rIxq1aCg==","signature_status":"signed_v1","signed_at":"2026-08-06T01:34:28.586930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.04378","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:712dda3592094e7ed0cd48f7b26465faf62a092e2dfcd7e726e468ecf334732d","sha256:e98f9ba94c285b1e6c378d758163bc24388c8af3becd4bd974c549db1936fc9b"],"state_sha256":"ef86a3ce8bbfc9a3f544a86b8fc7f012159fc5706248d2be5037ce75a27d04dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IA35Tz3h+WZQqzeBgJC5UYd06p4y8D6QoWI5TmiVw32AEJT1dyALcw7TveHriGjWOeap7vQp6z9vvTL4JurSAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:58:34.124436Z","bundle_sha256":"9ff99035b1410708d7ea08aaace218683a84f589bf83ca35145f4aeef5ad9d29"}}