{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GTMPJVJLOB57R4Z7EHFCWP3OWI","short_pith_number":"pith:GTMPJVJL","canonical_record":{"source":{"id":"2605.20414","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-19T19:10:30Z","cross_cats_sorted":[],"title_canon_sha256":"23786602b7c456f36e3d33a91b99b6027334486620ea5838bb47c70940929b0a","abstract_canon_sha256":"79da8435692cb3e0131cc9babade5cf83d03c27eba182f8e3599a598db9cdfd4"},"schema_version":"1.0"},"canonical_sha256":"34d8f4d52b707bf8f33f21ca2b3f6eb2147a10441ff12866c8038456a393a033","source":{"kind":"arxiv","id":"2605.20414","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20414","created_at":"2026-05-21T01:04:37Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20414v1","created_at":"2026-05-21T01:04:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20414","created_at":"2026-05-21T01:04:37Z"},{"alias_kind":"pith_short_12","alias_value":"GTMPJVJLOB57","created_at":"2026-05-21T01:04:37Z"},{"alias_kind":"pith_short_16","alias_value":"GTMPJVJLOB57R4Z7","created_at":"2026-05-21T01:04:37Z"},{"alias_kind":"pith_short_8","alias_value":"GTMPJVJL","created_at":"2026-05-21T01:04:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GTMPJVJLOB57R4Z7EHFCWP3OWI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.20414","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-19T19:10:30Z","cross_cats_sorted":[],"title_canon_sha256":"23786602b7c456f36e3d33a91b99b6027334486620ea5838bb47c70940929b0a","abstract_canon_sha256":"79da8435692cb3e0131cc9babade5cf83d03c27eba182f8e3599a598db9cdfd4"},"schema_version":"1.0"},"canonical_sha256":"34d8f4d52b707bf8f33f21ca2b3f6eb2147a10441ff12866c8038456a393a033","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:37.142155Z","signature_b64":"uzbK3mPzYuTDkIoweE8RYgYTK+Mk4WWE6W3Zt2jDTJKLloCvCqbHZZeJmpBzpRPaWIuqxt6hX6pvqET0pH5LAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34d8f4d52b707bf8f33f21ca2b3f6eb2147a10441ff12866c8038456a393a033","last_reissued_at":"2026-05-21T01:04:37.141693Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:37.141693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.20414","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":"2026-05-21T01:04:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v1lj38oHaVbjSEYyS5jfl5ihfNaKWHTqDDfPRTbdMx5p8R+Z4n+Li7t7tNM7GpKIiUHbpTqO4Rvmb6OwPY3uCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:21:02.179655Z"},"content_sha256":"ef7dcd4d65e056c45358360a268417c99e2f25268b60ab6da167c81d50cbf1e7","schema_version":"1.0","event_id":"sha256:ef7dcd4d65e056c45358360a268417c99e2f25268b60ab6da167c81d50cbf1e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GTMPJVJLOB57R4Z7EHFCWP3OWI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PlanRAG-Audio: Planning and Retrieval Augmented Generation for Long-form Audio Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Arora, Chien-yu, Cornell, Grant P, Huang, Jing, Liu, Markus, Masao, M\\\"uller, Nathan, Rupak V, Samuele, Shinji, Siddhant, Someki, Strimel, Susanj, Swaminathan, Watanabe","submitted_at":"2026-05-19T19:10:30Z","abstract_excerpt":"Long-form audio understanding poses significant challenges for large audio language models (LALMs) due to the extreme length of audio sequences and the need to reason over heterogeneous acoustic cues distributed over time, such as speech content, speaker identity, emotion, and sound events. To address these challenges, we propose \\textbf{PlanRAG-Audio}, a planning-based retrieval-augmented generation framework for scalable long-form audio understanding. Rather than having audio LALMs process entire recordings directly, PlanRAG-Audio explicitly plans which modalities and temporal spans are requ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20414","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/2605.20414/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":"2026-05-21T01:04:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ON9WLLppYdQSMavfTpiPVAIp7+wk4y+qYBOb6HZyDvcyLamYz+czSkw98yG9C3kfizjPw4ihHkz8lOGbc7byAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:21:02.180458Z"},"content_sha256":"96253b731e3010a3240f483fb4935b5c1b714bc8e3b55b735c6502d9d7e19ebc","schema_version":"1.0","event_id":"sha256:96253b731e3010a3240f483fb4935b5c1b714bc8e3b55b735c6502d9d7e19ebc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GTMPJVJLOB57R4Z7EHFCWP3OWI/bundle.json","