{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BS5QKG6R3QP5BKZBBACRXEZXQ7","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":"dfde26fe5bb0c85f5c3cd788d6c6844275027b1702b83c43d12141c276607a39","cross_cats_sorted":["cs.AI","cs.CV","cs.GR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-30T17:02:13Z","title_canon_sha256":"84c37f1a3c77ac7564bcbab370448e6bf3af4d2f4520990450d14b2ad57962ab"},"schema_version":"1.0","source":{"id":"2409.20502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.20502","created_at":"2026-07-05T09:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2409.20502v1","created_at":"2026-07-05T09:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20502","created_at":"2026-07-05T09:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"BS5QKG6R3QP5","created_at":"2026-07-05T09:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"BS5QKG6R3QP5BKZB","created_at":"2026-07-05T09:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"BS5QKG6R","created_at":"2026-07-05T09:13:44Z"}],"graph_snapshots":[{"event_id":"sha256:9efd3eac3318cd67a72d8bf3193999161b0262b8e75dbd62c65061b8339dc2ef","target":"graph","created_at":"2026-07-05T09:13:44Z","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/2409.20502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel framework COLLAGE for generating collaborative agent-object-agent interactions by leveraging large language models (LLMs) and hierarchical motion-specific vector-quantized variational autoencoders (VQ-VAEs). Our model addresses the lack of rich datasets in this domain by incorporating the knowledge and reasoning abilities of LLMs to guide a generative diffusion model. The hierarchical VQ-VAE architecture captures different motion-specific characteristics at multiple levels of abstraction, avoiding redundant concepts and enabling efficient multi-resolution representation. We ","authors_text":"Aniket Bera, Damon Conover, Divyanshu Daiya","cross_cats":["cs.AI","cs.CV","cs.GR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-30T17:02:13Z","title":"COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20502","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:d6c5ec01043ff3db3b747bab98a9dd9b773bf9e5d5983e6911f751963f03acbe","target":"record","created_at":"2026-07-05T09:13:44Z","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":"dfde26fe5bb0c85f5c3cd788d6c6844275027b1702b83c43d12141c276607a39","cross_cats_sorted":["cs.AI","cs.CV","cs.GR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-30T17:02:13Z","title_canon_sha256":"84c37f1a3c77ac7564bcbab370448e6bf3af4d2f4520990450d14b2ad57962ab"},"schema_version":"1.0","source":{"id":"2409.20502","kind":"arxiv","version":1}},"canonical_sha256":"0cbb051bd1dc1fd0ab2108051b933787d96fa97f438ce9cad68bf50b2856767f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cbb051bd1dc1fd0ab2108051b933787d96fa97f438ce9cad68bf50b2856767f","first_computed_at":"2026-07-05T09:13:44.550434Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:44.550434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/ZFW+b3GALDdbasPhKf0FaJfA0WPiWT6ipqZSIBBJYwYe5g+g0+hTOqZGQS3rwKL2S+XHy8mBVKXTenf9AQRAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:44.551021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.20502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6c5ec01043ff3db3b747bab98a9dd9b773bf9e5d5983e6911f751963f03acbe","sha256:9efd3eac3318cd67a72d8bf3193999161b0262b8e75dbd62c65061b8339dc2ef"],"state_sha256":"530d67a07b66b6135be607effaf09a68fb22eb1b970186d1afddf5f0e4931002"}