state_url":"https://pith.science/pith/GTMPJVJLOB57R4Z7EHFCWP3OWI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GTMPJVJLOB57R4Z7EHFCWP3OWI/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":"2026-05-25T21:21:02Z","links":{"resolver":"https://pith.science/pith/GTMPJVJLOB57R4Z7EHFCWP3OWI","bundle":"https://pith.science/pith/GTMPJVJLOB57R4Z7EHFCWP3OWI/bundle.json","state":"https://pith.science/pith/GTMPJVJLOB57R4Z7EHFCWP3OWI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GTMPJVJLOB57R4Z7EHFCWP3OWI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GTMPJVJLOB57R4Z7EHFCWP3OWI","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":"79da8435692cb3e0131cc9babade5cf83d03c27eba182f8e3599a598db9cdfd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-19T19:10:30Z","title_canon_sha256":"23786602b7c456f36e3d33a91b99b6027334486620ea5838bb47c70940929b0a"},"schema_version":"1.0","source":{"id":"2605.20414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20414","created_at":"2026-05-21T01:04:37Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20414v1","created_at":"2026-05-21T01:04:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20414","created_at":"2026-05-21T01:04:37Z"},{"alias_kind":"pith_short_12","alias_value":"GTMPJVJLOB57","created_at":"2026-05-21T01:04:37Z"},{"alias_kind":"pith_short_16","alias_value":"GTMPJVJLOB57R4Z7","created_at":"2026-05-21T01:04:37Z"},{"alias_kind":"pith_short_8","alias_value":"GTMPJVJL","created_at":"2026-05-21T01:04:37Z"}],"graph_snapshots":[{"event_id":"sha256:96253b731e3010a3240f483fb4935b5c1b714bc8e3b55b735c6502d9d7e19ebc","target":"graph","created_at":"2026-05-21T01:04:37Z","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/2605.20414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-form audio understanding poses significant challenges for large audio language models (LALMs) due to the extreme length of audio sequences and the need to reason over heterogeneous acoustic cues distributed over time, such as speech content, speaker identity, emotion, and sound events. To address these challenges, we propose \\textbf{PlanRAG-Audio}, a planning-based retrieval-augmented generation framework for scalable long-form audio understanding. Rather than having audio LALMs process entire recordings directly, PlanRAG-Audio explicitly plans which modalities and temporal spans are requ","authors_text":"Arora, Chien-yu, Cornell, Grant P, Huang, Jing, Liu, Markus, Masao, M\\\"uller, Nathan, Rupak V, Samuele, Shinji, Siddhant, Someki, Strimel, Susanj, Swaminathan, Watanabe","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-19T19:10:30Z","title":"PlanRAG-Audio: Planning and Retrieval Augmented Generation for Long-form Audio Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20414","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:ef7dcd4d65e056c45358360a268417c99e2f25268b60ab6da167c81d50cbf1e7","target":"record","created_at":"2026-05-21T01:04:37Z","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":"79da8435692cb3e0131cc9babade5cf83d03c27eba182f8e3599a598db9cdfd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-19T19:10:30Z","title_canon_sha256":"23786602b7c456f36e3d33a91b99b6027334486620ea5838bb47c70940929b0a"},"schema_version":"1.0","source":{"id":"2605.20414","kind":"arxiv","version":1}},"canonical_sha256":"34d8f4d52b707bf8f33f21ca2b3f6eb2147a10441ff12866c8038456a393a033","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34d8f4d52b707bf8f33f21ca2b3f6eb2147a10441ff12866c8038456a393a033","first_computed_at":"2026-05-21T01:04:37.141693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:37.141693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uzbK3mPzYuTDkIoweE8RYgYTK+Mk4WWE6W3Zt2jDTJKLloCvCqbHZZeJmpBzpRPaWIuqxt6hX6pvqET0pH5LAg==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:37.142155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef7dcd4d65e056c45358360a268417c99e2f25268b60ab6da167c81d50cbf1e7","sha256:96253b731e3010a3240f483fb4935b5c1b714bc8e3b55b735c6502d9d7e19ebc"],"state_sha256":"ddf9fe5f7eefb77a22141abbc9c656f13696287359a81ac0c3fcba8dc5647351"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/68ZYBfqcGRhpBjFAzgmiRN9QBl7JoCd3WxgmfVO0NTSQ/9VV5Txdh/t0nCH1r0p+nyWDTVriropOvG0vT6GDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:21:02.184373Z","bundle_sha256":"388eab39b569e8220ba33e1b03f821df20830ba06c1490dcb2853ac346e953d1"}}